Learning

AI vs Machine Learning

Learn more about watsonx: https://ibm.biz/BdvxDS What is really the difference between Artificial intelligence (AI) and machine learning (ML)? Are they actually the same thing? In this video, Jeff Crume explains the differences and relationship between AI & ML, as well as how related topics like Deep Learning (DL) and other types and properties of each. #ai #ml #dl #artificialintelligence #machinelearning #deeplearning #watsonx

Learning How to Learn: Powerful mental tools to help you master tough subjects

This course gives you easy access to the invaluable learning techniques used by experts in art, music, literature, math, science, sports, and many other disciplines. We’ll learn about how the brain uses two very different learning modes and how it encapsulates (“chunks”) information. We’ll also cover illusions of learning, memory techniques, dealing with procrastination, and best practices shown by research to be most effective in helping you master tough subjects.

Introduction to TensorFlow for Artificial Intelligence, Machine Learning, and Deep Learning

If you are a software developer who wants to build scalable AI-powered algorithms, you need to understand how to use the tools to build them. This course is part of the DeepLearning.AI TensorFlow Developer Specialization and will teach you best practices for using TensorFlow, a popular open-source framework for machine learning.

Introduction to AI and Machine Learning on Google Cloud

This course introduces the artificial intelligence (AI) and machine learning (ML) offerings on Google Cloud that support the data-to-AI lifecycle through AI foundations, AI development, and AI solutions. It explores the technologies, products, and tools available to build an ML model, an ML pipeline, and a generative AI project based on the different goals of users, including data scientists, AI developers, and ML engineers.

Introduction to Deep Learning & Neural Networks with Keras

Looking to start a career in Deep Learning? Look no further. This course will introduce you to the field of deep learning and help you answer many questions that people are asking nowadays, like what is deep learning, and how do deep learning models compare to artificial neural networks? You will learn about the different deep learning models and build your first deep learning model using the Keras library.

Fundamentals of Machine Learning and Artificial Intelligence

In this course, you will learn about the foundations of machine learning (ML) and artificial intelligence (AI). You will explore the connections between AI, ML, deep learning, and the emerging field of generative artificial intelligence (generative AI), which has captured the attention of businesses and individuals alike. You will gain a solid understanding of foundational AI terms, laying the groundwork for a deeper dive into these concepts. Additionally, you will learn about a selection of Amazon Web Services (AWS) services that use AI and ML capabilities. You will gain practical insights into how these tools can be used to solve real-world problems and drive innovation across various industries.

I’m sharing my learnings on how to use ChatGPT and other AI tools to generate leads, automate and grow my business.

Ok! I've been diving deep into how I can streamline and optimize my lead gen processes, and the things I've discovered have been mind-blowing. Recently came across a term called "EmotionAI". Wondered if anyone here has jumped on this and started implementing for lead gen? According to Exploding Topics, searches for "emotion AI" have increased by 525% over the past five years. Simply put, the tech can be used to provide more personalized experiences. And we all know that more personalized outreach means more likely conversions. As the AI market continues to grow, this will become increasingly mainstream. So, I thought why not share my learnings and real-life examples of how to use some these AI coupled with good ol’ chatGPT to grow. The first newsletter issue went out today. I plan to send every other Saturday but I might send every Saturday, still undecided. Anyway please check it out and subscribe if you want. Also let me know if you found it insightful.

"No Coding" AI And Machine Learning through Excel

Hi All, I am looking for some feedback from users on our new product. If you are looking for an easy way to build and execute machine learning, AI, and analytics through Excel please register for a free account and trial on axcel.io. Please note that you do not need any coding skills and all the computation is in the cloud. So you are not limited to Excel functionality. We have already built more than 70 models and are looking to expand based on your feedback. Thanks! Axcel Team

MIT Machine Learning graduate teaches machine learning and deep learning (for free)

I believe that anyone can transition to machine learning, if they decide to do so. For the last 3 months, I started a project to teach machine learning and deep learning. I recorded 70 videos in machine learning and deep learning. Every day, I scripted, recorded and edited 1 video for about 6-7 hours. The result is 2 massive playlists. 1️⃣ Machine Learning Teach by Doing playlist: (a) Topics covered: Regression, Classification, Neural Networks, Convolutional Neural Networks (b) Number of lectures: 35 (c) Lecture instructor: Me (IIT Madras BTech, MIT AI PhD) (d) Playlist link: https://www.youtube.com/playlist?list=PLPTV0NXA\ZSi-nLQ4XV2Mds8Z7bihK68L 2️⃣ Neural Networks from scratch playlist: (a) Topics covered: Neural Network architecture, forward pass, backward pass, optimizers. Completely coded in Python from scratch. No Pytorch. No Tensorflow. Only Numpy. (b) Number of lectures: 35 (c) Lecture instructor: Me (IIT Madras BTech, MIT AI PhD) Playlist link: https://www.youtube.com/playlist?list=PLPTV0NXA\ZSj6tNyn\UadmUeU3Q3oR-hu P.S: Lecturer background: I graduated with a PhD in machine learning from MIT. The video shows my notes in detail. https://i.redd.it/tjxybbqyngcd1.gif

How I Started Learning Machine Learning

Hello, everyone. As promised, I'll write a longer post about how I entered the world of ML, hoping it will help someone shape their path. I'll include links to all the useful materials I used alongside the story, which you can use for learning. I like to call myself an AI Research Scientist who enjoys exploring new AI trends, delving deeper into understanding their background, and applying them to real products. This way, I try to connect science and entrepreneurship because I believe everything that starts as scientific research ends up "on the shelves" as a product that solves a specific user problem. I began my journey in ML in 2016 when it wasn't such a popular field. Everyone had heard of it, but few were applying it. I have several years of development experience and want to try my hand at ML. The first problem I encountered was where to start - whether to learn mathematics, statistics, or something else. That's when I came across a name and a course that completely changed my career. Let's start You guessed it. It was Professor Andrew Ng and his globally popular Machine Learning course available on Coursera (I still have the certificate, hehe). This was also my first official online course ever. Since that course no longer exists as it's been replaced by a new one, I recommend you check out: Machine Learning (Stanford CS229) Machine Learning Specialization These two courses start from the basics of ML and all the necessary calculus you need to know. Many always ask questions like whether to learn linear algebra, statistics, or probability, but you don't need to know everything in depth. This knowledge helps if you're a scientist developing a new architecture, but as an engineer, not really. You need to know some basics to understand, such as how the backpropagation algorithm works. I know that Machine Learning (Stanford CS229) is a very long and arduous course, but it's the right start if you want to be really good at ML. In my time, I filled two thick notebooks by hand while taking the course mentioned above. TensorFlow and Keras After the course, I didn't know how to apply my knowledge because I hadn't learned specifically how to code things. Then, I was looking for ways to learn how to code it. That's when I came across a popular framework called Keras, now part of TensorFlow. I started with a new course and acquiring practical knowledge: Deep Learning Specialization Deep Learning by Ian Goodfellow Machine Learning Yearning by Andrew Ng These resources above were my next step. I must admit that I learned the most from that course and from the book Deep Learning by Ian Goodfellow because I like reading books (although this one is quite difficult to read). Learn by coding To avoid just learning, I went through various GitHub repositories that I manually retyped and learned that way. It may be an old-fashioned technique, but it helped me a lot. Now, most of those repositories don't exist, so I'll share some that I found to be good: Really good Jupyter notebooks that can teach you the basics of TensorFlow Another good repo for learning TF and Keras Master the challenge After mastering the basics in terms of programming in TF/Keras, I wanted to try solving some real problems. There's no better place for that challenge than Kaggle and the popular Titanic dataset. Here, you can really find a bunch of materials and simple examples of ML applications. Here are some of my favorites: Titanic - Machine Learning from Disaster Home Credit Default Risk House Prices - Advanced Regression Techniques Two Sigma: Using News to Predict Stock Movements I then decided to further develop my career in the direction of applying ML to the stock market, first using predictions on time series and then using natural language processing. I've remained in this field until today and will defend my doctoral dissertation soon. How to deploy models To continue, before I move on to the topic of specialization, we need to address the topic of deployment. Now that we've learned how to make some basic models in Keras and how to use them, there are many ways and services, but I'll only mention what I use today. For all my ML models, whether simple regression models or complex GPT models, I use FastAPI. It's a straightforward framework, and you can quickly create API endpoints. I'll share a few older and useful tutorials for beginners: AI as an API tutorial series A step-by-step guide Productizing an ML Model with FastAPI and Cloud Run Personally, I've deployed on various cloud providers, of which I would highlight GCP and AWS because they have everything needed for model deployment, and if you know how to use them, they can be quite cheap. Chose your specialization The next step in developing my career, besides choosing finance as the primary area, was my specialization in the field of NLP. This happened in early 2020 when I started working with models based on the Transformer architecture. The first model I worked with was BERT, and the first tasks were related to classifications. My recommendations are to master the Transformer architecture well because 99% of today's LLM models are based on it. Here are some resources: The legendary paper "Attention Is All You Need" Hugging Face Course on Transformers Illustrated Guide to Transformers - Step by Step Explanation Good repository How large language models work, a visual intro to transformers After spending years using encoder-based Transformer models, I started learning GPT models. Good open-source models like Llama 2 then appear. Then, I started fine-tuning these models using the excellent Unsloth library: How to Finetune Llama-3 and Export to Ollama Fine-tune Llama 3.1 Ultra-Efficiently with Unsloth After that, I focused on studying various RAG techniques and developing Agent AI systems. This is now called AI engineering, and, as far as I can see, it has become quite popular. So I'll write more about that in another post, but here I'll leave what I consider to be the three most famous representatives, i.e., their tutorials: LangChain tutorial LangGraph tutorial CrewAI examples Here I am today Thanks to the knowledge I've generated over all these years in the field of ML, I've developed and worked on numerous projects. The most significant publicly available project is developing an agent AI system for well-being support, which I turned into a mobile application. Also, my entire doctoral dissertation is related to applying ML to the stock market in combination with the development of GPT models and reinforcement learning (more on that in a separate post). After long 6 years, I've completed my dissertation, and now I'm just waiting for its defense. I'll share everything I'm working on for the dissertation publicly on the project, and in tutorials I'm preparing to write. If you're interested in these topics, I announce that I'll soon start with activities of publishing content on Medium and a blog, but I'll share all of that here on Reddit as well. Now that I've gathered years of experience and knowledge in this field, I'd like to share it with others and help as much as possible. If you have any questions, feel free to ask them, and I'll try to answer all of them. Thank you for reading.

How's the fast.ai Introduction to Machine Learning for Coders! Course?

It doesnt seem like the usual Machine Learning courses as it there are only two topics : Random forests and Gradient descent in which the whole course is covered. There are many topics missing like Clustering , other classification models.

How I Started Learning Machine Learning

Hello, everyone. As promised, I'll write a longer post about how I entered the world of ML, hoping it will help someone shape their path. I'll include links to all the useful materials I used alongside the story, which you can use for learning. I like to call myself an AI Research Scientist who enjoys exploring new AI trends, delving deeper into understanding their background, and applying them to real products. This way, I try to connect science and entrepreneurship because I believe everything that starts as scientific research ends up "on the shelves" as a product that solves a specific user problem. I began my journey in ML in 2016 when it wasn't such a popular field. Everyone had heard of it, but few were applying it. I have several years of development experience and want to try my hand at ML. The first problem I encountered was where to start - whether to learn mathematics, statistics, or something else. That's when I came across a name and a course that completely changed my career. Let's start You guessed it. It was Professor Andrew Ng and his globally popular Machine Learning course available on Coursera (I still have the certificate, hehe). This was also my first official online course ever. Since that course no longer exists as it's been replaced by a new one, I recommend you check out: Machine Learning (Stanford CS229) Machine Learning Specialization These two courses start from the basics of ML and all the necessary calculus you need to know. Many always ask questions like whether to learn linear algebra, statistics, or probability, but you don't need to know everything in depth. This knowledge helps if you're a scientist developing a new architecture, but as an engineer, not really. You need to know some basics to understand, such as how the backpropagation algorithm works. I know that Machine Learning (Stanford CS229) is a very long and arduous course, but it's the right start if you want to be really good at ML. In my time, I filled two thick notebooks by hand while taking the course mentioned above. TensorFlow and Keras After the course, I didn't know how to apply my knowledge because I hadn't learned specifically how to code things. Then, I was looking for ways to learn how to code it. That's when I came across a popular framework called Keras, now part of TensorFlow. I started with a new course and acquiring practical knowledge: Deep Learning Specialization Deep Learning by Ian Goodfellow Machine Learning Yearning by Andrew Ng These resources above were my next step. I must admit that I learned the most from that course and from the book Deep Learning by Ian Goodfellow because I like reading books (although this one is quite difficult to read). Learn by coding To avoid just learning, I went through various GitHub repositories that I manually retyped and learned that way. It may be an old-fashioned technique, but it helped me a lot. Now, most of those repositories don't exist, so I'll share some that I found to be good: Really good Jupyter notebooks that can teach you the basics of TensorFlow Another good repo for learning TF and Keras Master the challenge After mastering the basics in terms of programming in TF/Keras, I wanted to try solving some real problems. There's no better place for that challenge than Kaggle and the popular Titanic dataset. Here, you can really find a bunch of materials and simple examples of ML applications. Here are some of my favorites: Titanic - Machine Learning from Disaster Home Credit Default Risk House Prices - Advanced Regression Techniques Two Sigma: Using News to Predict Stock Movements I then decided to further develop my career in the direction of applying ML to the stock market, first using predictions on time series and then using natural language processing. I've remained in this field until today and will defend my doctoral dissertation soon. How to deploy models To continue, before I move on to the topic of specialization, we need to address the topic of deployment. Now that we've learned how to make some basic models in Keras and how to use them, there are many ways and services, but I'll only mention what I use today. For all my ML models, whether simple regression models or complex GPT models, I use FastAPI. It's a straightforward framework, and you can quickly create API endpoints. I'll share a few older and useful tutorials for beginners: AI as an API tutorial series A step-by-step guide Productizing an ML Model with FastAPI and Cloud Run Personally, I've deployed on various cloud providers, of which I would highlight GCP and AWS because they have everything needed for model deployment, and if you know how to use them, they can be quite cheap. Chose your specialization The next step in developing my career, besides choosing finance as the primary area, was my specialization in the field of NLP. This happened in early 2020 when I started working with models based on the Transformer architecture. The first model I worked with was BERT, and the first tasks were related to classifications. My recommendations are to master the Transformer architecture well because 99% of today's LLM models are based on it. Here are some resources: The legendary paper "Attention Is All You Need" Hugging Face Course on Transformers Illustrated Guide to Transformers - Step by Step Explanation Good repository How large language models work, a visual intro to transformers After spending years using encoder-based Transformer models, I started learning GPT models. Good open-source models like Llama 2 then appear. Then, I started fine-tuning these models using the excellent Unsloth library: How to Finetune Llama-3 and Export to Ollama Fine-tune Llama 3.1 Ultra-Efficiently with Unsloth After that, I focused on studying various RAG techniques and developing Agent AI systems. This is now called AI engineering, and, as far as I can see, it has become quite popular. So I'll write more about that in another post, but here I'll leave what I consider to be the three most famous representatives, i.e., their tutorials: LangChain tutorial LangGraph tutorial CrewAI examples Here I am today Thanks to the knowledge I've generated over all these years in the field of ML, I've developed and worked on numerous projects. The most significant publicly available project is developing an agent AI system for well-being support, which I turned into a mobile application. Also, my entire doctoral dissertation is related to applying ML to the stock market in combination with the development of GPT models and reinforcement learning (more on that in a separate post). After long 6 years, I've completed my dissertation, and now I'm just waiting for its defense. I'll share everything I'm working on for the dissertation publicly on the project, and in tutorials I'm preparing to write. If you're interested in these topics, I announce that I'll soon start with activities of publishing content on Medium and a blog, but I'll share all of that here on Reddit as well. Now that I've gathered years of experience and knowledge in this field, I'd like to share it with others and help as much as possible. If you have any questions, feel free to ask them, and I'll try to answer all of them. Thank you for reading.

What Reinforcement Learning Method Should I Use for Poker AI with LLMs?

Hey everyone, I’m working on a poker AI project, where I’m training a large language model (LLM) to predict poker actions from given game states (check, call, bet, raise, etc.). My end goal is to create a model that can play poker at a high level, primarily by self-play and opponent modeling. However, I’m running into some challenges that I hope you can help me with! Here's the situation: Training Method: I’m using supervised fine-tuning (SFT) on real poker hand history data to initially teach the LLM how to predict poker actions from game states. This means that the model learns from examples of past games, predicting the actions that players took in various situations. Self-Play Setup: I plan to eventually move to self-play, where the LLM will play against itself (or other types of models that I create to simulate different play styles). I’ll use these self-play sessions to improve the model over time. Opponent Pool: I’m creating 6 types of poker players (Loose Aggressive, Loose Passive, Tight Aggressive, Tight Passive, Maniac, and Nit), each trained at 5 different skill levels (Novice, Beg\*nner, Intermediate, Advanced, Expert). This gives me a decent range of opponent behavior for training. The problem: Here’s the catch: The LLM I’m using only outputs discrete actions (e.g., bet 3BB, raise to 10BB, etc.) with no access to the probabilities of actions, so I can't directly use methods like policy gradients or Q-learning that rely on action probabilities or continuous action spaces. This makes applying traditional RL methods a bit tricky. My question: Given that I don't have access to action probabilities, what RL method or strategy should I pursue to improve my model? Specifically, I’m looking for a way to: Incorporate self-play with reward-based learning. Refine the model through reinforcement learning, without the need for continuous probabilities. Ensure the model doesn’t just overfit to its own prior behavior but learns to adapt and exploit different strategies in poker. I’ve considered a few approaches like reward-weighted supervised fine-tuning or using simpler RL techniques like Monte Carlo updates, but I’m not sure which would work best with the LLM setup I have. I've also considered Q-learning or Deep Q-learning. Any advice or suggestions on which RL approach I should take given my situation would be greatly appreciated! Yes I used AI to write this queston. But it captures everything I want to say, and I suck at writing.

Teaching an AI to Play Mario: A Learning Journey

TLDR: I've always wanted to learn reinforcement learning, but the notation and concepts often seemed overwhelming (and scary). So, \~3 months ago, I set myself a challenge: Train an AI to Speedrun Mario Watch the progression here: https://youtu.be/OQitI066aI0 ​ Full Story: Three months ago, I stared at the dense forest of Reinforcement Learning (RL) papers and felt like Mario facing Bowser for the first time: unequipped and overwhelmingly outmatched. The notation seemed like hieroglyphics, and terms like "policy gradients" felt like they belonged in a sci-fi novel, not a beginner's project. But RL always seemed so cool, and I was really determined to achieve my goal. So, I started with the Sutton & Barto RL textbook, learning things like the Multi-Armed Bandit problem and MDPs working my way up to Actor-Critic methods. That book is literal gold & I highly recommend you work through it (even though it can be tough at times). I tried everything from random courses online to books on amazon & this textbook has been by far the most clear and effective way to learn RL. The biggest issue with the textbook is you learn a lot of theory, but don't learn implementation. So, I would go through a chapter a week & set aside Friday + the weekend to actually implement what I learned (usually by watching youtube tutorials & looking at Github Repos). Eventually, while searching for practical resources for implementing PPO, I stumbled upon a GitHub repository that literally trained an AI to play Mario. Rather than just cloning and running the code, I took a deeper approach. I aimed to understand the repository thoroughly, ensuring each line of code made sense in the context of what I had studied. But of course, this wasn't easy. One of the biggest issues was my hardware limitation. I was working on an old Mac. So, I started using Google Collab, but that had its own problems (session timeouts & limited GPU access). Ultimately, I found AWS Sagemaker to be pretty good. ​ After rewriting the code, I felt confident it would work because I understood every aspect of it. So, I trained the AI to play Mario across a variety of different levels (took a long time and a lot of trial and error with the learning rate). It feels amazing seeing your theoretical knowledge translate into tangible results & this project gave me a big confidence boost. ​ Anyways I made a video showing off the results (Note that I simplified the technical parts for it to reach a wider audience): https://youtu.be/OQitI066aI0 ​ Feel free to drop any questions or feedback, I'm more than happy to help or chat about my experiences. I hope my journey can inspire some of you who might be feeling overwhelmed with the idea of diving into reinforcement learning or any other area of AI. Remember, the hardest part is often taking the first step. Once you start, the momentum will carry you forward. Thank you for reading my super long post and sharing in my little success story! 🚀🕹️🎮

Scratch Machine Learning Algorithms Implementations

Hi there, other Redditors! Like many of you, when I first started working in the AI field, I wanted to build some basic Machine Learning models from scratch in order to better understand how each algorithm works, improve my programming and math skills, or simply produce an eye-catching, difficult project to put in the résumé. After spending some time searching for resources that could help me guide my studies, I discovered that the majority of scratch implementations that are currently available are either i) outdated (having been implemented years ago using Python 2 or an earlier version of Python 3); ii) too difficult to understand (using a lot of difficult, unfriendly optimization techniques or with poorly written code); or iii) too simple (only covering binary classification). With that in mind, I made the decision to develop user-friendly, uncomplicated, organized, and simple implementations from scratch. Aside from all of that, I've always wanted to create an open-source project so that others, particularly novices and those with less than a year's experience (like me), can collaborate with others, contribute to public projects, and experience Git firsthand (some of these implementations were made by other contributors!). Here are some implementations that are available: Algorithms (Random Forest Classifier and Regressor, Decision Tree Classifier and Regressor, KMeans, KNN Classifier and Regressor, Gaussian Naive Bayes, Linear Regression, Logistic Regression, PCA, Perceptron, MLP Classifier and Regressor, SVM Classifier and Regressor); Regression and classification metrics; Distance metrics (such as Euclidean); Data split functions (such as KFold); Activation and loss functions; Scalers (such as MinMaxScaler) and encoders (such as One Hot Encoder); and a few things more! Project's link: https://github.com/rafaelgreca/scratchml Disclaimer: The goal of this library is to provide code that is simpler, easier to understand, and more approachable for artificial intelligence enthusiasts and beginners who want to contribute to an open-source repository or who want to learn more about how algorithms work. It is not meant to replace existing libraries that are better, more optimized, and have a wider variety of implemented algorithms (such as scikit-learn, PyTorch, Keras, and Tensorflow). If you want to use optimized implementations with accurate results, please use one of the previously mentioned libraries. P.S.: I accidentally deleted the other post, so I am posting again. :-)

Learning Resources + Side Project Ideas

I made a post last night about my journey to landing an AI internship and have received a lot of responses asking about side projects and learning resources, so I am making another thread here consolidating this information for all those that are curious! Learning Process Step 1) Learn the basic fundamentals of the Math USE YOUTUBE!!! Literally just type in 'Machine Learning Math" and you will get tons of playlists covering nearly every topic. Personally I would focus on Linear Algebra and Calculus - specifically matrices/vector operations, dot products, eigenvectors/eigenvalues, derivatives and gradients. It might take a few tries until you find someone that meshes well with your learning style, but 3Blue1Brown is my top recommendation. I also read the book "Why Machines Learn" and found that extremely insightful. Work on implementing the math both with pen and paper then in Python. Step 2) Once you have a grip on the math fundamentals, I would pick up Hands-on Machine Learning with Sci-kit Learn, Keras and TensorFlow. This book was a game changer for me. It goes more in depth on the math and covers every topic from Linear Regression to the Transformers architecture. It also introduces you to Kaggle and some beginner level side projects. Step 3) After that book I would begin on side projects and also checking out other similar books, specifically Hands on Large Language Models and Hands on Generative AI. Step 4) If you have read all three of these books, and fully comprehend everything, then I would start looking up papers. I would just ask ChatGPT to feed you papers that are most relevant to your interests. Beginner Side Project Ideas 1) Build a Neural Network from scratch, using just Numpy. It can be super basic - have one input layer with 2 nodes, 1 hidden layer with 2 nodes, and output layer with one node. Learn about the forward feed process and play around with different activation functions and loss functions. Learn how these activation functions and loss functions impact backpropagation (hint: the derivatives of the activation functions and loss functions are all different). Get really good at this and understand the difference between regression models and classification models and which activation/loss functions go with which type of model. If you are really feeling crazy and are more focused on a SWE type of role, try doing it in a language other than python and try building a frontend for it so there is an interface where a user can input data and select their model architecture. 2) Build a CNN Image Classifier for the MNIST - Get familiar with the intricacies of CNN's, image manipulation, and basic computer vision concepts. 3) Build on top of open source LLM's. Go to Hugging Face's models page and start playing around with some. 4) KAGGLE COMPETITIONS - I will not explain further, do Kaggle Competitions. Other Resources I've mentioned YouTube, several books and Hugging Face. I also recommend: DataLemur.com \- Python practice, SQL practices, ML questions - his book Ace the Data Science Interview is also very good. X.com \- follow people that are prominent in the space. I joined an AI and Math Group that is constantly posting resources in there deep-ml.com If you have found any of this helpful - feel free to give me a follow on X and stay in touch @ x.com/hark0nnen\

Starting with Deep Learning in 2025 - Suggestion

I'm aware this has been asked many times here. so I'm not here to ask for a general advice - I've done some homework. My questions is - what do you think about this curriculum I put together (research + GPT)? Context: \- I'm a product manger with technical background and want to get back to a more technical depth. \- BSc in stats, familiar with all basic ML concepts, some maths (linear algebra etc), python. Basically, I got the basics covered a while ago so I'm looking to go back into the basics and I can learn and relearn anything I might need to with the internet. My focus is on getting hands on feel on where AI and deep learning is at in 2025, and understand the "under the hood" of key models used and LLMs specifically. Veterans - whats missing? what's redundant? Thanks so much! 🙏🏻 PS - hoping others will find this useful, you very well might too! |Week/Day|Goals|Resource|Activity| |:-|:-|:-|:-| |Week 1|Foundations of AI and Deep Learning||| |Day 1-2|Learn AI terminology and applications|DeepLearning.AI's "AI for Everyone"|Complete Module 1. Understand basic AI concepts and its applications.| |Day 3-5|Explore deep learning fundamentals|Fast.ai's Practical Deep Learning for Coders (2024)|Watch first 2 lessons. Code an image classifier as your first DL project.| |Day 6-7|Familiarize with ML/LLM terminology|Hugging Face Machine Learning Glossary|Study glossary terms and review foundational ML/LLM concepts.| |Week 2|Practical Deep Learning||| |Day 8-10|Build with PyTorch basics|PyTorch Beginner Tutorials|Complete the 60-minute blitz and create a simple neural network.| |Day 11-12|Explore more projects|Fast.ai Lesson 3|Implement a project such as text classification or tabular data analysis.| |Day 13-14|Fine-tune pre-trained models|Hugging Face Tutorials|Learn and apply fine-tuning techniques for a pre-trained model on a simple dataset.| |Week 3|Understanding LLMs||| |Day 15-17|Learn GPT architecture basics|OpenAI Documentation|Explore GPT architecture and experiment with OpenAI API Playground.| |Day 18-19|Understand tokenization and transformers|Hugging Face NLP Course|Complete the tokenization and transformers sections of the course.| |Day 20-21|Build LLM-based projects|TensorFlow NLP Tutorials|Create a text generator or summarizer using LLM techniques.| |Week 4|Advanced Concepts and Applications||| |Day 22-24|Review cutting-edge LLM research|Stanford's CRFM|Read recent LLM-related research and discuss its product management implications.| |Day 25-27|Apply knowledge to real-world projects|Kaggle|Select a dataset and build an NLP project using Hugging Face tools.| |Day 28-30|Explore advanced API use cases|OpenAI Cookbook and Forums|Experiment with advanced OpenAI API scenarios and engage in discussions to solidify knowledge.|

Join the AI4Earth challenge with the European Space Agency to highlight our footprint on Earth using Earth Observation data and Machine Learning

​ https://preview.redd.it/ww109cba14f71.png?width=2401&format=png&auto=webp&s=8bd3d43e8b63848af85c73478be61e43d9e10189 The primary goal is to get an insight into the human impact on Earth, to drive and guide conservation efforts of this planet we call home. Our approach will be twofold:  Firstly we will work on AI algorithms that can serve as an early detection system of human impact sites. Secondly we will use these detection systems to find satellite images that show the most impactful human-caused changes, which will be used in the creation of a video to launch an awareness campaign. You will be working with ESA to detect things like: Wildfires and Deforestation Marine Litter and Melting Glaciers Air quality detection & Novel animal migration patterns  and much more!  European Space Agency To reach these goals we’ve partnered up with ESA, who are able to use our algorithms to monitor new satellite data and guide conservation efforts. They will provide us with multi-spectral data of their Sentinel-2 satellite pair and with invaluable knowledge and research on the domain of Earth Observation data in participant only masterclasses.  Format The challenge will run throughout September and October, where you will collaborate with a diverse team of over 30 international data specialists and domain experts in subteams, all tackling this problem from different angles. Subtasks like the detection of deforestation, wildfires, marine litter or any other human caused impact. All contributors in the challenge are expected to spend 12 hours or more per week during the entirity of the two month challenge. To learn more subscribe to the info session on the 3rd of August 19:00 CEST HERE! Some important dates: 3rd of August – Info session 1st of September – Challenge Kick-off 29th of September – Midterm presentations 29th of October – Final presentations PARTNERS SUN - https://spacehubs.network The project is spearheaded by SUN whose goal is to increase the commercialization of space enabled solutions and growth of European start-ups and scale-ups in the space downstream and upstream sectors. ESA - https://esa.int ESA will be the main stakeholder and domain knowledge provider in the challenge. Their efforts to aid human’s space endeavours as well as protect the planet we live on will serve us for many years to come.  MLReef - https://mlreef.com MLReef provides an open source platform for collaborative Machine Learning. They provide the computational infrastructure to support the EO4Earth project as part of their AI4GOOD and Open Science initiatives. Brimatech  As a partner in the SUN project, the innovation management and market research expert Brimatech helps out in the overall organisation of the challenge.  Mothership The ‘Mothership’ is a dedicated open innovation program created by Space4Good and World Startup Factory. The Mothershi is leveraging recent advancements in artificial intelligence and satellite technologies in support of the UN Sustainable Development Goals. Space4Good  Space4Good is a geospatial innovation lab supporting impact makers on the ground with earth observation insights from above. Worldstartup  Worldstartup is a collective of international entrepreneurs, experts, mentors and investors, dedicated to help the best impact-driven startups and scaleups.

Study Plan for Learning Data Science Over the Next 12 Months [D]

In this thread, I address a study plan for 2021. In case you're interested, I wrote a whole article about this topic: Study Plan for Learning Data Science Over the Next 12 Months Let me know your thoughts on this. ​ https://preview.redd.it/emg20nzhet661.png?width=1170&format=png&auto=webp&s=cf09e4dc5e82ba2fd7b57c706ba2873be57fe8de We are ending 2020 and it is time to make plans for next year, and one of the most important plans and questions we must ask is what do we want to study?, what do we want to enhance?, what changes do we want to make?, and what is the direction we are going to take (or continue) in our professional careers?. Many of you will be starting on the road to becoming a data scientist, in fact you may be evaluating it, since you have heard a lot about it, but you have some doubts, for example about the amount of job offers that may exist in this area, doubts about the technology itself, and about the path you should follow, considering the wide range of options to learn. I’m a believer that we should learn from various sources, from various mentors, and from various formats. By sources I mean the various virtual platforms and face-to-face options that exist to study. By mentors I mean that it is always a good idea to learn from different points of view and learning from different teachers/mentors, and by formats I mean the choices between books, videos, classes, and other formats where the information is contained. When we extract information from all these sources we reinforce the knowledge learned, but we always need a guide, and this post aims to give you some practical insights and strategies in this regard. To decide on sources, mentors and formats it is up to you to choose. It depends on your preferences and ease of learning: for example, some people are better at learning from books, while others prefer to learn from videos. Some prefer to study on platforms that are practical (following online code), and others prefer traditional platforms: like those at universities (Master’s Degree, PHDs or MOOCs). Others prefer to pay for quality content, while others prefer to look only for free material. That’s why I won’t give a specific recommendation in this post, but I’ll give you the whole picture: a study plan. To start you should consider the time you’ll spend studying and the depth of learning you want to achieve, because if you find yourself without a job you could be available full time to study, which is a huge advantage. On the other hand, if you are working, you’ll have less time and you’ll have to discipline yourself to be able to have the time available in the evenings, mornings or weekends. Ultimately, the important thing is to meet the goal of learning and perhaps dedicating your career to this exciting area! We will divide the year into quarters as follows First Quarter: Learning the Basics Second Quarter: Upgrading the Level: Intermediate Knowledge Third Quarter: A Real World Project — A Full-stack Project Fourth Quarter: Seeking Opportunities While Maintaining Practice First Quarter: Learning the Basics ​ https://preview.redd.it/u7t9bthket661.png?width=998&format=png&auto=webp&s=4ad29cb43618e7acf793259243aa5a60a8535f0a If you want to be more rigorous you can have start and end dates for this period of study of the bases. It could be something like: From January 1 to March 30, 2021 as deadline. During this period you will study the following: A programming language that you can apply to data science: Python or R. We recommend Python due to the simple fact that approximately 80% of data science job offers ask for knowledge in Python. That same percentage is maintained with respect to the real projects you will find implemented in production. And we add the fact that Python is multipurpose, so you won’t “waste” your time if at some point you decide to focus on web development, for example, or desktop development. This would be the first topic to study in the first months of the year. Familiarize yourself with statistics and mathematics. There is a big debate in the data science community about whether we need this foundation or not. I will write a post later on about this, but the reality is that you DO need it, but ONLY the basics (at least in the beginning). And I want to clarify this point before continuing. We could say that data science is divided in two big fields: Research on one side and putting Machine Learning algorithms into production on the other side. If you later decide to focus on Research then you are going to need mathematics and statistics in depth (very in depth). If you are going to go for the practical part, the libraries will help you deal with most of it, under the hood. It should be noted that most job offers are in the practical part. For both cases, and in this first stage you will only need the basics of: Statistics (with Python and NumPy) Descriptive statistics Inferential Statistics Hypothesis testing Probability Mathematics (with Python and NumPy) Linear Algebra (For example: SVD) Multivariate Calculus Calculus (For example: gradient descent) Note: We recommend that you study Python first before seeing statistics and mathematics, because the challenge is to implement these statistical and mathematical bases with Python. Don’t look for theoretical tutorials that show only slides or statistical and/or mathematical examples in Excel/Matlab/Octave/SAS and other different to Python or R, it gets very boring and impractical! You should choose a course, program or book that teaches these concepts in a practical way and using Python. Remember that Python is what we finally use, so you need to choose well. This advice is key so you don’t give up on this part, as it will be the most dense and difficult. If you have these basics in the first three months, you will be ready to make a leap in your learning for the next three months. Second Quarter: Upgrading the Level: Intermediate Knowledge ​ https://preview.redd.it/y1y55vynet661.png?width=669&format=png&auto=webp&s=bd3e12bb112943025c39a8975faf4d64514df275 If you want to be more rigorous you can have start and end dates for this period of study at the intermediate level. It could be something like: From April 1 to June 30, 2021 as deadline. Now that you have a good foundation in programming, statistics and mathematics, it is time to move forward and learn about the great advantages that Python has for applying data analysis. For this stage you will be focused on: Data science Python stack Python has the following libraries that you should study, know and practice at this stage Pandas: for working with tabular data and make in-depth analysis Matplotlib and Seaborn: for data visualization Pandas is the in-facto library for data analysis, it is one of the most important (if not the most important) and powerful tools you should know and master during your career as a data scientist. Pandas will make it much easier for you to manipulate, cleanse and organize your data. Feature Engineering Many times people don’t go deep into Feature Engineering, but if you want to have Machine Learning models that make good predictions and improve your scores, spending some time on this subject is invaluable! Feature engineering is the process of using domain knowledge to extract features from raw data using data mining techniques. These features can be used to improve the performance of machine learning algorithms. Feature engineering can be considered as applied machine learning itself. To achieve the goal of good feature engineering you must know the different techniques that exist, so it is a good idea to at least study the main ones. Basic Models of Machine Learning At the end of this stage you will start with the study of Machine Learning. This is perhaps the most awaited moment! This is where you start to learn about the different algorithms you can use, which particular problems you can solve and how you can apply them in real life. The Python library we recommend you to start experimenting with ML is: scikit-learn. However it is a good idea that you can find tutorials where they explain the implementation of the algorithms (at least the simplest ones) from scratch with Python, since the library could be a “Black Box” and you might not understand what is happening under the hood. If you learn how to implement them with Python, you can have a more solid foundation. If you implement the algorithms with Python (without a library), you will put into practice everything seen in the statistics, mathematics and Pandas part. These are some recommendations of the algorithms that you should at least know in this initial stage Supervised learning Simple Linear Regression Multiple Linear Regression K-nearest neighbors (KNN) Logistic Regression Decision Trees Random Forest Unsupervised Learning K-Means PCA Bonus: if you have the time and you are within the time ranges, you can study these others Gradient Boosting Algorithms GBM XGBoost LightGBM CatBoost Note: do not spend more than the 3 months stipulated for this stage. Because you will be falling behind and not complying with the study plan. We all have shortcomings at this stage, it is normal, go ahead and then you can resume some concepts that did not understand in detail. The important thing is to have the basic knowledge and move forward! If at least you succeed to study the mentioned algorithms of supervised and unsupervised learning, you will have a very clear idea of what you will be able to do in the future. So don’t worry about covering everything, remember that it is a process, and ideally you should have some clearly established times so that you don’t get frustrated and feel you are advancing. So far, here comes your “theoretical” study of the basics of data science. Now we’ll continue with the practical part! Third Quarter: A Real World Project — A Full-stack Project ​ https://preview.redd.it/vrn783vqet661.png?width=678&format=png&auto=webp&s=664061b3d33b34979b74b10b9f8a3d0f7b8b99ee If you want to be more rigorous you can have start and end dates for this period of study at the intermediate level. It could be something like: From July 1 to September 30, 2021 as deadline. Now that you have a good foundation in programming, statistics, mathematics, data analysis and machine learning algorithms, it is time to move forward and put into practice all this knowledge. Many of these suggestions may sound out of the box, but believe me they will make a big difference in your career as a data scientist. The first thing is to create your web presence: Create a Github (or GitLab) account, and learn Git*. Being able to manage different versions of your code is important, you should have version control over them, not to mention that having an active Github account is very valuable in demonstrating your true skills. On Github, you can also set up your Jupyter Notebooks and make them public, so you can show off your skills as well. This is mine for example: https://github.com/danielmoralesp Learn the basics of web programming*. The advantage is that you already have Python as a skill, so you can learn Flask to create a simple web page. Or you can use a template engine like Github Pages, Ghost or Wordpress itself and create your online portfolio. Buy a domain with your name*. Something like myname.com, myname.co, myname.dev, etc. This is invaluable so you can have your CV online and update it with your projects. There you can make a big difference, showing your projects, your Jupyter Notebooks and showing that you have the practical skills to execute projects in this area. There are many front-end templates for you to purchase for free or for payment, and give it a more personalized and pleasant look. Don’t use free sub-domains of Wordpress, Github or Wix, it looks very unprofessional, make your own. Here is mine for example: https://www.danielmorales.dev/ Choose a project you are passionate about and create a Machine Learning model around it. The final goal of this third quarter is to create ONE project, that you are passionate about, and that is UNIQUE among others. It turns out that there are many typical projects in the community, such as predicting the Titanic Survivors, or predicting the price of Houses in Boston. Those kinds of projects are good for learning, but not for showing off as your UNIQUE projects. If you are passionate about sports, try predicting the soccer results of your local league. If you are passionate about finance, try predicting your country’s stock market prices. If you are passionate about marketing, try to find someone who has an e-commerce and implement a product recommendation algorithm and upload it to production. If you are passionate about business: make a predictor of the best business ideas for 2021 :) As you can see, you are limited by your passions and your imagination. In fact, those are the two keys for you to do this project: Passion and Imagination. However don’t expect to make money from it, you are in a learning stage, you need that algorithm to be deployed in production, make an API in Flask with it, and explain in your website how you did it and how people can access it. This is the moment to shine, and at the same time it’s the moment of the greatest learning. You will most likely face obstacles, if your algorithm gives 60% of Accuracy after a huge optimization effort, it doesn’t matter, finish the whole process, deploy it to production, try to get a friend or family member to use it, and that will be the goal achieved for this stage: Make a Full-stack Machine Learning project. By full-stack I mean that you did all the following steps: You got the data from somewhere (scrapping, open data or API) You did a data analysis You cleaned and transformed the data You created Machine Learning Models You deployed the best model to production for other people to use. This does not mean that this whole process is what you will always do in your daily job, but it does mean that you will know every part of the pipeline that is needed for a data science project for a company. You will have a unique perspective! Fourth Quarter: Seeking Opportunities While Maintaining Practice ​ https://preview.redd.it/qd0osystet661.png?width=1056&format=png&auto=webp&s=2da456b15985b2793041256f5e45bca99a23b51a If you want to be more rigorous you can have start and end dates for this period of study at the final level. It could be something like: From October 1 to December 31, 2021 as deadline. Now you have theoretical and practical knowledge. You have implemented a model in production. The next step depends on you and your personality. Let’s say you are an entrepreneur, and you have the vision to create something new from something you discovered or saw an opportunity to do business with this discipline, so it’s time to start planning how to do it. If that’s the case, obviously this post won’t cover that process, but you should know what the steps might be (or start figuring them out). But if you are one of those who want to get a job as a data scientist, here is my advice. Getting a job as a data scientist “You’re not going to get a job as fast as you think, if you keep thinking the same way”.Author It turns out that all people who start out as data scientists imagine themselves working for the big companies in their country or region. Or even remote. It turns out that if you aspire to work for a large company like data scientist you will be frustrated by the years of experience they ask for (3 or more years) and the skills they request. Large companies don’t hire Juniors (or very few do), precisely because they are already large companies. They have the financial muscle to demand experience and skills and can pay a commensurate salary (although this is not always the case). The point is that if you focus there you’re going to get frustrated! Here we must return to the following advise: “You need creativity to get a job in data science”. Like everything else in life we have to start at different steps, in this case, from the beginning. Here are the scenarios If you are working in a company and in a non-engineering role you must demonstrate your new skills to the company you are working for*. If you are working in the customer service area, you should apply it to your work, and do for example, detailed analysis of your calls, conversion rates, store data and make predictions about it! If you can have data from your colleagues, you could try to predict their sales! This may sound funny, but it’s about how creatively you can apply data science to your current work and how to show your bosses how valuable it is and EVANGELIZE them about the benefits of implementation. You’ll be noticed and they could certainly create a new data related department or job. And you already have the knowledge and experience. The key word here is Evangelize. Many companies and entrepreneurs are just beginning to see the power of this discipline, and it is your task to nurture that reality. If you are working in an area related to engineering, but that is not data science*. Here the same applies as the previous example, but you have some advantages, and that is that you could access the company’s data, and you could use it for the benefit of the company, making analyses and/or predictions about it, and again EVANGELIZING your bosses your new skills and the benefits of data science. If you are unemployed (or do not want, or do not feel comfortable following the two examples above)*, you can start looking outside, and what I recommend is that you look for technology companies and / or startups where they are just forming the first teams and are paying some salary, or even have options shares of the company. Obviously here the salaries will not be exorbitant, and the working hours could be longer, but remember that you are in the learning and practice stage (just in the first step), so you can not demand too much, you must land your expectations and fit that reality, and stop pretending to be paid $ 10,000 a month at this stage. But, depending of your country $1.000 USD could be something very interesting to start this new career. Remember, you are a Junior at this stage. The conclusion is: don’t waste your time looking at and/or applying to offers from big companies, because you will get frustrated. Be creative, and look for opportunities in smaller or newly created companies. Learning never stops While you are in that process of looking for a job or an opportunity, which could take half of your time (50% looking for opportunities, 50% staying in practice), you have to keep learning, you should advance to concepts such as Deep Learning, Data Engineer or other topics that you feel were left loose from the past stages or focus on the topics that you are passionate about within this group of disciplines in data science. At the same time you can choose a second project, and spend some time running it from end-to-end, and thus increase your portfolio and your experience. If this is the case, try to find a completely different project: if the first one was done with Machine Learning, let this second one be done with Deep learning. If the first one was deployed to a web page, that this second one is deployed to a mobile platform. Remember, creativity is the key! Conclusion We are at an ideal time to plan for 2021, and if this is the path you want to take, start looking for the platforms and media you want to study on. Get to work and don’t miss this opportunity to become a data scientist in 2021! Note: we are building a private community in Slack of data scientist, if you want to join us write to the email: support@datasource.ai I hope you enjoyed this reading! you can follow me on twitter or linkedin Thank you for reading!

Problems with automating manual data entry using Deep Learning

Full disclaimer: I work at Nanonets. Nanonets is a Deep Learning API company. We've written some of the most go to blogs on Deep Learning available on the internet. https://nanonets.com/blog/ This post might be a little different so apologies in advance if I'm violating any rules. We've written a blog that gives an overview of an important but often overlooked process in an organization: 3 way matching of Purchase Orders We've noticed that Deep learning (GCNs) + OCR can be applied and bring down manual digitization times significantly. i.e the process that typically takes a human 90 seconds can be done within 20 seconds with AI assistance. However there are quite a few caveats and nuances before beginning and this blog covers that aspect. Link to blog: https://nanonets.com/blog/how-to-ocr-purchase-orders-for-automation/

Is this a good ML learning progression on Coursera?

AI for Everyone Python for Everybody (UMich) Applied Data Science with Python Specialization (UMich) Machine Learning (Andrew Ng) Data Engineering, Big Data, and ML on GCP Specialization Natural Language Processing Specialization TensorFlow Developer Professional Certificate Machine Learning Engineering for Production (MLOps) by DeepLearning.AI Deep Learning Specialization Mathematics for Machine Learning Specialization Cloud Computing Specialization Product Management for AI and ML Products Specialization I’m currently a highschool junior with currently minimal Python knowledge (currently in BC Calc so I do have somewhat of a math background). However, I do own and run a business and in my business space there’s a huge issue I want to solve that affects pretty much every business. But right now obviously I can’t because I don’t have the necessary knowledge. I do intend to turn this into a startup and pursue AI/ML in college. And I aim to at least start building MVP for startup around June-Sept this year. If startup is not successful then I would still want to be an AI engineer. But is this a good learning progression that I should be able to complete before I start college?

Learning AI for Business Leaders

Hello Community, For the better part of 2 months I have been reading up on everything in getting a better understanding of the fundamentals of AI - from history of AI to reading the Google 8’s peer reviewed paper on the advent of transformers. I feel as though I am running in circles at times an not following a guided path approach to learning. I’m 40, work in international development in a leadership role - though I have a background in corporate finance and tech. I’m not an engineer, nor do I have the ambition of such a career pivot. However I do want to learn, be abreast, and know enough about the space when evaluating (and proposing) AI related opportunities - my role now should be a path towards a chief innovation officer for a development agency within the next 3-4 years. My sources have been basically everything I can find from tech blogs, WaPo, financial times, economist, and random internet searches. I have completed IBM’s Fundamental on AI course. However, I feel there no structure in learning as I have been piecemealing from so many different sources. Essentially I care about business cases and being able to confidently talk about AI. And not building and deploying a product. MIT and UPenn have some courses on AI for leaders, however, as the space is moving so fast I’m not confident how current their materials are. My ask: Are there any courses (or learning approaches) you recommend that is less-code and more focus on concept and applications I should do? Is my approach to learning too broad and I should focus on a subset of AI such as ML or specifically GenAI since it seems most applications are currently byproducts of it. Many thanks in advance for any support - truly appreciate it.

MS in Computer Science student (non-tech bachelor) applying for first Machine Learning intern/coop

Hi, I am an international student in the U.S applying for my first co-op for a Machine Learning/AI role, would love to get some advice on my current resume, thanks. I am currently in my second last semester of my 2 year's masters program in CS. I had no tech background before this program and was working in higher education administration. I have applied to about 50 positions so far on LinkedIn and HandShake and have had no responses but a few rejection emails. If you are a Machine learning professional, please help if I could improve my current project sections, I have two projects I am working on and hoping to swap them in after I finish them by the end of this semester: (1)Adaptive Learning curriculum for Spanish Language Learning (Duolingo-Inspired), which tailors lessons based on user's daily interactions (e.g., bar conversations, gym interactions). (2) DEI analytics and how they impact student performances and career outcome in Higher Ed. My interests lies in using ML in EdTech and Higher Education. But before finishing them, are my current projects passable? Also any suggestion to enhance my work experience section since they are not tech-related? Thanks! https://preview.redd.it/ww7smowjazne1.png?width=5100&format=png&auto=webp&s=289cde9aee45b2066dcfbb375fc318e7a3c5f5d7

Just completed a new type of language learning website - read popular stories scaled to different reading levels

As a language learner and software developer, I bootstrapped my project superlang.com over the past year working on the side. There is a mobile friendly web app now, and iOS/Android apps coming in a few months. A year ago I discovered the concept of "comprehensible input" as a way to help me learn German. Even if it's not a silver bullet, it sounded pretty great. Rather than drilling vocab or looking at grammar charts, I could "just read" and acquire the language. I picked up some fairy tales in German, and stories like Alice in Wonderland. Unfortunately, I couldn't really read them. I had to stop every sentence to look up words and try and decipher sentence constructions. Then I turned to some purpose built simple stories for German beginners. But there was a different problem... these were not really stories with any real plot. I could only read so many "Hans goes to the market" type stories before losing interest. My idea was to try to get the best of both worlds somehow. What if I could take a real story, say Alice in Wonderland (or even War and Peace), and dial the difficulty down to my level without losing the plotline. That way, beginners can start right away with something basically comprehensible. Then, you could also re-read the same story at increasing difficulty levels as you gain confidence. As a cherry on top, more illustrations would help with comprehension so each page could have a picture. Is it revolutionary? Maybe, maybe not. I am building off a well established idea of "graded readers" which are simplified stories meant for learning languages. And there are somewhat similar ideas out there now that AI is good at simplifying text, but none that really take this idea where it needs to be with many preloaded stories, multiple difficulty levels, high quality human verified text, and all the bells and whistles. I spent a year building Superlang and it is ready to put out there. Some quick notes: There are 3 languages so far, intended for native English speakers: German, French, and Spanish There are 3 difficulty levels you can set on each story: beginner (roughly A1-A2), intermediate (roughly A2-B1), and advanced (the same level as the original story, but typically B2+) There is premium version as producing the content was somewhat expensive. You can still do a lot of reading on the free version. I have done no marketing yet, except for this post :) The implementation is a combination of AI, and human proofreading and reviewing. In particular, the simplification of stories is very heavily AI driven. The illustrations for each page are AI as well. For translation, as many of you may be aware new LLM models are typically better than Google translate, but still far from perfect. I am very much a proponent of keeping real people in the loop, and so I have real people proofread the translations. That's why there are only about 700 pages of content so far and not tens of thousands. Let me know what you think, and if you find it helpful! Alice in Wonderland - beginner level German Romeo and Juliet - beginner level Spanish

[P] Building an Reinforcement Learning Agent to play The Legend of Zelda

A year go I started trying to use PPO to play the original Legend of Zelda, and I was able to train a model to beat the first boss after a few months of work. I wanted to share the project just for show and tell. I'd love to hear feedback and suggestions as this is just a hobby project. I don't do this for a living. The code for that lives in the original-design branch of my Triforce repo. I'm currently tinkering with new designs so the main branch is much less stable. Here's a video of the agent beating the first dungeon, which was trained with 5,000,000+ steps. At 38 seconds, you can see it learned that it's invulnerable at the screen edge, and it exploits that to avoid damage from a projectile. At 53 seconds it steps up to avoid damage from an unblockable projectile, even though it takes a -0.06 penalty for moving the wrong way (taking damage would be a larger penalty.) At 55 seconds it walks towards the rock projectile to block it. And so on, lots of little things the model does is easy to miss if you don't know the game inside and out. As a TLDR, here's an early version of my new (single) model. This doesn't make it quite as far, but if you watch closely it's combat is already far better, and is only trained on 320,000 steps (~6% of the steps the first model was trained on). This is pretty far along from my very first model. Original Design I got the original project working using stable-baselines's PPO and default neural network (Shared NatureCNN, I believe). SB was great to get started but ultimately stifling. In the new version of the project I've implemented PPO from scratch with torch with my own simple neural network similar to stable-baseline's default. I'm playing with all kinds of changes and designs now that I have more flexibility and control. Here is my rough original design: Overall Strategy My first pass through this project was basically "imagine playing Zelda with your older sibling telling you where to go and what to do". I give the model an objective vector which points to where I want it to go on the screen (as a bird flies, the agent still had to learn path finding to avoid damage and navigate around the map). This includes either point at the nearest enemy I want it to kill or a NSEW vector if it's supposed to move to the next room. Due a few limitations with stable-baselines (especially around action masking), I ended up training unique models for traversing the overworld vs the dungeon (since they have entirely different tilesets). I also trained a different model for when we have sword beams vs not. In the video above you can see what model is being used onscreen. In my current project I've removed this objective vector as it felt too much like cheating. Instead I give it a one-hot encoded objective (move north to the next room, pickup items, kill enemies, etc). So far it's working quite well without that crutch. The new project also does a much better job of combat even without multiple models to handle beams vs not. Observation/Action Space Image - The standard neural network had a really tough time being fed the entire screen. No amount of training seemed to help. I solved this by creating a viewport around Link that keeps him centered. This REALLY helped the model learn. I also had absolutely zero success with stacking frames to give Link a way to see enemy/projectile movement. The model simply never trained with stable-baselines when I implemented frame stacking and I never figured out why. I just added it to my current neural network and it seems to be working... Though my early experiments show that giving it 3 frames (skipping two in between, so frames curr, curr-3, curr-6) doesn't really give us that much better performance. It might if I took away some of the vectors. We'll see. Vectors - Since the model cannot see beyond its little viewport, I gave the model a vector to the closest item, enemy, and projectile onscreen. This made it so the model can shoot enemies across the room outside of its viewport. My new model gives it multiple enemies/items/projectiles and I plan to try to use an attention mechanism as part of the network to see if I can just feed it all of that data. Information - It also gets a couple of one-off datapoints like whether it currently has sword beams. The new model also gives it a "source" room (to help better understand dungeons where we have to backtrack), and a one-hot encoded objective. Action Space My original project just has a few actions, 4 for moving in the cardinal directions and 4 for attacking in each direction (I also added bombs but never spent any time training it). I had an idea to use masking to help speed up training. I.E. if link bumps into a wall, don't let him move in that direction again until he moves elsewhere, as the model would often spend an entire memory buffer running headlong straight into a wall before an update...better to do it once and get a huge negative penalty which is essentially the same result but faster. Unfortunately SB made it really annoying architecturally to pass that info down to the policy layer. I could have hacked it together, but eventually I just reimplemented PPO and my own neural network so I could properly mask actions in the new version. For example, when we start training a fresh model, it cannot attack when there aren't enemies on screen and I can disallow it from leaving certain areas. The new model actually understands splitting swinging the sword short range vs firing sword beams as two different actions, though I haven't yet had a chance to fully train with the split yet. Frameskip/Cooldowns - In the game I don't use a fixed frame skip for actions. Instead I use the internal ram state of game to know when Link is animation locked or not and only allow the agent to take actions when it's actually possible to give meaningful input to the game. This greatly sped up training. We also force movement to be between tiles on the game map. This means that when the agent decides to move it loses control for longer than a player would...a player can make more split second decisions. This made it easier to implement movement rewards though and might be something to clean up in the future. Other interesting details Pathfinding - To facilitate rewards, the original version of this project used A* to pathfind from link to what he should be doing. Here's a video of it in action. This information wasn't giving to the model directly but instead the agent would only be given the rewards if it exactly followed that path or the transposed version of it. It would also pathfind around enemies and not walk through them. This was a nightmare though. The corner cases were significant, and pushing Link towards enemies but not into them was really tricky. The new verison just uses a wavefront algorithm. I calculate a wave from the tiles we want to get to outwards, then make sure we are following the gradient. Also calculating the A* around enemies every frame (even with caching) was super slow. Wavefront was faster, especially because I give the new model no special rewards for walking around enemies...faster to compute and it has to learn from taking damage or not. Either way, the both the old and new models successfully learned how to pathfind around danger and obstacles, with or without the cheaty objective vector. Rewards - I programmed very dense rewards in both the old and new model. At basically every step, the model is getting rewarded or punished for something. I actually have some ideas I can't wait to try out to make the rewards more sparse. Or maybe we start with dense rewards for the first training, then fine-tune the model with sparser rewards. We'll see. Predicting the Future - Speaking of rewards. One interesting wrinkle is that the agent can do a lot of things that will eventually deal damage but not on that frame. For example, when Link sets a bomb it takes several seconds before it explodes, killing things. This can be a massive reward or penalty since he spent an extremely valuable resource, but may have done massive damage. PPO and other RL propagates rewards backwards, of course, but that spike in reward could land on a weird frame where we took damage or moved in the wrong direction. I probably could have just not solved that problem and let it shake out over time, but instead I used the fact that we are in an emulator to just see what the outcome of every decision is. When planting a bomb, shooting sword beams, etc, we let the game run forward until impact, then rewind time and reward the agent appropriately, continuing on from when we first paused. This greatly speeds up training, even if it's expensive to do this savestate, play forward, restore state. Neural Networks - When I first started this project (knowing very little about ML and RL), I thought most of my time would be tuning the shape of the neural network that we are using. In reality, the default provided by stable-baselines and my eventual reimplemnentation has been enough to make massive progress. Now that I have a solid codebase though, I really want to revisit this. I'd like to see if trying CoordConvs and similar networks might make the viewport unncessary. Less interesting details/thoughts Hyperparameters - Setting the entropy coefficinet way lower helped a TON in training stable models. My new PPO implementation is way less stable than stable-baselines (ha, imagine that), but still converges most of the time. Infinite Rewards - As with all reinforcement learning, if you give some way for the model to get infinite rewards, it will do just that and nothing else. I spent days, or maybe weeks tweaking reward functions to just get it to train and not find a spot on the wall it could hump for infinite rewards. Even just neutral rewards, like +0.5 moving forward and -0.5 for moving backwards, would often result in a model that just stepped left, then right infinitely. There has to be a real reward or punishment (non-neutral) for forward progress. Debugging Rewards - In fact, building a rewards debugger was the only way I made progress in this project. If you are tackling something this big, do that very early. Stable-Retro is pretty great - Couldn't be happier with the clean design for implementing emulation for AI. Torch is Awesome - My early versions heavily used numpy and relied on stable-baselines, with its multiproc parallelization support. It worked great. Moving the project over to torch was night and day though. It gave me so much more flexibility, instant multithreading for matrix operations. I have a pretty beefy computer and I'm almost at the same steps per second as 20 proc stable-retro/numpy. Future Ideas This has already gone on too long. I have some ideas for future projects, but maybe I'll just make them another post when I actually do them. Special Thanks A special thanks to Brad Flaugher for help with the early version of this, Fiskbit from the Zelda1 speedrunning community for help pulling apart the raw assembly to build this thing, and MatPoliquin for maintaining Stable-Retro. Happy to answer any questions, really I just love nerding out about this stuff.

[D] Misuse of Deep Learning in Nature Journal’s Earthquake Aftershock Paper

Recently, I saw a post by Rajiv Shah, Chicago-based data-scientist, regarding an article published in Nature last year called Deep learning of aftershock patterns following large earthquakes, written by scientists at Harvard in collaboration with Google. Below is the article: Stand Up for Best Practices: Misuse of Deep Learning in Nature’s Earthquake Aftershock Paper The Dangers of Machine Learning Hype Practitioners of AI, machine learning, predictive modeling, and data science have grown enormously over the last few years. What was once a niche field defined by its blend of knowledge is becoming a rapidly growing profession. As the excitement around AI continues to grow, the new wave of ML augmentation, automation, and GUI tools will lead to even more growth in the number of people trying to build predictive models. But here’s the rub: While it becomes easier to use the tools of predictive modeling, predictive modeling knowledge is not yet a widespread commodity. Errors can be counterintuitive and subtle, and they can easily lead you to the wrong conclusions if you’re not careful. I’m a data scientist who works with dozens of expert data science teams for a living. In my day job, I see these teams striving to build high-quality models. The best teams work together to review their models to detect problems. There are many hard-to-detect-ways that lead to problematic models (say, by allowing target leakage into their training data). Identifying issues is not fun. This requires admitting that exciting results are “too good to be true” or that their methods were not the right approach. In other words, it’s less about the sexy data science hype that gets headlines and more about a rigorous scientific discipline. Bad Methods Create Bad Results Almost a year ago, I read an article in Nature that claimed unprecedented accuracy in predicting earthquake aftershocks by using deep learning. Reading the article, my internal radar became deeply suspicious of their results. Their methods simply didn’t carry many of the hallmarks of careful predicting modeling. I started to dig deeper. In the meantime, this article blew up and became widely recognized! It was even included in the release notes for Tensorflow as an example of what deep learning could do. However, in my digging, I found major flaws in the paper. Namely, data leakage which leads to unrealistic accuracy scores and a lack of attention to model selection (you don’t build a 6 layer neural network when a simpler model provides the same level of accuracy). To my earlier point: these are subtle, but incredibly basic predictive modeling errors that can invalidate the entire results of an experiment. Data scientists are trained to recognize and avoid these issues in their work. I assumed that this was simply overlooked by the author, so I contacted her and let her know so that she could improve her analysis. Although we had previously communicated, she did not respond to my email over concerns with the paper. Falling On Deaf Ears So, what was I to do? My coworkers told me to just tweet it and let it go, but I wanted to stand up for good modeling practices. I thought reason and best practices would prevail, so I started a 6-month process of writing up my results and shared them with Nature. Upon sharing my results, I received a note from Nature in January 2019 that despite serious concerns about data leakage and model selection that invalidate their experiment, they saw no need to correct the errors, because “Devries et al. are concerned primarily with using machine learning as [a] tool to extract insight into the natural world, and not with details of the algorithm design.” The authors provided a much harsher response. You can read the entire exchange on my github. It’s not enough to say that I was disappointed. This was a major paper (it’s Nature!) that bought into AI hype and published a paper despite it using flawed methods. Then, just this week, I ran across articles by Arnaud Mignan and Marco Broccardo on shortcomings that they found in the aftershocks article. Here are two more data scientists with expertise in earthquake analysis who also noticed flaws in the paper. I also have placed my analysis and reproducible code on github. Standing Up For Predictive Modeling Methods I want to make it clear: my goal is not to villainize the authors of the aftershocks paper. I don’t believe that they were malicious, and I think that they would argue their goal was to just show how machine learning could be applied to aftershocks. Devries is an accomplished earthquake scientist who wanted to use the latest methods for her field of study and found exciting results from it. But here’s the problem: their insights and results were based on fundamentally flawed methods. It’s not enough to say, “This isn’t a machine learning paper, it’s an earthquake paper.” If you use predictive modeling, then the quality of your results are determined by the quality of your modeling. Your work becomes data science work, and you are on the hook for your scientific rigor. There is a huge appetite for papers that use the latest technologies and approaches. It becomes very difficult to push back on these papers. But if we allow papers or projects with fundamental issues to advance, it hurts all of us. It undermines the field of predictive modeling. Please push back on bad data science. Report bad findings to papers. And if they don’t take action, go to twitter, post about it, share your results and make noise. This type of collective action worked to raise awareness of p-values and combat the epidemic of p-hacking. We need good machine learning practices if we want our field to continue to grow and maintain credibility. Link to Rajiv's Article Original Nature Publication (note: paywalled) GitHub repo contains an attempt to reproduce Nature's paper Confrontational correspondence with authors

[R] Apple’s Machine Learning Researchers Have Developed A No-Code AI Platform Called ‘Trinity’ For Complex Spatial Datasets

Apple’s machine learning research team has developed a no-code Artificial Intelligence (AI) platform called Trinity. This AI is designed to enable machine learning researchers and non-technical geospatial domain experts alike to experiment with different signals or datasets in order to solve problems on their own, such as complex issues that arise from the world around us every day. The ability to solve diverse problems is made possible by transforming complex Spatio-temporal datasets so that they can be consumed and solved with a standard deep learning model, like Convolutional Neural Networks. This new way of looking at data has the potential to formulate disparate problems in one standardized form for easy consumption. Quick Read: https://www.marktechpost.com/2021/07/23/apples-machine-learning-researchers-have-developed-a-no-code-ai-platform-called-trinity-for-complex-spatial-datasets/ Paper: https://arxiv.org/pdf/2106.11756.pdf

[N] 20 hours of new lectures on Deep Learning and Reinforcement Learning with lots of examples

If anyone's interested in a Deep Learning and Reinforcement Learning series, I uploaded 20 hours of lectures on YouTube yesterday. Compared to other lectures, I think this gives quite a broad/compact overview of the fields with lots of minimal examples to build on. Here are the links: Deep Learning (playlist) The first five lectures are more theoretical, the second half is more applied. Lecture 1: Introduction. (slides, video) Lecture 2: Mathematical principles and backpropagation. (slides, colab, video) Lecture 3: PyTorch programming: coding session*. (colab1, colab2, video) - minor issues with audio, but it fixes itself later. Lecture 4: Designing models to generalise. (slides, video) Lecture 5: Generative models. (slides, desmos, colab, video) Lecture 6: Adversarial models. (slides, colab1, colab2, colab3, colab4, video) Lecture 7: Energy-based models. (slides, colab, video) Lecture 8: Sequential models: by* u/samb-t. (slides, colab1, colab2, video) Lecture 9: Flow models and implicit networks. (slides, SIREN, GON, video) Lecture 10: Meta and manifold learning. (slides, interview, video) Reinforcement Learning (playlist) This is based on David Silver's course but targeting younger students within a shorter 50min format (missing the advanced derivations) + more examples and Colab code. Lecture 1: Foundations. (slides, video) Lecture 2: Markov decision processes. (slides, colab, video) Lecture 3: OpenAI gym. (video) Lecture 4: Dynamic programming. (slides, colab, video) Lecture 5: Monte Carlo methods. (slides, colab, video) Lecture 6: Temporal-difference methods. (slides, colab, video) Lecture 7: Function approximation. (slides, code, video) Lecture 8: Policy gradient methods. (slides, code, theory, video) Lecture 9: Model-based methods. (slides, video) Lecture 10: Extended methods. (slides, atari, video)

[D] What is your honest experience with reinforcement learning?

In my personal experience, SOTA RL algorithms simply don't work. I've tried working with reinforcement learning for over 5 years. I remember when Alpha Go defeated the world famous Go player, Lee Sedol, and everybody thought RL would take the ML community by storm. Yet, outside of toy problems, I've personally never found a practical use-case of RL. What is your experience with it? Aside from Ad recommendation systems and RLHF, are there legitimate use-cases of RL? Or, was it all hype? Edit: I know a lot about AI. I built NexusTrade, an AI-Powered automated investing tool that lets non-technical users create, update, and deploy their trading strategies. I’m not an idiot nor a noob; RL is just ridiculously hard. Edit 2: Since my comments are being downvoted, here is a link to my article that better describes my position. It's not that I don't understand RL. I released my open-source code and wrote a paper on it. It's the fact that it's EXTREMELY difficult to understand. Other deep learning algorithms like CNNs (including ResNets), RNNs (including GRUs and LSTMs), Transformers, and GANs are not hard to understand. These algorithms work and have practical use-cases outside of the lab. Traditional SOTA RL algorithms like PPO, DDPG, and TD3 are just very hard. You need to do a bunch of research to even implement a toy problem. In contrast, the decision transformer is something anybody can implement, and it seems to match or surpass the SOTA. You don't need two networks battling each other. You don't have to go through hell to debug your network. It just naturally learns the best set of actions in an auto-regressive manner. I also didn't mean to come off as arrogant or imply that RL is not worth learning. I just haven't seen any real-world, practical use-cases of it. I simply wanted to start a discussion, not claim that I know everything. Edit 3: There's a shockingly number of people calling me an idiot for not fully understanding RL. You guys are wayyy too comfortable calling people you disagree with names. News-flash, not everybody has a PhD in ML. My undergraduate degree is in biology. I self-taught myself the high-level maths to understand ML. I'm very passionate about the field; I just have VERY disappointing experiences with RL. Funny enough, there are very few people refuting my actual points. To summarize: Lack of real-world applications Extremely complex and inaccessible to 99% of the population Much harder than traditional DL algorithms like CNNs, RNNs, and GANs Sample inefficiency and instability Difficult to debug Better alternatives, such as the Decision Transformer Are these not legitimate criticisms? Is the purpose of this sub not to have discussions related to Machine Learning? To the few commenters that aren't calling me an idiot...thank you! Remember, it costs you nothing to be nice! Edit 4: Lots of people seem to agree that RL is over-hyped. Unfortunately those comments are downvoted. To clear up some things: We've invested HEAVILY into reinforcement learning. All we got from this investment is a robot that can be super-human at (some) video games. AlphaFold did not use any reinforcement learning. SpaceX doesn't either. I concede that it can be useful for robotics, but still argue that it's use-cases outside the lab are extremely limited. If you're stumbling on this thread and curious about an RL alternative, check out the Decision Transformer. It can be used in any situation that a traditional RL algorithm can be used. Final Edit: To those who contributed more recently, thank you for the thoughtful discussion! From what I learned, model-based models like Dreamer and IRIS MIGHT have a future. But everybody who has actually used model-free models like DDPG unanimously agree that they suck and don’t work.

Learning AI(?) where to start

So lately "learning Artificial Intelligence" caught my attention. I would like to start experimenting with it as well but i have no idea where to start. I am talking about that part when using command line AI generations are created and they get a fitness value based on how close they got to completing the task. I do not even know what it is called and also sorry for this weird description, that's all i know about it. I saw it on a video in which an AI was learning how to complete old video games like super mario, mario kart and such, but i assume it's the same concept as AI trying to write books based on human written books? Thank you for your help in advance and sorry again for the weird description. (I did check the FAQ but it's too much information for an absolute beginner, i am interested in this particular field only, for now at least)

[P] My deep learning library from sophomore year in high school

I made a deep learning library in Java a while ago to help me understand how neural networks work. I implemented vanilla fully connected layers, convolutional layers, pooling layers, GRU cells, multiple gradient descent optimizers, and other cool stuff. I also strived for an object oriented framework with a Keras-like interface. It took me quite a while to understand the full backprop algorithm as I did not know how derivatives work when I started. Also, many intrinsic details about how neural networks operate were obscured behind very similar mathematical equations in most of the blog posts I've seen (although Stanford CS231 was very helpful). In the end, I derived the backprop equations for updating the weights by hand for all of the layers in the library. As such, I want to share my code and maybe help others that are learning about neural networks. Note the library is very slow. There are no fancy GPU speedups because the library is pure Java. You can test the pretrained MNIST by running TestMNISTDraw2.java in the src/tests folder that also contains other demos. Edit: Is this too "beginner" for this sub?

[D] "Grokking" Deep Learning architectures and using them in practice

Hi all, I'm on the first years of my PhD in Computer Vision and obviously the vast majority of research in it is nowadays using Deep Learning techniques. I like to think that I'm far from an absolute beginner in the sense that: I've trained neural networks and more "traditional" ML models in a couple of courses, as well as for my MSc thesis, albeit almost out-of-the-box stuff. I have a decent understanding of Linear Algebra, Calculus and Probability Theory (undergrad courses from CS degree). I say "decent" because I'm of the firm opinion that the more math one knows the more impressive the things they can do in AI, so I really don't consider myself a math whiz, but judging from the math knowledge an average "How to get started with Deep Learning" blog post assumes, I'd say I'm well ahead. I'm also devoting some time every day to a more rigorous study of these areas, eventually hoping to expand to other related ones. I can get through Deep Learning papers and usually* obtain at least a basic understanding of what they're about, as well as why it works, at least according to the authors and their experiments. I do still have some trouble with more state-of-the-art works, especially ones that also use things from NLP. However, I don't really feel confident that I can actually produce useful research that investigates and/or uses this sort of methods to do something new. During undergrad, in order to actually understand most -if not all- concepts taught to me in programming and math I'd actually do things with them: solve problems, prove statements, or just code with the goal of creating some system or seeing how an idea actually works (e.g. polymorphism). I realize, however, that this has not been the case with Deep Learning, at least for me: I've never tried to actually code a CNN or ResNet, much less a word2vec model, a Transformer, or any sort of generative model. Sure, I've read about how the first layers of a CNN learn edges etc. but I've never actually "seen it with my own eyes". Transformers in particular seem to really trouble me. Although I sort-of understand the idea behind attention etc., I struggle to see what sort of features they end up using (in contrast to CNNs, where the idea of learning convolutional filters is much more intuitive to me). Which brings me to the question of what's an efficient way to go from understanding a paper to actually feeling like you really, truly, "grok" the material and could build on it, or use it in some scenario? Do you think implementing research papers from scratch or almost from scratch can be useful? Or is it way too time consuming for someone already busy with a PhD? Is it even feasible or are most papers -sadly- unreproducible if you don't use authors' code? How do you manage to stay on track with such a rapidly evolving field, on any level beyond a completely surface understanding? How do you find a good balance between learning to use tools/frameworks, reading papers and gaining the deeper sort of understanding I mention?

[R] Reinforcement Learning for Sequential Decision and Optimal Control

Since early 21st century, artificial intelligence (AI) has been reshaping almost all areas of human society, which has high potential to spark the fourth industrial revolution. Notable examples can be found in the sector of road transportation, where AI has drastically changed automobile design and traffic management. Many new technologies, such as driver assistance, autonomous driving, and cloud-based cooperation, are emerging at an unbelievable speed. These new technologies have the potential to significantly improve driving ability, reduce traffic accidents, and relieve urban congestion. As one of the most important AI branches, reinforcement learning (RL) has attracted increasing attention in recent years. RL is an interdisciplinary field of trial-and-error learning and optimal control, which promises to provide optimal solutions for decision-making or control in large-scale and complex dynamic processes. One of its most conspicuous successes is AlphaGo from Google DeepMind, which has beaten the highest-level professional human player. The underlying key technology is the so-called deep reinforcement learning, which equips AlphaGo with amazing self-evolution ability and high playing intelligence. Despite a few successes, the application of RL is still in its infancy because most RL algorithms are rather difficult to comprehend and implement. RL connects deeply with statistical learning and convex optimization, and involves a wide range of new concepts and theories. As a beginner, one must undergo a long and tedious learning process to become an RL master. Without fully understanding those underlying principles, it is very difficult for new users to make proper adjustments to achieve the best application performance. ​ https://preview.redd.it/tggt6o3o481c1.jpg?width=248&format=pjpg&auto=webp&s=75e2b58ac8da9273f2511a4fe37ef508d86a6e96 Reference： Shengbo Eben Li, Reinforcement Learning for Sequential Decision and Optimal Control. Springer Verlag, Singapore, 2023 Website of e-book: https://link.springer.com/book/10.1007/978-981-19-7784-8 ​ QR code to Springer Book contents This book aims to provide a systematic introduction to fundamental RL theories, mainstream RL algorithms and typical RL applications for researchers and engineers. The main topics include Markov decision processes, Monte Carlo learning, temporal difference learning, RL with function approximation, policy gradient method, approximate dynamic programming, deep reinforcement learning, etc. Chapter 1 provides an overview of RL, including its history, famous scholars, successful examples and up-to-date challenges. Chapter 2 discusses the basis of RL, including main concepts and terminologies, Bellman’s optimality condition, and general problem formulation. Chapter 3 introduces Monte Carlo learning methods for model-free RL, including on-policy/off-policy methods and importance sampling technique. Chapter 4 introduces temporal difference learning methods for model-free RL, including Sarsa, Q-learning, and expected Sarsa. Chapter 5 introduces stochastic dynamic programming (DP), i.e., model-based RL with tabular representation, including value iteration DP, policy iteration DP and their convergence mechanisms. Chapter 6 introduces how to approximate policy and value functions in indirect RL methods as well as the associated actor-critic architecture. Chapter 7 derives different kinds of direct policy gradients, including likelihood ratio gradient, natural policy gradient and a few advanced variants. Chapter 8 introduces infinite-horizon ADP, finite-horizon ADP and its connection with model predictive control. Chapter 9 discusses how to handle state constraints and its connection with feasibility and safety, as well as the newly proposed actor-critic-scenery learning architecture. Chapter 10 is devoted to deep reinforcement learning, including how to train artificial neural networks and typical deep RL algorithms such as DQN, DDPG, TD3, TRPO, PPO, SAC, and DSAC. Chapter 11 provides various RL topics,including robust RL, POMDP, multi-agent RL, meta-RL, inverse RL, offline RL, major RL libraries and platforms. Author information: Shengbo Eben Li is currently a professor at Tsinghua University in the interdisciplinary field of autonomous driving and artificial intelligence. Before joining Tsinghua University, he has worked at Stanford University, University of Michigan, and UC Berkeley. His active research interests include intelligent vehicles and driver assistance, deep reinforcement learning, optimal control and estimation, etc. He has published more than 130 peer-reviewed papers in top-tier international journals and conferences. He is the recipient of best paper awards (finalists) of IEEE ITSC, ICCAS, IEEE ICUS, IEEE IV, L4DC, etc. He has received a number of important academic honors, including National Award for Technological Invention of China (2013), National Award for Progress in Sci & Tech of China (2018), Distinguished Young Scholar of Beijing NSF (2018), Youth Sci & Tech Innovation Leader from MOST China (2020), etc. He also serves as Board of Governor of IEEE ITS Society, Senior AE of IEEE OJ ITS, and AEs of IEEE ITSM, IEEE Trans ITS, Automotive Innovation, etc.

[P] RLHF Learning to Summarize: Implementation by CarperAI with trlX

Hi, "Learning to summarize from human feedback" is a 2020 paper by OpenAI demonstrating how to use reinforcement learning with human feedback (RLHF) to fine-tune a language model to produce higher quality summaries of news articles and Reddit posts than is possible with supervised fine-tuning. Now, CarperAI has demonstrated how to use their library trlX to implement this work, by applying RLHF to the summarization dataset released by OpenAI and fine-tuning GPT-J-6B. Read the full report here, with a code walkthrough: https://wandb.ai/carperai/summarize_RLHF/reports/Implementing-RLHF-Learning-to-Summarize-with-trlX--VmlldzozMzAwODM2 trlX library here: https://github.com/CarperAI/trlx Twitter thread here: https://twitter.com/carperai/status/1613645352514768897

[D] What is your honest experience with reinforcement learning?

In my personal experience, SOTA RL algorithms simply don't work. I've tried working with reinforcement learning for over 5 years. I remember when Alpha Go defeated the world famous Go player, Lee Sedol, and everybody thought RL would take the ML community by storm. Yet, outside of toy problems, I've personally never found a practical use-case of RL. What is your experience with it? Aside from Ad recommendation systems and RLHF, are there legitimate use-cases of RL? Or, was it all hype? Edit: I know a lot about AI. I built NexusTrade, an AI-Powered automated investing tool that lets non-technical users create, update, and deploy their trading strategies. I’m not an idiot nor a noob; RL is just ridiculously hard. Edit 2: Since my comments are being downvoted, here is a link to my article that better describes my position. It's not that I don't understand RL. I released my open-source code and wrote a paper on it. It's the fact that it's EXTREMELY difficult to understand. Other deep learning algorithms like CNNs (including ResNets), RNNs (including GRUs and LSTMs), Transformers, and GANs are not hard to understand. These algorithms work and have practical use-cases outside of the lab. Traditional SOTA RL algorithms like PPO, DDPG, and TD3 are just very hard. You need to do a bunch of research to even implement a toy problem. In contrast, the decision transformer is something anybody can implement, and it seems to match or surpass the SOTA. You don't need two networks battling each other. You don't have to go through hell to debug your network. It just naturally learns the best set of actions in an auto-regressive manner. I also didn't mean to come off as arrogant or imply that RL is not worth learning. I just haven't seen any real-world, practical use-cases of it. I simply wanted to start a discussion, not claim that I know everything. Edit 3: There's a shockingly number of people calling me an idiot for not fully understanding RL. You guys are wayyy too comfortable calling people you disagree with names. News-flash, not everybody has a PhD in ML. My undergraduate degree is in biology. I self-taught myself the high-level maths to understand ML. I'm very passionate about the field; I just have VERY disappointing experiences with RL. Funny enough, there are very few people refuting my actual points. To summarize: Lack of real-world applications Extremely complex and inaccessible to 99% of the population Much harder than traditional DL algorithms like CNNs, RNNs, and GANs Sample inefficiency and instability Difficult to debug Better alternatives, such as the Decision Transformer Are these not legitimate criticisms? Is the purpose of this sub not to have discussions related to Machine Learning? To the few commenters that aren't calling me an idiot...thank you! Remember, it costs you nothing to be nice! Edit 4: Lots of people seem to agree that RL is over-hyped. Unfortunately those comments are downvoted. To clear up some things: We've invested HEAVILY into reinforcement learning. All we got from this investment is a robot that can be super-human at (some) video games. AlphaFold did not use any reinforcement learning. SpaceX doesn't either. I concede that it can be useful for robotics, but still argue that it's use-cases outside the lab are extremely limited. If you're stumbling on this thread and curious about an RL alternative, check out the Decision Transformer. It can be used in any situation that a traditional RL algorithm can be used. Final Edit: To those who contributed more recently, thank you for the thoughtful discussion! From what I learned, model-based models like Dreamer and IRIS MIGHT have a future. But everybody who has actually used model-free models like DDPG unanimously agree that they suck and don’t work.

[D] Do you know any institutions/nonprofits/companies/governments/etc. trying to apply deep learning and other ML/AI/GenAI techniques to implement universal basic income (UBI) or something similar to UBI like universal basic services?

Do you know any institutions/nonprofits/companies/governments/etc. trying to apply deep learning and other ML/AI/GenAI techniques to implement universal basic income (UBI) or something similar to UBI like universal basic services? Maybe for chatbot guidance on UBI program details, selecting candidates that need it the most, predicting poverty, UBI impacts, demographic and economic indicators to identify optimal UBI payment amounts and frequencies for different population segments, preventing fraud, etc. It can be just sketching future models in theory, or already implementing it in practice. I found this relevant paper: Can Data and Machine Learning Change the Future of Basic Income Models? A Bayesian Belief Networks Approach. https://www.mdpi.com/2306-5729/9/2/18 "Appeals to governments for implementing basic income are contemporary. The theoretical backgrounds of the basic income notion only prescribe transferring equal amounts to individuals irrespective of their specific attributes. However, the most recent basic income initiatives all around the world are attached to certain rules with regard to the attributes of the households. This approach is facing significant challenges to appropriately recognize vulnerable groups. A possible alternative for setting rules with regard to the welfare attributes of the households is to employ artificial intelligence algorithms that can process unprecedented amounts of data. Can integrating machine learning change the future of basic income by predicting households vulnerable to future poverty? In this paper, we utilize multidimensional and longitudinal welfare data comprising one and a half million individuals’ data and a Bayesian beliefs network approach to examine the feasibility of predicting households’ vulnerability to future poverty based on the existing households’ welfare attributes."

[D] The machine learning community has a toxicity problem

It is omnipresent! First of all, the peer-review process is broken. Every fourth NeurIPS submission is put on arXiv. There are DeepMind researchers publicly going after reviewers who are criticizing their ICLR submission. On top of that, papers by well-known institutes that were put on arXiv are accepted at top conferences, despite the reviewers agreeing on rejection. In contrast, vice versa, some papers with a majority of accepts are overruled by the AC. (I don't want to call any names, just have a look the openreview page of this year's ICRL). Secondly, there is a reproducibility crisis. Tuning hyperparameters on the test set seem to be the standard practice nowadays. Papers that do not beat the current state-of-the-art method have a zero chance of getting accepted at a good conference. As a result, hyperparameters get tuned and subtle tricks implemented to observe a gain in performance where there isn't any. Thirdly, there is a worshiping problem. Every paper with a Stanford or DeepMind affiliation gets praised like a breakthrough. For instance, BERT has seven times more citations than ULMfit. The Google affiliation gives so much credibility and visibility to a paper. At every ICML conference, there is a crowd of people in front of every DeepMind poster, regardless of the content of the work. The same story happened with the Zoom meetings at the virtual ICLR 2020. Moreover, NeurIPS 2020 had twice as many submissions as ICML, even though both are top-tier ML conferences. Why? Why is the name "neural" praised so much? Next, Bengio, Hinton, and LeCun are truly deep learning pioneers but calling them the "godfathers" of AI is insane. It has reached the level of a cult. Fourthly, the way Yann LeCun talked about biases and fairness topics was insensitive. However, the toxicity and backlash that he received are beyond any reasonable quantity. Getting rid of LeCun and silencing people won't solve any issue. Fifthly, machine learning, and computer science in general, have a huge diversity problem. At our CS faculty, only 30% of undergrads and 15% of the professors are women. Going on parental leave during a PhD or post-doc usually means the end of an academic career. However, this lack of diversity is often abused as an excuse to shield certain people from any form of criticism. Reducing every negative comment in a scientific discussion to race and gender creates a toxic environment. People are becoming afraid to engage in fear of being called a racist or sexist, which in turn reinforces the diversity problem. Sixthly, moral and ethics are set arbitrarily. The U.S. domestic politics dominate every discussion. At this very moment, thousands of Uyghurs are put into concentration camps based on computer vision algorithms invented by this community, and nobody seems even remotely to care. Adding a "broader impact" section at the end of every people will not make this stop. There are huge shitstorms because a researcher wasn't mentioned in an article. Meanwhile, the 1-billion+ people continent of Africa is virtually excluded from any meaningful ML discussion (besides a few Indaba workshops). Seventhly, there is a cut-throat publish-or-perish mentality. If you don't publish 5+ NeurIPS/ICML papers per year, you are a looser. Research groups have become so large that the PI does not even know the name of every PhD student anymore. Certain people submit 50+ papers per year to NeurIPS. The sole purpose of writing a paper has become to having one more NeurIPS paper in your CV. Quality is secondary; passing the peer-preview stage has become the primary objective. Finally, discussions have become disrespectful. Schmidhuber calls Hinton a thief, Gebru calls LeCun a white supremacist, Anandkumar calls Marcus a sexist, everybody is under attack, but nothing is improved. Albert Einstein was opposing the theory of quantum mechanics. Can we please stop demonizing those who do not share our exact views. We are allowed to disagree without going for the jugular. The moment we start silencing people because of their opinion is the moment scientific and societal progress dies. Best intentions, Yusuf

5-Day Applied Rationality Workshop for Machine Learning Students & Researchers

The Center for Applied Rationality is a Berkeley-based nonprofit that runs immersive workshops for entrepreneurs, researchers, students, and other ambitious, analytical, practically-minded people. The practice of “applied rationality”, which the workshops aim towards, involves noticing what cognitive algorithms you seem to be running, checking whether those algorithms seem to be helping you form accurate beliefs and achieve your goals, and looking for ways to improve them. A typical 4-day CFAR workshop costs $3900 to attend, but thanks to a generous grant from the Future of Life Institute this fall we will be running a free five-day workshop for students and researchers in the fields of machine learning and artificial intelligence. All costs are covered by this grant, including room, board, and flights. The workshop will take place this Aug 30 through Sep 4 in the San Francisco Bay Area and will include: 2 days focused on learning models and skills, such as how habits develop and how to redesign your habits. 2 days focused on practicing skills and applying them to whichever areas of your life you would like to make improvements on, such as how to make faster progress on projects or how to have more productive collaborations with colleagues. 1 day (special to this workshop) focused on discussion of the long-term impact of artificial intelligence, and on what reasoning habits — if spread across the relevant research communities — may increase the probability of positive long-term AI outcomes. Go here to read more or to apply, or ask questions here.

[N] TheSequence Scope: When it comes to machine learning, size matters: Microsoft's DeepSpeed framework, which can train a model with up to a trillion parameters

Hi there! Offering to your attention the latest edition of a weekly ML-newsletter that focusing on three things: impactful ML research papers, cool ML tech solutions, and ML use cases supported by investors. Please, see it below. Reddit is a new thing for me, and I've been struggling a bit with it, so please don't judge me too harsh for this promotion. This weekly digest is free and I hope you'd find the format convenient for you. Your feedback is very appreciated, and please feel free to sign up if you like it. 📝 Editorial  The recent emergence of pre-trained language models and transformer architectures pushed the creation of larger and larger machine learning models. Google’s BERT presented attention mechanism and transformer architecture possibilities as the “next big thing” in ML, and the numbers seem surreal. OpenAI’s GPT-2 set a record by processing 1.5 billion parameters, followed by Microsoft’s Turing-NLG, which processed 17 billion parameters just to see the new GPT-3 processing an astonishing 175 billion parameters. To not feel complacent, just this week Microsoft announced a new release of its DeepSpeed framework (which powers Turing-NLG), which can train a model with up to a trillion parameters. That sounds insane but it really isn’t.   What we are seeing is a consequence of several factors. First, computation power and parallelization techniques have evolved to a point where it is relatively easy to train machine learning models in large clusters of machines. Second and most importantly, in the current state of machine learning, larger models have regularly outperformed smaller and more specialized models. Knowledge reusability methods like transfer learning are still in very nascent stages. As a result, it’s really hard to build small models that can operate in uncertain environments. Furthermore, as models like GPT-3 and Turing-NLG have shown, there is some unexplainable magic that happens after models go past a certain size. Many of the immediate machine learning problems might be solved by scaling the current generation of neural network architectures. Plain and simple, when it comes to machine learning, size matters.   We would love to hear your opinions about the debate between broader-larger vs. smaller and more specialized models.   Leave a comment Now, to the most important developments in the AI industry this week 🔎 ML Research GPT-3 Falls Short in Machine Comprehension Proposed by researchers from a few major American universities, a 57-task test to measure models’ ability to reason poses challenges even for sophisticated models like GPT-3 ->read more in the original paper Better Text Summarization OpenAI published a paper showing a reinforcement learning with human feedback technique that can surpass supervised models ->read more on OpenAI blog Reinforcement Learning with Offline Datasets Researchers from the Berkeley AI Research (BAIR) Lab published a paper unveiling a method that uses offline datasets to improve reinforcement learning models->read more on BAIR blog 🤖 Cool AI Tech Releases New Version of DeepSpeed Microsoft open-sourced a new version of DeepSpeed, an open-source library for parallelizable training that can scale up to models with 1 trillion parameters->read more on Microsoft Research blog 💸 Money in AI AI-powered customer experience management platform Sprinklr has raised $200 million (kudos to our subscribers from Sprinklr 👏). Sprinklr's “AI listening processing” solution allows companies to get structured and meaningful sentiments and insights from unstructured customer data that comes from public conversations on different websites and social platforms. Xometry, an on-demand industrial parts marketplace, raises $75 million in Series E funding. The company provides a digital way of creating the right combination of buyers and manufacturers. Another example of AI implementation into matching two sides for a deal. Real estate tech company Orchard raises $69 million in its recent funding round. Orchard aims to digitize the whole real estate market, by developing a solution that combines machine learning and rapid human assistance to smooth the search, match the right deal, and simplify buying and selling relationships. Cybersecurity startup Pcysys raised $25 million in its funding round. Pcysys’ platform, which doesn’t require installation or network reconfiguration, uses algorithms to scan and “ethically” attack enterprise networks. Robotics farming company Iron Ox raised $20 million in a funding round. The system of farming robots is still semi-autonomous, the company’s goal is to become fully autonomous.  Insurtech company Descartes Underwriting raised $18.5 million. The company applies AI and machine learning technologies to climate risk predicting and insurance underwriting. Legaltech startup ThoughtRiver raised $10 million in its Series A round. Its AI solution applied to contract pre-screening aims to boost operational efficiency. Medtech startup Skin Analytics raised $5.1 million in Series A funding. Skin Analytics has developed a clinically validated AI system that can identify not only the important skin cancers but also precancerous lesions that can be treated, as well as a range of lesions that are benign. Amazon, along with several government organizations and three other industry partners, helped fund the National Science Foundation, a high-priority AI research initiative. The amount of funding is not disclosed. The content of TheSequence is written by Jesus Rodriguez, one of the most-read contributors to KDNuggets and TDS. You can check his Medium here.

[P] How to Identify Business Processes That Can Be Machine Learning-Enabled

Identifying Business Processes That Can Be Machine Learning-Enabled ➡ What to look for and expect when analyzing workflows for tasks can be automated with Machine Learning https://medium.com/ai%C2%B3-theory-practice-business/identifying-business-processes-that-can-be-ml-enabled-529cbe90aa84

[P] Contextual AI – SAP’s first open-source machine learning library for explainability

Machine learning shows great promise in the enterprise software space to change the way data is processed, insights are gained, and businesses are run. However, given how relatively new this field is, data scientists and machine learning engineers often find themselves possessing more questions than answers about their data and machine learning models. These may include: Is my data “valid,” or fit for training a machine learning model? Which parts of my data are more influential on the machine learning model’s learning outcomes? Why did the model make that prediction? At SAP, where we develop enterprise software embedded with machine learning, answering such questions with explainability is becoming a critical part of building trust with customers. Indeed, in products such as SAP Cash Application, where we automate the processing of various financial documents, providing a “why” to machine learning predictions has not only built transparency to our users, but it also helps establish the necessary auditability in our products. Explainability is thus becoming a topic of increasing interest to many in the company, and a group of us have been working on developing reusable explainability components that can be used by others. We are therefore excited to announce the release of contextual AI, SAP’s first open-source machine learning framework focused on adding explainability to various stages of a machine learning pipeline – data, training, and inference – thereby addressing the trust gap between machine learning systems and their end-users. Below are a few links for more information about our project: GitHub repository Documentation Blog post on the release We welcome any questions/feedback/contributions. Thanks, and take care!

[R] [online, free] Hong Kong Machine Learning Meetup! 17 October 7pm (GMT+8)

https://preview.redd.it/ysrie4qiruz71.jpg?width=1058&format=pjpg&auto=webp&s=51f39633ebf7715f623407004a230166df35f60d https://www.meetup.com/Hong-Kong-Machine-Learning-Meetup/events/281165939/ Join us for HKML S4E4, a monthly free & online machine learning meetup. Be aware, technical content. Talks: Application of Natural Language Processing to unstructured financial text to create alternative data for Finance; AI Automation and how it's a game-changer on the way we apply AI to Business; TBD

[N] New Trends to Power Faster Artificial Intelligence and Machine Learning Adoption?

In 2012, Google X lab created a neural network that can identify cats. Since then, technology companies have been increasingly adopting AI/ML on a large scale to build better applications and services for consumers (ToC). On the other hand, AI/ML's adoption on the enterprises' side (ToB) has yet to see the same growth trajectory due to the costs and complexities in both hardware and software. However, Since 2020, we started noticing three emerging tech trends that can help accelerate enterprises' adoption of AI/ML. Breakthrough in semiconductors: In 2020, Nvidia debut the concept of "Data Processing Unit," a new class of programmable processors that combine high-performance CPU with SmartNiC (network interface controller). Data centers can deploy DPUs to optimize computing offload and frees up CPUs to focus on intended tasks, such as machine learning. DPUs help resolve a significant bottleneck for ML training, where models, sometimes with billions of parameters, are way too big for traditional CPUs and GPUs to handle. Other leading semiconductor players, such as Marvell and Xilinx, follow suit with their in-house or partner-designed DPUs. Industry analysts have forecasted that the market size for DPUs in data centers alone could reach $50 billion by 2025. ​ https://preview.redd.it/l436muluhnn61.png?width=1430&format=png&auto=webp&s=ba8d1298056ea31bddd25f1596ff64b7e107580a Breakthrough in software: we also saw significant progress of "Conversational AI," a new form of AI that can understand and speak languages with human-like accuracy, in 2020. Conversational AI allows two-way interactions and provides a much better user experience than traditional AI-powered Chatbot, mostly a one-way response system. The secret of conversational AI is its ability to handle lots of human conversation variance. Developers have designed innovative algorithms such as "Switch transformers" and "Sparse training" to enable models to handle vast amounts of data. The size of conversational AI training models is enormous and keeps expanding. For example, in February 2021, Google Brain announced a model with 1.6 trillion parameters, nine times the size of the famous Open AI GPT-3 (175 billion parameters) unveiled in July 2020. GPT-3 is 100+ times bigger than GPT-2 introduced in 2019. ​ https://preview.redd.it/oajpi2yvhnn61.png?width=1430&format=png&auto=webp&s=1482913a98e17ddc1d62cc79864598d4012ad6f7 Cloud giants are expanding machine-learning platforms for developers. Andy Jassy famously said that "AI is shifting from a niche experiment inside technical departments to becoming more mainstream in business processes." in the 2020 AWS reInvent. During the conference, AWS rolled out many AI products across the technology stack, including AI chips (AWS Trainium), database (Aurora Machine Learning), and vertical solutions (Amazon Healthlake), etc. However, the most significant development is the drastic expansion of "Amazon SageMaker," one of the largest cloud machine-learning platforms. SageMaker has been offering new features to make it easier for developers to automate machine learning workflow. Microsoft Azure and Google Cloud are also growing their ML developer platforms. ​ https://preview.redd.it/z9wf2o8xhnn61.png?width=1430&format=png&auto=webp&s=9f607acfe8f0dbf36fb9b472f3cb40b80f13879e Witnessing these breakthroughs in semiconductor and software, coupled with cloud giants' effort to democratize AI, we see a coming inflection point of accelerated AI adoption in both ToC and ToB markets. So how do we benefit from this megatrend? In semiconductors, we like companies with DPUs exposure. In AI development and processing, we favor multi-cloud AI platforms such as Databricks. In enterprise software, we believe there will be a strong wave of new AI-based enterprise applications that can be creative and efficient in solving real-world problems.

[N] Pornhub uses machine learning to re-colour 20 historic erotic films (1890 to 1940, even some by Thomas Eddison)

As a data scientist, got to say it was pretty interesting to read about the use of machine learning to "train" an AI with 100,000 nudey videos and images to help it know how to colour films that were never in colour in the first place. Safe for work (non-Porhub) link -> https://itwire.com/business-it-news/data/pornhub-uses-ai-to-restore-century-old-erotic-films-to-titillating-technicolour.html

[D] Misuse of Deep Learning in Nature Journal’s Earthquake Aftershock Paper

Recently, I saw a post by Rajiv Shah, Chicago-based data-scientist, regarding an article published in Nature last year called Deep learning of aftershock patterns following large earthquakes, written by scientists at Harvard in collaboration with Google. Below is the article: Stand Up for Best Practices: Misuse of Deep Learning in Nature’s Earthquake Aftershock Paper The Dangers of Machine Learning Hype Practitioners of AI, machine learning, predictive modeling, and data science have grown enormously over the last few years. What was once a niche field defined by its blend of knowledge is becoming a rapidly growing profession. As the excitement around AI continues to grow, the new wave of ML augmentation, automation, and GUI tools will lead to even more growth in the number of people trying to build predictive models. But here’s the rub: While it becomes easier to use the tools of predictive modeling, predictive modeling knowledge is not yet a widespread commodity. Errors can be counterintuitive and subtle, and they can easily lead you to the wrong conclusions if you’re not careful. I’m a data scientist who works with dozens of expert data science teams for a living. In my day job, I see these teams striving to build high-quality models. The best teams work together to review their models to detect problems. There are many hard-to-detect-ways that lead to problematic models (say, by allowing target leakage into their training data). Identifying issues is not fun. This requires admitting that exciting results are “too good to be true” or that their methods were not the right approach. In other words, it’s less about the sexy data science hype that gets headlines and more about a rigorous scientific discipline. Bad Methods Create Bad Results Almost a year ago, I read an article in Nature that claimed unprecedented accuracy in predicting earthquake aftershocks by using deep learning. Reading the article, my internal radar became deeply suspicious of their results. Their methods simply didn’t carry many of the hallmarks of careful predicting modeling. I started to dig deeper. In the meantime, this article blew up and became widely recognized! It was even included in the release notes for Tensorflow as an example of what deep learning could do. However, in my digging, I found major flaws in the paper. Namely, data leakage which leads to unrealistic accuracy scores and a lack of attention to model selection (you don’t build a 6 layer neural network when a simpler model provides the same level of accuracy). To my earlier point: these are subtle, but incredibly basic predictive modeling errors that can invalidate the entire results of an experiment. Data scientists are trained to recognize and avoid these issues in their work. I assumed that this was simply overlooked by the author, so I contacted her and let her know so that she could improve her analysis. Although we had previously communicated, she did not respond to my email over concerns with the paper. Falling On Deaf Ears So, what was I to do? My coworkers told me to just tweet it and let it go, but I wanted to stand up for good modeling practices. I thought reason and best practices would prevail, so I started a 6-month process of writing up my results and shared them with Nature. Upon sharing my results, I received a note from Nature in January 2019 that despite serious concerns about data leakage and model selection that invalidate their experiment, they saw no need to correct the errors, because “Devries et al. are concerned primarily with using machine learning as [a] tool to extract insight into the natural world, and not with details of the algorithm design.” The authors provided a much harsher response. You can read the entire exchange on my github. It’s not enough to say that I was disappointed. This was a major paper (it’s Nature!) that bought into AI hype and published a paper despite it using flawed methods. Then, just this week, I ran across articles by Arnaud Mignan and Marco Broccardo on shortcomings that they found in the aftershocks article. Here are two more data scientists with expertise in earthquake analysis who also noticed flaws in the paper. I also have placed my analysis and reproducible code on github. Standing Up For Predictive Modeling Methods I want to make it clear: my goal is not to villainize the authors of the aftershocks paper. I don’t believe that they were malicious, and I think that they would argue their goal was to just show how machine learning could be applied to aftershocks. Devries is an accomplished earthquake scientist who wanted to use the latest methods for her field of study and found exciting results from it. But here’s the problem: their insights and results were based on fundamentally flawed methods. It’s not enough to say, “This isn’t a machine learning paper, it’s an earthquake paper.” If you use predictive modeling, then the quality of your results are determined by the quality of your modeling. Your work becomes data science work, and you are on the hook for your scientific rigor. There is a huge appetite for papers that use the latest technologies and approaches. It becomes very difficult to push back on these papers. But if we allow papers or projects with fundamental issues to advance, it hurts all of us. It undermines the field of predictive modeling. Please push back on bad data science. Report bad findings to papers. And if they don’t take action, go to twitter, post about it, share your results and make noise. This type of collective action worked to raise awareness of p-values and combat the epidemic of p-hacking. We need good machine learning practices if we want our field to continue to grow and maintain credibility. Link to Rajiv's Article Original Nature Publication (note: paywalled) GitHub repo contains an attempt to reproduce Nature's paper Confrontational correspondence with authors

[D] What is your honest experience with reinforcement learning?

In my personal experience, SOTA RL algorithms simply don't work. I've tried working with reinforcement learning for over 5 years. I remember when Alpha Go defeated the world famous Go player, Lee Sedol, and everybody thought RL would take the ML community by storm. Yet, outside of toy problems, I've personally never found a practical use-case of RL. What is your experience with it? Aside from Ad recommendation systems and RLHF, are there legitimate use-cases of RL? Or, was it all hype? Edit: I know a lot about AI. I built NexusTrade, an AI-Powered automated investing tool that lets non-technical users create, update, and deploy their trading strategies. I’m not an idiot nor a noob; RL is just ridiculously hard. Edit 2: Since my comments are being downvoted, here is a link to my article that better describes my position. It's not that I don't understand RL. I released my open-source code and wrote a paper on it. It's the fact that it's EXTREMELY difficult to understand. Other deep learning algorithms like CNNs (including ResNets), RNNs (including GRUs and LSTMs), Transformers, and GANs are not hard to understand. These algorithms work and have practical use-cases outside of the lab. Traditional SOTA RL algorithms like PPO, DDPG, and TD3 are just very hard. You need to do a bunch of research to even implement a toy problem. In contrast, the decision transformer is something anybody can implement, and it seems to match or surpass the SOTA. You don't need two networks battling each other. You don't have to go through hell to debug your network. It just naturally learns the best set of actions in an auto-regressive manner. I also didn't mean to come off as arrogant or imply that RL is not worth learning. I just haven't seen any real-world, practical use-cases of it. I simply wanted to start a discussion, not claim that I know everything. Edit 3: There's a shockingly number of people calling me an idiot for not fully understanding RL. You guys are wayyy too comfortable calling people you disagree with names. News-flash, not everybody has a PhD in ML. My undergraduate degree is in biology. I self-taught myself the high-level maths to understand ML. I'm very passionate about the field; I just have VERY disappointing experiences with RL. Funny enough, there are very few people refuting my actual points. To summarize: Lack of real-world applications Extremely complex and inaccessible to 99% of the population Much harder than traditional DL algorithms like CNNs, RNNs, and GANs Sample inefficiency and instability Difficult to debug Better alternatives, such as the Decision Transformer Are these not legitimate criticisms? Is the purpose of this sub not to have discussions related to Machine Learning? To the few commenters that aren't calling me an idiot...thank you! Remember, it costs you nothing to be nice! Edit 4: Lots of people seem to agree that RL is over-hyped. Unfortunately those comments are downvoted. To clear up some things: We've invested HEAVILY into reinforcement learning. All we got from this investment is a robot that can be super-human at (some) video games. AlphaFold did not use any reinforcement learning. SpaceX doesn't either. I concede that it can be useful for robotics, but still argue that it's use-cases outside the lab are extremely limited. If you're stumbling on this thread and curious about an RL alternative, check out the Decision Transformer. It can be used in any situation that a traditional RL algorithm can be used. Final Edit: To those who contributed more recently, thank you for the thoughtful discussion! From what I learned, model-based models like Dreamer and IRIS MIGHT have a future. But everybody who has actually used model-free models like DDPG unanimously agree that they suck and don’t work.

AI Implementation & Learning Experiences in Business - What's Your Story?

AI Implementation & Learning Experiences in Business - What's Your Story? Hey everyone! I'm researching how people are actually learning and implementing AI tools (like ChatGPT, Copilot) in business settings, and I'd love to hear your real experiences. If you're willing to share: 🔹 Learning: How are you learning AI? (self-taught, courses, trial & error?) What's been frustrating about the learning process? Found any particularly good resources? 🔹 Implementation: What's been the biggest challenge in actually using AI at work? Where does implementation usually get stuck? Any unexpected problems you've hit? Would especially love to hear from: People just starting out Those who tried and hit roadblocks Folks who've successfully implemented AI Anyone who attempted and gave up Really just trying to understand the real-world patterns and challenges people are facing. Your experiences (good or bad) could help others avoid the same pitfalls.

If you were a Machine learning engineer what Ai project will you build ?

I’m a machine learning engineer and I’ve been testing cool features and integrating some modules for some SMB, I’m open to work if you have some ideas or needs. Cheers 🥂

Is striking a balance between learning Python for AI tools creation and pursuing filmmaking/editing a realistic goal?

I've been drawn into the world of AI and automation and want to harness it for tool creation as I get lots of ideas and see the value in learning Python for that, even if I learn no code tools as python help with advanced functions I heard? (I’m totally not a coder) But I also have other interests like designing life management systems like in Notion, also really want to learn filmmaking and editing That being said, Is it possible to learn python and AI tool building without having it take most of my time? Is it realistic for it to be on the side while I pursue these other interests? I know notion and designing systems can be related and work side by side to tool building, but what if I don’t really wanna be a coder and spend all my time doing that? 😔

IVAN.ed: The platform for Social Learning ( SOMEONE CAN USE THIS IDEA BECAUSE I CURRENTLY DON'T HAVE THE TECH KNOWLEDEGE TO MAKE IT COME TRUE )

Overview: IVAN.ed is an innovative educational platform designed to transform the way students and educators interact and share knowledge. By combining the best elements of social media with a focus on learning, IVAN.ed aims to create a dynamic, engaging, and user-friendly environment for educational content. Key Features: Social Learning Network: A platform where students, educators, and experts can create and share educational content, similar to a social media experience but dedicated to learning. AI-Driven Content Moderation: Implementing advanced AI algorithms to ensure high-quality and relevant content, maintaining the platform’s integrity and usefulness. User Profiles and Content Creation: Users can build profiles, upload videos, create posts, and engage with content through comments, (instead of like there is the knowledge meter , based on what as taught in the videos), notes will be provided down of each video using ai. Enhanced Discovery: Advanced search and recommendation systems to help users find content that matches their interests and educational needs. Minimal Distractions: user interface designed to minimize distractions and enhance focus, making the learning experience more efficient. Goals: Accessibility: Provide a free or low-cost platform where knowledge is accessible to all. Community Engagement: Foster a vibrant learning community with meaningful interactions. Innovation: Leverage AI to maintain high standards of content and user experience. Conclusion: IVAN.ed aims to bridge the gap between traditional education and modern social media, creating an interactive and engaging space for learning. By prioritizing user experience and content quality, IVAN.ed will empower educators and learners alike, making education more accessible and impactful. THIS MESSAGE WAS GENERATED USING GPT , SINCE I AM NOT VERY GOOD AN CONVEING MY IDEAS , BUT NOW I NEED PEOPLE TO SEE THIS IDEA AND CRITIZE IT OR EVEN GIVE ME SOME IDEAS TO MAKE IT BETTER , BUT THIS IS JUST THE BLUEPRINT AND I HAVEN'T EVEN BEGUN THE ACTUAL DEVELOPMENT PHASE, BUT I AM OPEN FOR SOME HELP ! -thank you if you read it this far

Is striking a balance between learning Python for AI tools creation and pursuing filmmaking/editing a realistic goal?

I've been drawn into the world of AI and automation and want to harness it for tool creation as I get lots of ideas and see the value in learning Python for that, even if I learn no code tools as python help with advanced functions I heard? (I’m totally not a coder) But I also have other interests like designing life management systems like in Notion, also really want to learn filmmaking and editing That being said, Is it possible to learn python and AI tool building without having it take most of my time? Is it realistic for it to be on the side while I pursue these other interests? I know notion and designing systems can be related and work side by side to tool building, but what if I don’t really wanna be a coder and spend all my time doing that? 😔

📢 Day 2 : Learning Linear Regression – Understanding the Math Behind ML

Hey everyone! Today, I studied Linear Regression and its mathematical representation. 📖 Key Concepts: ✅ Hypothesis Function → h(x) =θ0+θ1x ✅ Cost Function (Squared Error Loss) → Measures how well predictions match actual values. ✅ Gradient Descent → Optimizes parameters to minimize cost. Here are my handwritten notes summarizing what I learned! Next, I’ll implement this in Python. Any dataset recommendations for practice? 🚀 #MachineLearning #AI #LinearRegression

Artificial Intelligence for Business Creating Value with Machine Learning

Learn how to create value with machine learning and artificial intelligence in business

Machine Learning Basics

Learn the basics of machine learning including supervised and unsupervised learning neural networks and deep learning

No Code AI and Machine Learning Program

A program that teaches AI and Machine Learning concepts without requiring coding skills

Practical AI Machine Learning Data Science LLM

Listen to the technology audio show Practical AI Machine Learning Data Science LLM from Changelog Media in Apple Podcasts Spotify YouTube Overcast and other podcast apps

Beginner Introduction to Generative AI Learning Path

This learning path provides an overview of generative AI concepts from the fundamentals of large language models to responsible AI principles

No Code AI and Machine Learning Building Data Science Solutions

In this 12 week program you will learn to use AI and Machine Learning to make data driven business decisions by understanding the theory and practical applications of supervised and unsupervised learning neural networks recommendation engines computer vision etc

Production-Level-Deep-Learning

:bulb: A Guide to Production Level Deep Learning :clapper: :scroll: :ferry: 🇨🇳 Translation in Chinese.md) :label: NEW: Machine Learning Interviews :label: Note: This repo is under continous development, and all feedback and contribution are very welcome :blush: Deploying deep learning models in production can be challenging, as it is far beyond training models with good performance. Several distinct components need to be designed and developed in order to deploy a production level deep learning system (seen below): This repo aims to be an engineering guideline for building production-level deep learning systems which will be deployed in real world applications. The material presented here is borrowed from Full Stack Deep Learning Bootcamp (by Pieter Abbeel at UC Berkeley, Josh Tobin at OpenAI, and Sergey Karayev at Turnitin), TFX workshop by Robert Crowe, and Pipeline.ai's Advanced KubeFlow Meetup by Chris Fregly. Machine Learning Projects Fun :flushed: fact: 85% of AI projects fail. 1 Potential reasons include: Technically infeasible or poorly scoped Never make the leap to production Unclear success criteria (metrics) Poor team management ML Projects lifecycle Importance of understanding state of the art in your domain: Helps to understand what is possible Helps to know what to try next Mental Model for ML project The two important factors to consider when defining and prioritizing ML projects: High Impact: Complex parts of your pipeline Where "cheap prediction" is valuable Where automating complicated manual process is valuable Low Cost: Cost is driven by: Data availability Performance requirements: costs tend to scale super-linearly in the accuracy requirement Problem difficulty: Some of the hard problems include: unsupervised learning, reinforcement learning, and certain categories of supervised learning Full stack pipeline The following figure represents a high level overview of different components in a production level deep learning system: In the following, we will go through each module and recommend toolsets and frameworks as well as best practices from practitioners that fit each component. Data Management 1.1 Data Sources Supervised deep learning requires a lot of labeled data Labeling own data is costly! Here are some resources for data: Open source data (good to start with, but not an advantage) Data augmentation (a MUST for computer vision, an option for NLP) Synthetic data (almost always worth starting with, esp. in NLP) 1.2 Data Labeling Requires: separate software stack (labeling platforms), temporary labor, and QC Sources of labor for labeling: Crowdsourcing (Mechanical Turk): cheap and scalable, less reliable, needs QC Hiring own annotators: less QC needed, expensive, slow to scale Data labeling service companies: FigureEight Labeling platforms: Diffgram: Training Data Software (Computer Vision) Prodigy: An annotation tool powered by active learning (by developers of Spacy), text and image HIVE: AI as a Service platform for computer vision Supervisely: entire computer vision platform Labelbox: computer vision Scale AI data platform (computer vision & NLP) 1.3. Data Storage Data storage options: Object store: Store binary data (images, sound files, compressed texts) Amazon S3 Ceph Object Store Database: Store metadata (file paths, labels, user activity, etc). Postgres is the right choice for most of applications, with the best-in-class SQL and great support for unstructured JSON. Data Lake: to aggregate features which are not obtainable from database (e.g. logs) Amazon Redshift Feature Store: store, access, and share machine learning features (Feature extraction could be computationally expensive and nearly impossible to scale, hence re-using features by different models and teams is a key to high performance ML teams). FEAST (Google cloud, Open Source) Michelangelo Palette (Uber) Suggestion: At training time, copy data into a local or networked filesystem (NFS). 1 1.4. Data Versioning It's a "MUST" for deployed ML models: Deployed ML models are part code, part data. 1 No data versioning means no model versioning. Data versioning platforms: DVC: Open source version control system for ML projects Pachyderm: version control for data Dolt: a SQL database with Git-like version control for data and schema 1.5. Data Processing Training data for production models may come from different sources, including Stored data in db and object stores, log processing, and outputs of other classifiers*. There are dependencies between tasks, each needs to be kicked off after its dependencies are finished. For example, training on new log data, requires a preprocessing step before training. Makefiles are not scalable. "Workflow manager"s become pretty essential in this regard. Workflow orchestration: Luigi by Spotify Airflow by Airbnb: Dynamic, extensible, elegant, and scalable (the most widely used) DAG workflow Robust conditional execution: retry in case of failure Pusher supports docker images with tensorflow serving Whole workflow in a single .py file Development, Training, and Evaluation 2.1. Software engineering Winner language: Python Editors: Vim Emacs VS Code (Recommended by the author): Built-in git staging and diff, Lint code, open projects remotely through ssh Notebooks: Great as starting point of the projects, hard to scale (fun fact: Netflix’s Notebook-Driven Architecture is an exception, which is entirely based on nteract suites). nteract: a next-gen React-based UI for Jupyter notebooks Papermill: is an nteract library built for parameterizing, executing, and analyzing* Jupyter Notebooks. Commuter: another nteract project which provides a read-only display of notebooks (e.g. from S3 buckets). Streamlit: interactive data science tool with applets Compute recommendations 1: For individuals or startups*: Development: a 4x Turing-architecture PC Training/Evaluation: Use the same 4x GPU PC. When running many experiments, either buy shared servers or use cloud instances. For large companies:* Development: Buy a 4x Turing-architecture PC per ML scientist or let them use V100 instances Training/Evaluation: Use cloud instances with proper provisioning and handling of failures Cloud Providers: GCP: option to connect GPUs to any instance + has TPUs AWS: 2.2. Resource Management Allocating free resources to programs Resource management options: Old school cluster job scheduler ( e.g. Slurm workload manager ) Docker + Kubernetes Kubeflow Polyaxon (paid features) 2.3. DL Frameworks Unless having a good reason not to, use Tensorflow/Keras or PyTorch. 1 The following figure shows a comparison between different frameworks on how they stand for "developement" and "production"*. 2.4. Experiment management Development, training, and evaluation strategy: Always start simple Train a small model on a small batch. Only if it works, scale to larger data and models, and hyperparameter tuning! Experiment management tools: Tensorboard provides the visualization and tooling needed for ML experimentation Losswise (Monitoring for ML) Comet: lets you track code, experiments, and results on ML projects Weights & Biases: Record and visualize every detail of your research with easy collaboration MLFlow Tracking: for logging parameters, code versions, metrics, and output files as well as visualization of the results. Automatic experiment tracking with one line of code in python Side by side comparison of experiments Hyper parameter tuning Supports Kubernetes based jobs 2.5. Hyperparameter Tuning Approaches: Grid search Random search Bayesian Optimization HyperBand and Asynchronous Successive Halving Algorithm (ASHA) Population-based Training Platforms: RayTune: Ray Tune is a Python library for hyperparameter tuning at any scale (with a focus on deep learning and deep reinforcement learning). Supports any machine learning framework, including PyTorch, XGBoost, MXNet, and Keras. Katib: Kubernete's Native System for Hyperparameter Tuning and Neural Architecture Search, inspired by Google vizier and supports multiple ML/DL frameworks (e.g. TensorFlow, MXNet, and PyTorch). Hyperas: a simple wrapper around hyperopt for Keras, with a simple template notation to define hyper-parameter ranges to tune. SIGOPT: a scalable, enterprise-grade optimization platform Sweeps from [Weights & Biases] (https://www.wandb.com/): Parameters are not explicitly specified by a developer. Instead they are approximated and learned by a machine learning model. Keras Tuner: A hyperparameter tuner for Keras, specifically for tf.keras with TensorFlow 2.0. 2.6. Distributed Training Data parallelism: Use it when iteration time is too long (both tensorflow and PyTorch support) Ray Distributed Training Model parallelism: when model does not fit on a single GPU Other solutions: Horovod Troubleshooting [TBD] Testing and Deployment 4.1. Testing and CI/CD Machine Learning production software requires a more diverse set of test suites than traditional software: Unit and Integration Testing: Types of tests: Training system tests: testing training pipeline Validation tests: testing prediction system on validation set Functionality tests: testing prediction system on few important examples Continuous Integration: Running tests after each new code change pushed to the repo SaaS for continuous integration: Argo: Open source Kubernetes native workflow engine for orchestrating parallel jobs (incudes workflows, events, CI and CD). CircleCI: Language-Inclusive Support, Custom Environments, Flexible Resource Allocation, used by instacart, Lyft, and StackShare. Travis CI Buildkite: Fast and stable builds, Open source agent runs on almost any machine and architecture, Freedom to use your own tools and services Jenkins: Old school build system 4.2. Web Deployment Consists of a Prediction System and a Serving System Prediction System: Process input data, make predictions Serving System (Web server): Serve prediction with scale in mind Use REST API to serve prediction HTTP requests Calls the prediction system to respond Serving options: Deploy to VMs, scale by adding instances Deploy as containers, scale via orchestration Containers Docker Container Orchestration: Kubernetes (the most popular now) MESOS Marathon Deploy code as a "serverless function" Deploy via a model serving solution Model serving: Specialized web deployment for ML models Batches request for GPU inference Frameworks: Tensorflow serving MXNet Model server Clipper (Berkeley) SaaS solutions Seldon: serve and scale models built in any framework on Kubernetes Algorithmia Decision making: CPU or GPU? CPU inference: CPU inference is preferable if it meets the requirements. Scale by adding more servers, or going serverless. GPU inference: TF serving or Clipper Adaptive batching is useful (Bonus) Deploying Jupyter Notebooks: Kubeflow Fairing is a hybrid deployment package that let's you deploy your Jupyter notebook* codes! 4.5 Service Mesh and Traffic Routing Transition from monolithic applications towards a distributed microservice architecture could be challenging. A Service mesh (consisting of a network of microservices) reduces the complexity of such deployments, and eases the strain on development teams. Istio: a service mesh to ease creation of a network of deployed services with load balancing, service-to-service authentication, monitoring, with few or no code changes in service code. 4.4. Monitoring: Purpose of monitoring: Alerts for downtime, errors, and distribution shifts Catching service and data regressions Cloud providers solutions are decent Kiali:an observability console for Istio with service mesh configuration capabilities. It answers these questions: How are the microservices connected? How are they performing? Are we done? 4.5. Deploying on Embedded and Mobile Devices Main challenge: memory footprint and compute constraints Solutions: Quantization Reduced model size MobileNets Knowledge Distillation DistillBERT (for NLP) Embedded and Mobile Frameworks: Tensorflow Lite PyTorch Mobile Core ML ML Kit FRITZ OpenVINO Model Conversion: Open Neural Network Exchange (ONNX): open-source format for deep learning models 4.6. All-in-one solutions Tensorflow Extended (TFX) Michelangelo (Uber) Google Cloud AI Platform Amazon SageMaker Neptune FLOYD Paperspace Determined AI Domino data lab Tensorflow Extended (TFX) [TBD] Airflow and KubeFlow ML Pipelines [TBD] Other useful links: Lessons learned from building practical deep learning systems Machine Learning: The High Interest Credit Card of Technical Debt Contributing References: [1]: Full Stack Deep Learning Bootcamp, Nov 2019. [2]: Advanced KubeFlow Workshop by Pipeline.ai, 2019. [3]: TFX: Real World Machine Learning in Production

Introduction_to_Machine_Learning

Machine Learning Course Welcome to the "Machine Learning" course of Department of Computer Engineering, Sharif University of Technology. You can access slides, Jupyter notebooks, and exercises. Please note that this content is a work in progress and will be updated throughout Fall 2024 semester. For course materials from previous semesters, please visit the Previous Semesters section. Class videos and additional resources can be found on the SharifML website (Persian language). Feel free to use this content, provided you properly cite both the course and this GitHub repository. For more details, see the Creative Commons BY license.

awesome-quantum-machine-learning

Awesome Quantum Machine Learning A curated list of awesome quantum machine learning algorithms,study materials,libraries and software (by language). Table of Contents INTRODUCTION Why Quantum Machine Learning? BASICS What is Quantum Mechanics? What is Quantum Computing? What is Topological Quantum Computing? Quantum Computing vs Classical Computing QUANTUM COMPUTING Atom Structure Photon wave Electron Fluctuation or spin States SuperPosition SuperPosition specific for machine learning(Quantum Walks) Classical Bit Quantum Bit or Qubit or Qbit Basic Gates in Quantum Computing Quantum Diode Quantum Transistor Quantum Processor Quantum Registery QRAM Quantum Entanglement QUANTUM COMPUTING MACHINE LEARNING BRIDGE Complex Numbers Tensors Tensors Network Oracle Hadamard transform Hilbert Space eigenvalues and eigenvectors Schr¨odinger Operators Quantum lambda calculus Quantum Amplitute Phase Qubits Encode and Decode convert classical bit to qubit Quantum Dirac and Kets Quantum Complexity Arbitrary State Generation QUANTUM ALGORITHMS Quantum Fourier Transform Variational-Quantum-Eigensolver Grovers Algorithm Shor's algorithm Hamiltonian Oracle Model Bernstein-Vazirani Algorithm Simon’s Algorithm Deutsch-Jozsa Algorithm Gradient Descent Phase Estimation Haar Tansform Quantum Ridgelet Transform Quantum NP Problem QUANTUM MACHINE LEARNING ALGORITHMS Quantum K-Nearest Neighbour Quantum K-Means Quantum Fuzzy C-Means Quantum Support Vector Machine Quantum Genetic Algorithm Quantum Hidden Morkov Models Quantum state classification with Bayesian methods Quantum Ant Colony Optimization Quantum Cellular Automata Quantum Classification using Principle Component Analysis Quantum Inspired Evolutionary Algorithm Quantum Approximate Optimization Algorithm Quantum Elephant Herding Optimization Quantum-behaved Particle Swarm Optimization Quantum Annealing Expectation-Maximization QAUNTUM NEURAL NETWORK Quantum perceptrons Qurons Quantum Auto Encoder Quantum Annealing Photonic Implementation of Quantum Neural Network Quantum Feed Forward Neural Network Quantum Boltzman Neural Network Quantum Neural Net Weight Storage Quantum Upside Down Neural Net Quantum Hamiltonian Neural Net QANN QPN SAL Quantum Hamiltonian Learning Compressed Quantum Hamiltonian Learning QAUNTUM STATISTICAL DATA ANALYSIS Quantum Probability Theory Kolmogorovian Theory Quantum Measurement Problem Intuitionistic Logic Heyting Algebra Quantum Filtering Paradoxes Quantum Stochastic Process Double Negation Quantum Stochastic Calculus Hamiltonian Calculus Quantum Ito's Formula Quantum Stochastic Differential Equations(QSDE) Quantum Stochastic Integration Itō Integral Quasiprobability Distributions Quantum Wiener Processes Quantum Statistical Ensemble Quantum Density Operator or Density Matrix Gibbs Canonical Ensemble Quantum Mean Quantum Variance Envariance Polynomial Optimization Quadratic Unconstrained Binary Optimization Quantum Gradient Descent Quantum Based Newton's Method for Constrained Optimization Quantum Based Newton's Method for UnConstrained Optimization Quantum Ensemble Quantum Topology Quantum Topological Data Analysis Quantum Bayesian Hypothesis Quantum Statistical Decision Theory Quantum Minimax Theorem Quantum Hunt-Stein Theorem Quantum Locally Asymptotic Normality Quantum Ising Model Quantum Metropolis Sampling Quantum Monte Carlo Approximation Quantum Bootstrapping Quantum Bootstrap Aggregation Quantum Decision Tree Classifier Quantum Outlier Detection Cholesky-Decomposition for Quantum Chemistry Quantum Statistical Inference Asymptotic Quantum Statistical Inference Quantum Gaussian Mixture Modal Quantum t-design Quantum Central Limit Theorem Quantum Hypothesis Testing Quantum Chi-squared and Goodness of Fit Testing Quantum Estimation Theory Quantum Way of Linear Regression Asymptotic Properties of Quantum Outlier Detection in Quantum Concepts QAUNTUM ARTIFICIAL INTELLIGENCE Heuristic Quantum Mechanics Consistent Quantum Reasoning Quantum Reinforcement Learning QAUNTUM COMPUTER VISION QUANTUM PROGRAMMING LANGUAGES , TOOLs and SOFTWARES ALL QUANTUM ALGORITHMS SOURCE CODES , GITHUBS QUANTUM HOT TOPICS Quantum Cognition Quantum Camera Quantum Mathematics Quantum Information Processing Quantum Image Processing Quantum Cryptography Quantum Elastic Search Quantum DNA Computing Adiabetic Quantum Computing Topological Big Data Anlytics using Quantum Hamiltonian Time Based Quantum Computing Deep Quantum Learning Quantum Tunneling Quantum Entanglment Quantum Eigen Spectrum Quantum Dots Quantum elctro dynamics Quantum teleportation Quantum Supremacy Quantum Zeno Effect Quantum Cohomology Quantum Chromodynamics Quantum Darwinism Quantum Coherence Quantum Decoherence Topological Quantum Computing Topological Quantum Field Theory Quantum Knots Topological Entanglment Boson Sampling Quantum Convolutional Code Stabilizer Code Quantum Chaos Quantum Game Theory Quantum Channel Tensor Space Theory Quantum Leap Quantum Mechanics for Time Travel Quantum Secured Block Chain Quantum Internet Quantum Optical Network Quantum Interference Quantum Optical Network Quantum Operating System Electron Fractionalization Flip-Flop Quantum Computer Quantum Information with Gaussian States Quantum Anomaly Detection Distributed Secure Quantum Machine Learning Decentralized Quantum Machine Learning Artificial Agents for Quantum Designs Light Based Quantum Chips for AI Training QUANTUM STATE PREPARATION ALGORITHM FOR MACHINE LEARNING Pure Quantum State Product State Matrix Product State Greenberger–Horne–Zeilinger State W state AKLT model Majumdar–Ghosh Model Multistate Landau–Zener Models Projected entangled-pair States Infinite Projected entangled-pair States Corner Transfer Matrix Method Tensor-entanglement Renormalization Tree Tensor Network for Supervised Learning QUANTUM MACHINE LEARNING VS DEEP LEARNING QUANTUM MEETUPS QUANTUM GOOGLE GROUPS QUANTUM BASED COMPANIES QUANTUM LINKEDLIN QUANTUM BASED DEGREES CONSOLIDATED QUANTUM ML BOOKS CONSOLIDATED QUANTUM ML VIDEOS CONSOLIDATED QUANTUM ML Reserach Papers CONSOLIDATED QUANTUM ML Reserach Scientist RECENT QUANTUM UPDATES FORUM ,PAGES AND NEWSLETTER INTRODUCTION Why Quantum Machine Learning? Machine Learning(ML) is just a term in recent days but the work effort start from 18th century. What is Machine Learning ? , In Simple word the answer is making the computer or application to learn themselves . So its totally related with computing fields like computer science and IT ? ,The answer is not true . ML is a common platform which is mingled in all the aspects of the life from agriculture to mechanics . Computing is a key component to use ML easily and effectively . To be more clear ,Who is the mother of ML ?, As no option Mathematics is the mother of ML . The world tremendous invention complex numbers given birth to this field . Applying mathematics to the real life problem always gives a solution . From Neural Network to the complex DNA is running under some specific mathematical formulas and theorems. As computing technology growing faster and faster mathematics entered into this field and makes the solution via computing to the real world . In the computing technology timeline once a certain achievements reached peoples interested to use advanced mathematical ideas such as complex numbers ,eigen etc and its the kick start for the ML field such as Artificial Neural Network ,DNA Computing etc. Now the main question, why this field is getting boomed now a days ? , From the business perspective , 8-10 Years before during the kick start time for ML ,the big barrier is to merge mathematics into computing field . people knows well in computing has no idea on mathematics and research mathematician has no idea on what is computing . The education as well as the Job Opportunities is like that in that time . Even if a person tried to study both then the business value for making a product be not good. Then the top product companies like Google ,IBM ,Microsoft decided to form a team with mathematician ,a physician and a computer science person to come up with various ideas in this field . Success of this team made some wonderful products and they started by providing cloud services using this product . Now we are in this stage. So what's next ? , As mathematics reached the level of time travel concepts but the computing is still running under classical mechanics . the companies understood, the computing field must have a change from classical to quantum, and they started working on the big Quantum computing field, and the market named this field as Quantum Information Science .The kick start is from Google and IBM with the Quantum Computing processor (D-Wave) for making Quantum Neural Network .The field of Quantum Computer Science and Quantum Information Science will do a big change in AI in the next 10 years. Waiting to see that........... .(google, ibm). References D-Wave - Owner of a quantum processor Google - Quantum AI Lab IBM - Quantum Computer Lab Quora - Question Regarding future of quantum AI NASA - NASA Quantum Works Youtube - Google Video of a Quantum Processor external-link - MIT Review microsoft new product - Newly Launched Microsoft Quantum Language and Development Kit microsoft - Microsoft Quantum Related Works Google2 - Google Quantum Machine Learning Blog BBC - About Google Quantum Supremacy,IBM Quantum Computer and Microsoft Q Google Quantum Supremacy - Latest 2019 Google Quantum Supremacy Achievement IBM Quantum Supremacy - IBM Talk on Quantum Supremacy as a Primer VICE on the fight - IBM Message on Google Quantum Supremacy IBM Zurich Quantum Safe Cryptography - An interesting startup to replace all our Certificate Authority Via Cloud and IBM Q BASICS What is Quantum Mechanics? In a single line study of an electron moved out of the atom then its classical mechanic ,vibrates inside the atom its quantum mechanics WIKIPEDIA - Basic History and outline LIVESCIENCE. - A survey YOUTUBE - Simple Animation Video Explanining Great. What is Quantum Computing? A way of parallel execution of multiple processess in a same time using qubit ,It reduces the computation time and size of the processor probably in neuro size WIKIPEDIA - Basic History and outline WEBOPEDIA. - A survey YOUTUBE - Simple Animation Video Explanining Great. Quantum Computing vs Classical Computing LINK - Basic outline Quantum Computing Atom Structure one line : Electron Orbiting around the nucleous in an eliptical format YOUTUBE - A nice animation video about the basic atom structure Photon Wave one line : Light nornmally called as wave transmitted as photons as similar as atoms in solid particles YOUTUBE - A nice animation video about the basic photon 1 YOUTUBE - A nice animation video about the basic photon 2 Electron Fluctuation or spin one line : When a laser light collide with solid particles the electrons of the atom will get spin between the orbitary layers of the atom ) YOUTUBE - A nice animation video about the basic Electron Spin 1 YOUTUBE - A nice animation video about the basic Electron Spin 2 YOUTUBE - A nice animation video about the basic Electron Spin 3 States one line : Put a point on the spinning electron ,if the point is in the top then state 1 and its in bottom state 0 YOUTUBE - A nice animation video about the Quantum States SuperPosition two line : During the spin of the electron the point may be in the middle of upper and lower position, So an effective decision needs to take on the point location either 0 or 1 . Better option to analyse it along with other electrons using probability and is called superposition YOUTUBE - A nice animation video about the Quantum Superposition SuperPosition specific for machine learning(Quantum Walks) one line : As due to computational complexity ,quantum computing only consider superposition between limited electrons ,In case to merge more than one set quantum walk be the idea YOUTUBE - A nice video about the Quantum Walks Classical Bits one line : If electron moved from one one atom to other ,from ground state to excited state a bit value 1 is used else bit value 0 used Qubit one line : The superposition value of states of a set of electrons is Qubit YOUTUBE - A nice video about the Quantum Bits 1 YOUTUBE - A nice video about the Bits and Qubits 2 Basic Gates in Quantum Computing one line : As like NOT, OR and AND , Basic Gates like NOT, Hadamard gate , SWAP, Phase shift etc can be made with quantum gates YOUTUBE - A nice video about the Quantum Gates Quantum Diode one line : Quantum Diodes using a different idea from normal diode, A bunch of laser photons trigger the electron to spin and the quantum magnetic flux will capture the information YOUTUBE - A nice video about the Quantum Diode Quantum Transistors one line : A transistor default have Source ,drain and gate ,Here source is photon wave ,drain is flux and gate is classical to quantum bits QUORA -Discussion about the Quantum Transistor YOUTUBE - Well Explained Quantum Processor one line : A nano integration circuit performing the quantum gates operation sorrounded by cooling units to reduce the tremendous amount of heat YOUTUBE - Well Explained Quantum Registery QRAM one line : Comapring the normal ram ,its ultrafast and very small in size ,the address location can be access using qubits superposition value ,for a very large memory set coherent superposition(address of address) be used PDF - very Well Explained QUANTUM COMPUTING MACHINE LEARNING BRIDGE Complex Numbers one line : Normally Waves Interference is in n dimensional structure , to find a polynomial equation n order curves ,better option is complex number YOUTUBE - Wonderful Series very super Explained Tensors one line : Vectors have a direction in 2D vector space ,If on a n dimensional vector space ,vectors direction can be specify with the tensor ,The best solution to find the superposition of a n vector electrons spin space is representing vectors as tensors and doing tensor calculus YOUTUBE - Wonderful super Explained tensors basics YOUTUBE - Quantum tensors basics Tensors Network one line : As like connecting multiple vectors ,multple tensors form a network ,solving such a network reduce the complexity of processing qubits YOUTUBE - Tensors Network Some ideas specifically for quantum algorithms QUANTUM MACHINE LEARNING ALGORITHMS Quantum K-Nearest Neighbour info : Here the centroid(euclidean distance) can be detected using the swap gates test between two states of the qubit , As KNN is regerssive loss can be tally using the average PDF1 from Microsoft - Theory Explanation PDF2 - A Good Material to understand the basics Matlab - Yet to come soon Python - Yet to come soon Quantum K-Means info : Two Approaches possible ,1. FFT and iFFT to make an oracle and calculate the means of superposition 2. Adiobtic Hamiltonian generation and solve the hamiltonian to determine the cluster PDF1 - Applying Quantum Kmeans on Images in a nice way PDF2 - Theory PDF3 - Explaining well the K-means clustering using hamiltonian Matlab - Yet to come soon Python - Yet to come soon Quantum Fuzzy C-Means info : As similar to kmeans fcm also using the oracle dialect ,but instead of means,here oracle optimization followed by a rotation gate is giving a good result PDF1 - Theory Matlab - Yet to come soon Python - Yet to come soon Quantum Support Vector Machine info : A little different from above as here kernel preparation is via classical and the whole training be in oracles and oracle will do the classification, As SVM is linear ,An optimal Error(Optimum of the Least Squares Dual Formulation) Based regression is needed to improve the performance PDF1 - Nice Explanation but little hard to understand :) PDF2 - Nice Application of QSVM Matlab - Yet to come soon Python - Yet to come soon Quantum Genetic Algorithm info : One of the best algorithm suited for Quantum Field ,Here the chromosomes act as qubit vectors ,the crossover part carrying by an evaluation and the mutation part carrying by the rotation of gates ![Flow Chart]() PDF1 - Very Beautiful Article , well explained and superp PDF2 - A big theory :) PDF3 - Super Comparison Matlab - Simulation Python1 - Simulation Python2 - Yet to come Quantum Hidden Morkov Models info : As HMM is already state based ,Here the quantum states acts as normal for the markov chain and the shift between states is using quantum operation based on probability distribution ![Flow Chart]() PDF1 - Nice idea and explanation PDF2 - Nice but a different concept little Matlab - Yet to come Python1 - Yet to come Python2 - Yet to come Quantum state classification with Bayesian methods info : Quantum Bayesian Network having the same states concept using quantum states,But here the states classification to make the training data as reusable is based on the density of the states(Interference) ![Bayesian Network Sample1]() ![Bayesian Network Sample2]() ![Bayesian Network Sample3]() PDF1 - Good Theory PDF2 - Good Explanation Matlab - Yet to come Python1 - Yet to come Python2 - Yet to come Quantum Ant Colony Optimization info : A good algorithm to process multi dimensional equations, ACO is best suited for Sales man issue , QACO is best suited for Sales man in three or more dimension, Here the quantum rotation circuit is doing the peromene update and qubits based colony communicating all around the colony in complex space ![Ant Colony Optimization 1]() PDF1 - Good Concept PDF2 - Good Application Matlab - Yet to come Python1 - Yet to come Python2 - Yet to come Quantum Cellular Automata info : One of the very complex algorithm with various types specifically used for polynomial equations and to design the optimistic gates for a problem, Here the lattice is formed using the quatum states and time calculation is based on the change of the state between two qubits ,Best suited for nano electronics ![Quantum Cellular Automata]() Wikipedia - Basic PDF1 - Just to get the keywords PDF2 - Nice Explanation and an easily understandable application Matlab - Yet to come Python1 - Yet to come Python2 - Yet to come QAUNTUM NEURAL NETWORK one line : Its really one of the hardest topic , To understand easily ,Normal Neural Network is doing parallel procss ,QNN is doing parallel of parallel processess ,In theory combination of various activation functions is possible in QNN ,In Normal NN more than one activation function reduce the performance and increase the complexity Quantum perceptrons info : Perceptron(layer) is the basic unit in Neural Network ,The quantum version of perceptron must satisfy both linear and non linear problems , Quantum Concepts is combination of linear(calculus of superposition) and nonlinear(State approximation using probability) ,To make a perceptron in quantum world ,Transformation(activation function) of non linearity to certain limit is needed ,which is carrying by phase estimation algorithm ![Quantum Perceptron 3]() PDF1 - Good Theory PDF2 - Good Explanation Matlab - Yet to come Python1 - Yet to come Python2 - Yet to come QAUNTUM STATISTICAL DATA ANALYSIS one line : An under research concept ,It can be seen in multiple ways, one best way if you want to apply n derivative for a problem in current classical theory its difficult to compute as its serialization problem instead if you do parallelization of differentiation you must estimate via probability the value in all flows ,Quantum Probability Helps to achieve this ,as the loss calculation is very less . the other way comparatively booming is Quantum Bayesianism, its a solution to solve most of the uncertainity problem in statistics to combine time and space in highly advanced physical research QUANTUM PROGRAMMING LANGUAGES , TOOLs and SOFTWARES All info : All Programming languages ,softwares and tools in alphabetical order Software - Nice content of all Python library - A python library Matlab based python library - Matlab Python Library Quantum Tensor Network Github - Tensor Network Bayesforge - A Beautiful Amazon Web Service Enabled Framework for Quantum Alogorithms and Data Analytics Rigetti - A best tools repository to use quantum computer in real time Rigetti Forest - An API to connect Quantum Computer quil/pyQuil - A quantum instruction language to use forest framework Grove - Grove is a repository to showcase quantum Fourier transform, phase estimation, the quantum approximate optimization algorithm, and others developed using Forest QISKit - A IBM Kit to access quantum computer and mainly for quantum circuits IBM Bluemix Simulator - A Bluemix Simulator for Quantum Circuits Microsoft Quantum Development Kit - Microsoft Visual Studio Enbaled Kit for Quantum Circuit Creation Microsoft "Q#" - Microsoft Q Sharp a new Programming Language for Quantum Circuit Creation qiskit api python - An API to connect IBM Quantum Computer ,With the generated token its easy to connect ,but very limited utils ,Lot of new utils will come soon Cyclops Tensor Framework - A framework to do tensor network simulations Python ToolKit for chemistry and physics Quantum Algorithm simulations - A New Started Project for simulating molecule and solids Bayesian Based Quatum Projects Repository - A nice repository and the kickstarter of bayesforge Google Fermion Products - A newly launched product specifivally for chemistry simulation Tree Tensor Networks - Interesting Tensor Network in Incubator Deep Tensor Neural Network - Some useful information about Tensor Neural Network in Incubator Generative Tensorial Networks - A startup to apply machine learning via tensor network for drug discovery Google Bristlecone - A new Quantum Processor from Google , Aimed for Future Hardwares with full fledged AI support XANADU - A Light based Quantum Hardware(chips supports) and Software Company Started in Preparation Stage. Soon will be in market fathom computing - A new concept to train the ai in a processor using light and quantum based concepts. soon products will be launch Alibaba Quantum Computing Cloud Service - Cloud Service to access 11 Bit Quantum Computing Processor Atomistic Machine Learning Project - Seems something Interesting with Deep Tensor Network for Quantum Chemistry Applications circQ and Google Works - Google Top Efforts on Tools IBM Safe Cryptography on Cloud - IBM Started and Developing a Quantm Safe Cryptography to replace all our Certificate Authority via Cloud Google Tensor Network Open Source - Google Started the Most Scientist Preferred Way To Use a Quantum Computer Circuit. Tensor Flow Which Makes Easy to Design the Network and Will Leave the Work Effect Of Gates, Processor Preparation and also going to tell the beauty of Maths Google Tensor Network Github - Github Project of Google Tensor Network Quantum Tensorflow - Yet to come soon Quantum Spark - Yet to come soon Quatum Map Reduce - Yet to come soon Quantum Database - Yet to come soon Quantum Server - Yet to come soon Quantum Data Analytics - Yet to come soon QUANTUM HOT TOPICS Deep Quantum Learning why and what is deep learning? In one line , If you know deep learning you can get a good job :) ,Even a different platform undergraduated and graduated person done a master specialization in deep learning can work in this big sector :), Practically speaking machine learning (vector mathematics) , deep learning (vector space(Graphics) mathematics) and big data are the terms created by big companies to make a trend in the market ,but in science and research there is no word such that , Now a days if you ask a junior person working in this big companies ,what is deep learning ,you will get some reply as "doing linear regression with stochastic gradient for a unsupervised data using Convolutional Neural Network :)" ,They knows the words clearly and knows how to do programming using that on a bunch of "relative data" , If you ask them about the FCM , SVM and HMM etc algorithms ,they will simply say these are olden days algorithms , deep learning replaced all :), But actually they dont know from the birth to the till level and the effectiveness of algorithms and mathematics ,How many mathematical theorems in vector, spaces , tensors etc solved to find this "hiding the complexity technology", They did not played with real non relative data like medical images, astro images , geology images etc , finding a relation and features is really complex and looping over n number of images to do pattern matching is a giant work , Now a days the items mentioned as deep learning (= multiple hidden artifical neural network) is not suitable for that why quantum deep learning or deep quantum learning? In the mid of Artificial Neural Network Research people realised at the maximum extreme only certain mathematical operations possible to do with ANN and the aim of this ANN is to achieve parallel execution of many mathematical operations , In artificial Intelligence ,the world intelligence stands for mathematics ,how effective if a probem can be solvable is based on the mathematics logic applying on the problem , more the logic will give more performance(more intelligent), This goal open the gate for quantum artificial neural network, On applying the ideas behind the deep learning to quantum mechanics environment, its possible to apply complex mathematical equations to n number of non relational data to find more features and can improve the performance Quantum Machine Learning vs Deep Learning Its fun to discuss about this , In recent days most of the employees from Product Based Companies Like google,microsoft etc using the word deep learning ,What actually Deep Learning ? and is it a new inventions ? how to learn this ? Is it replacing machine learning ? these question come to the mind of junior research scholars and mid level employees The one answer to all questions is deep learning = parallel "for" loops ,No more than that ,Its an effective way of executing multiple tasks repeatly and to reduce the computation cost, But it introduce a big cap between mathematics and computerscience , How ? All classical algorithms based on serial processing ,Its depends on the feedback of the first loop ,On applying a serial classical algorithm in multiple clusters wont give a good result ,but some light weight parallel classical algorithms(Deep learning) doing the job in multiple clusters and its not suitable for complex problems, What is the solution for then? As in the title Quantum Machine Learning ,The advantage behind is deep learning is doing the batch processing simply on the data ,but quantum machine learning designed to do batch processing as per the algorithm The product companies realised this one and they started migrating to quantum machine learning and executing the classical algorithms on quantum concept gives better result than deep learning algorithms on classical computer and the target to merge both to give very wonderful result References Quora - Good Discussion Quora - The Bridge Discussion Pdf - Nice Discussion Google - Google Research Discussion Microsoft - Microsoft plan to merge both IBM - IBM plan to merge both IBM Project - IBM Project idea MIT and Google - Solutions for all questions QUANTUM MEETUPS Meetup 1 - Quantum Physics Meetup 2 - Quantum Computing London Meetup 3 - Quantum Computing New York Meetup 4 - Quantum Computing Canada Meetup 5 - Quantum Artificial Intelligence Texas Meetup 6 - Genarl Quantum Mechanics , Mathematics New York Meetup 7 - Quantum Computing Mountain View California Meetup 8 - Statistical Analysis New York Meetup 9 - Quantum Mechanics London UK Meetup 10 - Quantum Physics Sydney Australia Meetup 11 - Quantum Physics Berkeley CA Meetup 12 - Quantum Computing London UK Meetup 13 - Quantum Mechanics Carmichael CA Meetup 14 - Maths and Science Group Portland Meetup 15 - Quantum Physics Santa Monica, CA Meetup 16 - Quantum Mechanics London Meetup 17 - Quantum Computing London Meetup 18 - Quantum Meta Physics ,Kansas City , Missouri ,US Meetup 19 - Quantum Mechanics and Physics ,Boston ,Massachusetts ,US Meetup 20 - Quantum Physics and Mechanics ,San Francisco ,California Meetup 21 - Quantum Mechanics ,Langhorne, Pennsylvania Meetup 22 - Quantum Mechanics ,Portland QUANTUM BASED DEGREES Plenty of courses around the world and many Universities Launching it day by day ,Instead of covering only Quantum ML , Covering all Quantum Related topics gives more idea in the order below Available Courses Quantum Mechanics for Science and Engineers Online Standford university - Nice Preparatory Course edx - Quantum Mechanics for Everyone NPTEL 1 - Nice Series of Courses to understand basics and backbone of quantum mechanics NPTEL 2 NPTEL 3 NPTEL 4 NPTEL 5 Class Based Course UK Bristol Australia Australian National University Europe Maxs Planks University Quantum Physics Online MIT - Super Explanation and well basics NPTEL - Nice Series of Courses to understand basics and backbone of quantum Physics Class Based Course Europe University of Copenhagen Quantum Chemistry Online NPTEL 1 - Nice Series of Courses to understand basics and backbone of quantum Chemistry NPTEL 2 - Class Based Course Europe UGent Belgium Quantum Computing Online MIT - Super Explanation and well basics edx - Nice Explanation NPTEL - Nice Series of Courses to understand basics and backbone of quantum Computing Class Based Course Canada uwaterloo Singapore National University Singapore USA Berkley China Baidu Quantum Technology Class Based Course Canada uwaterloo Singapore National University Singapore Europe Munich Russia Skoltech Quantum Information Science External Links quantwiki Online MIT - Super Explanation and well basics edx - Nice Explanation NPTEL - Nice Series of Courses to understand basics and backbone of quantum information and computing Class Based Course USA MIT Standford University Joint Center for Quantum Information and Computer Science - University of Maryland Canada Perimeter Institute Singapore National University Singapore Europe ULB Belgium IQOQI Quantum Electronics Online MIT - Wonderful Course NPTEL - Nice Series of Courses to understand basics and backbone of quantum Electronics Class Based Course USA Texas Europe Zurich ICFO Asia Tata Institute Quantum Field Theory Online Standford university - Nice Preparatory Course edx - Some QFT Concepts available Class Based Course UK Imperial Europe Vrije Quantum Computer Science Class Based Course USA Oxford Joint Center for Quantum Information and Computer Science - University of Maryland Quantum Artificial Intelligence and Machine Learning External Links Quora 1 Quora 1 Artificial Agents Research for Quantum Designs Quantum Mathematics Class Based Course USA University of Notre CONSOLIDATED Quantum Research Papers scirate - Plenty of Quantum Research Papers Available Peter Wittek - Famous Researcher for the Quantum Machine Leanrning , Published a book in this topic [Murphy Yuezhen Niu] (https://scholar.google.com/citations?user=0wJPxfkAAAAJ&hl=en) - A good researcher published some nice articles Recent Quantum Updates forum ,pages and newsletter Quantum-Tech - A Beautiful Newsletter Page Publishing Amazing Links facebook Quantum Machine Learning - Running By me . Not that much good :). You can get some ideas Linkedlin Quantum Machine Learning - A nice page running by experts. Can get plenty of ideas FOSDEM 2019 Quantum Talks - A one day talk in fosdem 2019 with more than 10 research topics,tools and ideas FOSDEM 2020 Quantum Talks - Live talk in fosdem 2020 with plenty new research topics,tools and ideas License Dedicated Opensources ![Dedicated Opensources]() Source code of plenty of Algortihms in Image Processing , Data Mining ,etc in Matlab, Python ,Java and VC++ Scripts Good Explanations of Plenty of algorithms with flow chart etc Comparison Matrix of plenty of algorithms Is Quantum Machine Learning Will Reveal the Secret Maths behind Astrology? Awesome Machine Learning and Deep Learning Mathematics is online Published Basic Presentation of the series Quantum Machine Learning Contribution If you think this page might helpful. Please help for World Education Charity or kids who wants to learn

machine-learning-blackjack-solution

machine-learning-blackjack-solution Introduction A genetic algorithm is a type of artificial intelligence programming that uses ideas from evolution to solve complex problems. It works by creating a population of (initially random) candidate solutions, then repeatedly selecting pairs of candidates and combining their solutions using a process similar to genetic crossover. Sometimes candidate solutions even go through mutation, just to introduce new possibilities into the population. After a large number of generations, the best solution found up to that point is often the optimal, best solution possible. Genetic algorithms are particularly well-suited for combinatorial problems, where there are huge numbers of potential solutions to a problem. The evolutionary process they go through is, in essence, a search through a huge solution space. A solution space so large that you simply could never use a brute force approach. This project is a demonstration of using a genetic algorithm to find an optimal strategy for playing the casino game Blackjack. Please see this article for a story about how this program was used, and what the results were. The article describes some of the available settings, and shows how different values for those settings affect the final result. The source code is for a Windows application written in Cthat allows you to play with different settings like population size, selection style and mutation rate. Each generation's best solution is displayed, so you can watch the program literally evolve a solution. !blackjack strategy tester screenshot The property grid located at the upper left of the screen is where you adjust settings. There's an informational area below that, and the right side of the screen is the display area for the three tables that represent a strategy for playing Blackjack. The tall table on the left is for hard hands, the table in the upper right is for soft hands, and the table in the lower right is for pairs. We'll talk more about how to interpret this strategy in a bit. The columns along the tops of the three tables are for the dealer upcard. When you play Blackjack the dealer has one of his two cards initially turned face up, and the rank of that card has a big impact on recommended strategy. Notice that the upcard ranks don't include Jack, Queen or King. That's because those cards all count 10, so we group them and the Ten together and simplify the tables. To use the tables, first, determine if you have a pair, soft hand, or hard hand. Then look in the appropriate table, with the correct dealer upcard column. The cell in the table will be "H" when the correct strategy is to hit, "S" when the correct strategy is to stand, "D" for double-down, and (in the pairs table only) "P" for split. A Word About This "Optimal" Strategy Before we go any further, it needs to be stated that this problem of finding an optimal Blackjack strategy has already been solved. Back in the 1960s, a mathematician named Edward O. Thorp authored a book called Beat the Dealer, which included charts showing the optimal "Basic" strategy. That strategy looks like this: !optimal blackjack strategy So we're solving a problem that has already been solved, but that's actually good. That means we can compare our results to the known best solution. For example, if our result strategy tells us to do anything but stand when holding a pair of Tens, Jacks, Queens or Kings, we know there's a problem. There's one other thing to get out of the way before we go any further, and that's the idea of nondeterministic code. That means that if we run the same code twice in a row, we're likely to get two different results. That's something that happens with genetic algorithms due to their inherent randomness. There's no guarantee you'll find the absolute optimal solution, but it is assured that you will find an optimal or near-optimal solution. It's something that isn't typical when writing code, so it takes some adjustment for most programmers. Genetic Algorithms Now let's talk about the details of a genetic algorithm. Fitness Scores First of all, we need a way to evaluate candidates so we can compare them to each other. That means a numeric fitness score, which in this case is quite simple: you simulate playing a certain number of hands using the strategy, and then count the number of chips you have at the end. The big question is, how many hands should we test with? The challenge of trying to test a strategy is that due to the innate randomness of Blackjack, you could use the same strategy ten times and get ten completely different results. Obviously, the more hands you play, the more the randomness gets smoothed out, and the quality of the underlying strategy starts to emerge. If you doubt this, just think about flipping a coin. If you only flip it five times, there's certainly a possibility that it'll come up heads all five times (in fact, that happens just over 3% of the time). However, if you flip it 500 times, there's no way it's going to end up all heads - the odds of it happening are 0.5500, which works out to be roughly once every 3 x 10150 times you try it. After some testing and analysis, it was determined that a minimum of 100,000 hands per test is needed for a reasonable level of accuracy. There's still variance even at that number, but in order to cut the variance in half, you'd need to bump the number of hands to 500,000. One reason this accuracy is important is that in the later generations, the differences between candidates are very small. Evolution has caused the main parts of the strategy to converge on a particular approach, and towards the end all it's doing is refining the minor details. In those cases it's important to accurately determine the difference between two similar candidates. Representation Representation is simply the idea that we need to use a data structure for a candidate solution that can be combined via crossover, and possibly mutated. In this case, that's also quite simple because the way that human beings represent a Blackjack strategy is to use three tables, as we've seen. Representing those in code with three two-dimensional arrays is the obvious approach. Each cell in those three tables will have "Hit", "Stand", "Double-Down", or (only for pairs) "Split". By the way, since there are 160 cells in the hard hands table, and 80 cells in the soft hands table, and 100 cells in the pairs table, we can calculate exactly how many possible distinct strategies there are for Blackjack: 4100 x 380 x 3160 = 5 x 10174 possible Blackjack strategies That's a big number, which is obviously impossible to search using brute force. Genetic algorithms (GAs) are extremely helpful when trying to find an optimal solution from a very large set of possible solutions like this. Blackjack Rules and Strategies The rules of Blackjack are fairly simple. The dealer and the player both are dealt two cards. The player sees both of their cards (they are usually dealt face up), and one of the dealer's cards is dealt face up. Each card has a value - for cards between 2 and 10, the value is the same as the card's rank (so an Eight of Spades counts as 8, for example). All face cards count as 10, and an Ace can either be 1 or 11 (it counts as 11 only when that does not result in a hand that exceeds 21). The suit of a card does not matter. After the cards are dealt, if the player has Blackjack (a total of 21) and the dealer does not, the player is immediately paid 1.5 times their original bet, and a new hand is dealt. If the player has 21 and the dealer does also, then it's a tie and the player gets their original bet back, and a new hand is dealt. If the player wasn't dealt a Blackjack, then play continues with the player deciding whether to Stand (not get any more cards), Hit (receive an additional card), Double-down (place an additional bet, and receive one and only one more card), or, in the case of holding a pair, splitting the hand, which means placing an additional bet and receiving two new cards, so the end result is that the player is now playing two (or, in the case of multiple splits, more than two) hands simultaneously. If the player hits or double-downs and has a resulting hand that exceeds 21, then they lose and play continues with the next hand. If not, then the dealer draws until their hand totals at least 17. If the dealer exceeds 21 at this point, the player receives a payment equal to twice their original bet. If the dealer doesn't exceed 21, then the hands are compared and the player with the highest total that doesn't exceed 21 wins. Because of these rules, certain effective strategies emerge. One common strategy is that if you hold a hard hand with a value of 20, 19 or 18, you should Stand, since you avoid busting by going over 21, and you have a nice hand total that might win in a showdown with the dealer. Another common strategy is to split a pair of Aces, since Aces are so powerful (due to the fact that count as 11 or 1, you can often Hit a hand with a soft Ace with no risk of busting). Likewise, splitting a pair of 8s is a good idea because with a hard total of 16, it's likely you will bust if you take a Hit (since so many cards count as 10). As a human being, all it takes is a little knowledge about the rules in order to construct a strategy. The GA program doesn't have that advantage, and operates completely without any pre-programmed knowledge of Blackjack. It simply uses the relative fitness scores and the mechanism of evolution to find the solution. GA Settings There are many variables or settings for a GA. You can adjust population size, how parent candidates are selected, how the resulting children may be mutated, and several other items. The following sections describe some of these settings: Setting: Selection Style Once we've solved representation and have a fitness function, the next step is to select two candidates for crossover during the process of building a new generation. There are three common styles for selection, and this program supports all of them. First, you can choose Roulette Wheel selection. It's named for a Roulette wheel because you can imagine each candidate's fitness score being a wedge in a pie chart, with a size proportionate to its relative fitness compared to the other candidates. (Of course, this assumes that all fitness scores are positive, which we will talk about shortly). The main benefit of Roulette Wheel selection is that selection is fitness-proportionate. Imagine if you had only three candidates, with fitness scores of 1, 3, and 8. The relative selection probabilities for those candidates will be 1/12, 3/12, and 8/12. The downside of Roulette Wheel selection is that it tends to be somewhat slow in terms of processing. The selection process is done by iterating through the candidates until a particular condition is matched - in other words, O(N) performance. Another potential problem with Roulette Wheel selection is that there may be situations where fitness scores vary widely, to such an extent that only certain candidates have any reasonable chance of being selected. This happens frequently in early generations, since the majority of candidates are mostly random. Although this might sound like a positive (since you ultimately want to select candidates with high fitness scores), it also results in a loss of genetic diversity. In other words, even though a particular candidate may have a low fitness score in an early generation, it may contain elements that are needed to find the ultimate solution in later generations. Ranked Selection is the solution to this problem. Instead of using raw fitness scores during the selection process, the candidates are sorted by fitness, with the worst candidate receiving a score of 0, the second worse receiving 1, and so forth, all the way to the best candidate, which has a score equal to the population size - 1. Ranked Selection is quite slow, since it combines the O(N) performance of Roulette Wheel, with the additional requirement that the candidates be sorted before selection. However, there may be circumstances where it performs better than other selection approaches. Finally, the fastest selection method of all is called Tournament Selection. This method simply selects N random candidates from the current generation, and then uses the one with the best fitness score. A tournament size of 2 means two random candidates are selected, and the best of those two is used. If you have a large tournament size (like 10), then 10 different candidates will be selected, with the best of those being the ultimate selection. That obviously tilts the balance between randomness and quality. Tournament selection works well in most cases, but it does require some experimentation to find the best tourney size. Setting: Elitism Elitism is a technique that helps ensure that the best candidates are always maintained. Since all selection methods are random to some degree, it is possible to completely lose the best candidates from one generation to another. By using Elitism, we automatically advance a certain percentage of the best candidates to the next generation. Elitism does have a negative impact on performance since all of the candidates must be sorted by fitness score. Typically Elitism is done before filling the rest of a new generation with new candidates created by crossover. Crossover Details Once two candidate solutions have been selected, the next step in building a new generation is to combine those two into a single new candidate, hopefully using the best of both parent strategies. There are a number of ways to do crossover, but the method used in this program is quite straightforward - the two fitness scores are compared, and crossover happens in a relatively proportionate way. If one candidate has a fitness of 10, and the other has a fitness of 5, then the one with fitness 10 contributes twice as much to the child as the parent with a fitness of 5. Since the fitness scores in this program are based on how much the strategy would win over thousands of hands, almost all fitness scores will be negative. (This is obviously because the rules are set up so the house always wins.) This makes it difficult to calculate relative fitnesses (how do you compare a positive number with a negative, and find relative proportions?), and also causes problems with selection methods like Roulette Wheel or Ranked. To solve this, we find the lowest fitness score of the generation and add that value to each candidate. This results in an adjusted fitness score of 0 for the very worse candidate, so it never gets selected. Mutation As has been mentioned a few times, maintaining genetic diversity in our population of candidate solutions is a good thing. It helps the GA ultimately find the very best solution, by occasionally altering a candidate in a positive direction. There are two settings for mutation. MutationRate controls what percentage of new candidates have mutation done on them. MutationImpact controls what percentage of their strategy is randomized. Population Size Population size has a significant impact on performance. The smaller the population size, the faster the GA will execute. On the other hand, if the size is too low the population may not have enough genetic diversity to find the ultimate solution. During testing, it looks like 700 to 1000 is a good balance between speed and correctness. Performance Notes This program consumes a lot of processing power. Running tests of hundreds of thousands of hands of Blackjack for hundreds or thousands of candidates consumes a lot of time. It's really imperative to write the code so that it works as efficiently as possible. If your CPU isn't consistently at or above 95% usage, there's still room for improvement. Multi-threading is a natural fit for genetic algorithms because we often want to perform the same action on each candidate. The best example of this is when we calculate fitness scores. This is often an operation that takes quite a bit of time. In our case, we're dealing out 100,000 hands, and each hand has to be played until the end. If we're single-threading that code, it's going to take a long time. Multi-threading is really the way to go. Luckily, there's a ridiculously simple way to efficiently use all of your processors for an operation like this. This code loops over all of the candidates in the currentGeneration list, calls the fitness function and sets the fitness property for each: Regardless of the number of items in the list or the number of processors on your machine, the code will efficiently run the code in a multi-threaded manner, and continue only when all of the threads are complete. One of the side effects of making this code multi-threaded is that all of the code relating to evaluating a candidate must be thread-safe, including any Singleton objects. When making code thread-safe, pay attention that you don't accidentally introduce code that will slow your program down unintentionally, because sometimes it can be quite subtle. Random numbers are central to how genetic algorithms work, so it's critical that they can be used correctly from a multithreaded environment. That means that each random number generator must be separate from the others, and it also means that each must produce a distinct series of random numbers. Random number generators use seed values which are usually time-based, like the number of milliseconds the computer has been turned on. Starting with that seed, subsequent calls will return a series of numbers that look random, but really aren't. If you start with the same seed, you get the same sequence. And that's a problem because if you create multiple random number generator objects in a loop using the default time-based seed, several of them will have the same time-based initial seed value, which will result in the same sequence of "random" numbers. That's a bug, because it can reduce the true randomness of the program a great deal, and that's vital to a genetic algorithm. There are a couple of ways to solve this problem. First, you can make the random object truly a singleton, and restrict access to it by using a Clock statement. The makes all access serialized for any random number need, which reduces performance. Another approach is to make the variable static per thread. By declaring the variable as static and also marking it with the [ThreadStatic] attribute, the .NET runtime allocates one static variable per thread. That eliminates the locking/serialization, but also has performance issues. The approach used in this application is to use a non-default seed value. In this case we call Guid.NewGuid().GetHashCode(), which generates a new, unique GUID, then gets an integer hashcode value that should be unique, depending on how GetHashCode is implemented. While multithreading really helps performance, there are also other things we can do to improve performance. For example, when dealing with large populations, the hundreds or thousands of objects that will be generated each generation can quickly turn into a huge problem related to garbage collection. In the end, the easiest way to solve that is to look through the code and find objects being allocate inside a loop. It's better to declare the variable outside of the loop, and then clear it in the loop, rather than reallocate it. In a program like this one where you could be looping hundreds of thousands of times, this can result in a very significant performance boost. For example, in an early version of this code, a Deck object was created for each hand. Since there are hundreds of candidate solutions running hundreds of thousands of trial hands, this was a huge inefficiency. The code was changed to allocate one deck per test sequence. The deck was shuffled as needed, so it never needs to be reallocated. Beyond the cards in the deck, another object type that was repeatedly created and destroyed were the candidate strategies. To mitigate this problem, a StrategyPool class was created that handles allocation and deallocation. This means that strategy objects are reused, rather than dynamically created when needed. The pool class has to be thread-safe, so it does serialize access to its methods via a Clock statement, but overall using the pool approach produced a good performance increase. Finally, a subtle form of object allocation is conversion. In an early version of the code, a utility card function used Convert.ToInt32(rankEnum). Obviously, the easiest way to convert from an enum to an int is simply to cast it, like (int)rankEnum. But it's hard to know exactly what the difference is between that approach, int.Parse(), int.TryParse(), or Convert.ToInt32(), since they can all be used and are roughly equivalent. Perhaps the compiler was boxing the enum value before passing it to Convert.ToInt32(), because the profiler identified this as a function that had large amounts of thread contention waiting - and the problem got much, much worse as the generations passed. By rewriting the conversion to use a simple cast, the program performance increased threefold (3x). Contributing Please read CONTRIBUTING.md for details on our code of conduct, and the process for submitting pull requests to us. Author Greg Sommerville - Initial work* License This project is licensed under the Apache 2.0 License - see the LICENSE.md file for details

bootcamp_machine-learning

Bootcamp Machine Learning One week to learn the basics in Machine Learning! :robot: Table of Contents Download Curriculum Module05 - Stepping Into Machine Learning Module06 - Univariate Linear Regression Module07 - Multivariate Linear Regression Module08 - Logistic Regression Module09 - Regularization Acknowledgements Contributors Beta-testers This project is a Machine Learning bootcamp created by 42 AI. As notions seen during this bootcamp can be complex, we very strongly advise students to have previously done the following bootcamp: Python 42 Artificial Intelligence is a student organization of the Paris campus of the school 42. Our purpose is to foster discussion, learning, and interest in the field of artificial intelligence, by organizing various activities such as lectures and workshops. Download The pdf files of each module can be downloaded from our realease page: https://github.com/42-AI/bootcampmachine-learning/releases Curriculum Module05 - Stepping Into Machine Learning Get started with some linear algebra and statistics Sum, mean, variance, standard deviation, vectors and matrices operations. Hypothesis, model, regression, loss function. Module06 - Univariate Linear Regression Implement a method to improve your model's performance: gradient descent, and discover the notion of normalization Gradient descent, linear regression, normalization. Module07 - Multivariate Linear Regression Extend the linear regression to handle more than one features, build polynomial models and detect overfitting Multivariate linear hypothesis, multivariate linear gradient descent, polynomial models. Training and test sets, overfitting. Module08 - Logistic Regression Discover your first classification algorithm: logistic regression! Logistic hypothesis, logistic gradient descent, logistic regression, multiclass classification. Accuracy, precision, recall, F1-score, confusion matrix. Module09 - Regularization Fight overfitting! Regularization, overfitting. Regularized loss function, regularized gradient descent. Regularized linear regression. Regularized logistic regression. Acknowledgements Contributors Amric Trudel (amric@42ai.fr) Maxime Choulika (maxime@42ai.fr) Pierre Peigné (ppeigne@student.42.fr) Matthieu David (mdavid@student.42.fr) Benjamin Carlier (bcarlier@student.42.fr) Pablo Clement (pclement@student.42.fr) Amir Mahla (amahla@42ai.fr) Mathieu Perez (mathieu.perez@42ai.fr) Beta-testers Richard Blanc (riblanc@student.42.fr) Solveig Gaydon Ohl (sgaydon-@student.42.fr) Quentin Feuillade--Montixi (qfeuilla@student.42.fr)

How-to-learn-Deep-Learning

Approach A practical, top-down approach, starting with high-level frameworks with a focus on Deep Learning. UPDATED VERSION: 👉 Check out my 60-page guide, No ML Degree, on how to land a machine learning job without a degree. Getting started [2 months] There are three main goals to get up to speed with deep learning: 1) Get familiar to the tools you will be working with, e.g. Python, the command line and Jupyter notebooks 2) Get used to the workflow, everything from finding the data to deploying a trained model 3) Building a deep learning mindset, an intuition for how deep learning models behave and how to improve them Spend a week on codecademy.com and learn the python syntax, command line and git. If you don't have any previous programming experience, it's good to spend a few months learning how to program. Otherwise, it's easy to become overwhelmed. Spend one to two weeks using Pandas and Scikit-learn on Kaggle problems using Jupyter Notebook on Colab, e.g. Titanic, House prices, and Iris. This gives you an overview of the machine learning mindset and workflow. Spend one month implementing models on cloud GPUs. Start with FastAI and PyTorch. The FastAI community is the go-to place for people wanting to apply deep learning and share the state of the art techniques. Once you have done this, you will know how to add value with ML. Portfolio [3 - 12 months] Think of your portfolio as evidence to a potential employer that you can provide value for them. When you are looking for your first job, there are four main roles you can apply for Machine Learning Engineering, Applied Machine Learning Researcher / Residencies, Machine Learning Research Scientist, and Software Engineering. A lot of the work related to machine learning is pure software engineering roles (category 4), e.g. scaling infrastructure, but that's out of scope for this article. It's easiest to get a foot in the door if you aim for Machine Learning Engineering roles. There are a magnitude more ML engineering roles compared to category 2 & 3 roles, they require little to no theory, and they are less competitive. Most employers prefer scaling and leveraging stable implementations, often ~1 year old, instead of allocating scarce resources to implement SOTA papers, which are often time-consuming and seldom work well in practice. Once you can cover your bills and have a few years of experience, you are in a better position to learn theory and advance to category 2 & 3 roles. This is especially true if you are self-taught, you often have an edge against an average university graduate. In general, graduates have weak practical skills and strong theory skills. Context You'll have a mix of 3 - 10 technical and non-technical people looking at your portfolio, regardless of their background, you want to spark the following reactions: the applicant has experience tackling our type of problems, the applicant's work is easy to understand and well organized, and the work was without a doubt 100% made by the applicant. Most ML learners end up with the same portfolio as everyone else. Portfolio items include things as MOOC participation, dog/cat classifiers, and implementations on toy datasets such as the titanic and iris datasets. They often indicate that you actively avoid real-world problem-solving, and prefer being in your comfort zone by copy-pasting from tutorials. These portfolio items often signal negative value instead of signaling that you are a high-quality candidate. A unique portfolio item implies that you have tackled a unique problem without a solution, and thus have to engage in the type of problem-solving an employee does daily. A good starting point is to look for portfolio ideas on active Kaggle competitions, and machine learning consulting projects, and demo versions of common production pipelines. Here's a Twitter thread on how to come up with portfolio ideas. Here are rough guidelines to self-assess the strength of your portfolio: Machine learning engineering: Even though ML engineering roles are the most strategic entry point, they are still highly competitive. In general, there are ~50 software engineering roles for every ML role. From the self-learners I know, 2/3 fail to get a foot in the door and end up taking software engineering roles instead. You are ready to look for a job when you have two high-quality projects that are well-documented, have unique datasets, and are relevant to a specific industry, say banking or insurance. Project Type | Base score | -------------| -----------| Common project | -1 p || Unique project | 10 p | Multiplier Type | Factor -----------------|----------------- Strong documentation | 5x 5000-word article | 5x Kaggle Medal | 10x Employer relevancy | 20x Hireable: 5,250 p Competative: 15,000 p Applied research / research assistant/ residencies: For most companies, the risk of pursuing cutting edge research is often too high, thus only the biggest companies tend to need this skillset. There are smaller research organizations that hire for these positions, but these positions tend to be poorly advertised and have a bias for people in their existing community. Many of these roles don't require a Ph.D., which makes them available to most people with a Bachelor's or Master's degrees, or self-learners with one year of focussed study. Given the status, scarcity, and requirements for these positions, they are the most competitive ML positions. Positions at well-known companies tend to get more than a thousand applicants per position. Daily, these roles require that you understand and can implement SOTA papers, thus that's what they will be looking for in your portfolio. Projects type | Base score --------------| ----------- Common project | -10 p Unique project | 1 p SOTA paper implementation | 20 p Multiplier type | Factor ----------------| --------------- Strong documentation | 5x 5000-word article | 5x SOTA performance | 5x Employer relevancy | 20x Hireable: 52,500 p Competitive: 150,000 p Research Scientist: Research scientist roles require a Ph.D. or equivalent experience. While the former category requires the ability to implement SOTA papers, this category requires you to come up with research ideas. The mainstream research community measure the quality of research ideas by their impact, here is a list of the venues and their impact. To have a competitive portfolio, you need two published papers in the top venues in an area that's relevant to your potential employer. Project type | Base score -------------| ---------------- Common project | -100 p An unpublished paper | 5 p ICML/ICLR/NeurIPS publication | 500p All other publications | 50 p Multiplier type | Factor ------------------| ------------------ First author paper | 10x Employer relevancy | 20x Hireable: 20,000 p Competitive roles and elite PhD positions: 200,000 p Examples: My first portfolio item (after 2 months of learning): Code | Write-up My second portfolio item (after 4 months of learning): Code | Write-up Dylan Djian's first portfolio item: Code | Write-up Dylan Djian's second portfolio item: Code | Write-up Reiichiro Nakano's first portfolio item: Code | Write-up Reiichiro Nakano's second portfolio item: Write-up Most recruiters will spend 10-20 seconds on each of your portfolio items. Unless they can understand the value in that time frame, the value of the project is close to zero. Thus, writing and documentation are key. Here's another thread on how to write about portfolio items. The last key point is relevancy. It's more fun to make a wide range of projects, but if you want to optimize for breaking into the industry, you want to do all projects in one niche, thus making your skillset super relevant for a specific pool of employers. Further Inspiration: FastAI student projects Stanford NLP student projects Stanford CNN student projects Theory 101 [4 months] Learning how to read papers is critical if you want to get into research, and a brilliant asset as an ML engineer. There are three key areas to feel comfortable reading papers: 1) Understanding the details of the most frequent algorithms, gradient descent, linear regression, and MLPs, etc 2) Learning how to translate the most frequent math notations into code 3) Learn the basics of algebra, calculus, statistics, and machine learning For the first week, spend it on 3Blue1Brown's Essence of linear algebra, the Essence of Calculus, and StatQuests' the Basics (of statistics) and Machine Learning. Use a spaced repetition app like Anki and memorize all the key concepts. Use images as much as possible, they are easier to memorize. Spend one month recoding the core concepts in python numpy, including least squares, gradient descent, linear regression, and a vanilla neural network. This will help you reduce a lot of cognitive load down the line. Learning that notations are compact logic and how to translate it into code will make you feel less anxious about the theory. I believe the best deep learning theory curriculum is the Deep Learning Book by Ian Goodfellow and Yoshua Bengio and Aaron Courville. I use it as a curriculum, and the use online courses and internet resources to learn the details about each concept. Spend three months on part 1 of the Deep learning book. Use lectures and videos to understand the concepts, Khan academy type exercises to master each concept, and Anki flashcards to remember them long-term. Key Books: Deep Learning Book by Ian Goodfellow and Yoshua Bengio and Aaron Courville. Deep Learning for Coders with fastai and PyTorch: AI Applications Without a PhD by Jeremy Howard and Sylvain. Gugger. Deep Learning with Python by François Chollet. Neural Networks and Deep Learning by Michael Nielsen. Grokking Deep Learning by Andrew W. Trask. Forums FastAI Keras Slack Distill Slack Pytorch Twitter Other good learning strategies: Emil Wallner S. Zayd Enam Catherine Olsson Greg Brockman V2 Greg Brockman V1 Andrew Ng Amid Fish Spinning Up by OpenAI Confession as an AI researcher YC Threads: One and Two If you have suggestions/questions create an issue or ping me on Twitter. UPDATED VERSION: 👉 Check out my 60-page guide, No ML Degree, on how to land a machine learning job without a degree. Language versions: Korean | English

Practical-Deep-Learning-For-Coders

Practical Deep Learning for Coders Material for my Proctor of Fast.AI's course. This course is originally done by Jeremy Howard and Rachel Thomas, and is taught at the University by course alumni. The course can be found here: https://course.fast.ai The Fast.AI forums can be found at: https://forums.fast.ai

Stop Learning Excel—Meet the AI Spreadsheet

Mastering Excel used to mean memorizing complex formulas like VLOOKUP, creating pivot tables, and manually sorting data. But now, AI spreadsheets are here to change the game! In this video, I showcase 7 ways AI makes spreadsheets effortless, even for beginners. With Bricks, an AI-powered and free spreadsheet tool, I’ll demonstrate how you can: Automate table joins without formulas Sort data with simple prompts Apply conditional formatting in seconds Filter data dynamically Summarize or group data effortlessly Create charts automatically Remove duplicates with ease Whether you're a spreadsheet pro or just getting started, this video will show you how AI can handle all the hard work for you. I’ve even included a sample Excel workbook so you can follow along and try these features for yourself. Are you ready to embrace the future of spreadsheets? Watch now and see why it might be time to stop learning Excel and start using AI! Host: Kevin Stratvert 📚 RESOURCES Download the sample workbook: https://1drv.ms/x/s!AmxrofZZlZ-whfhLV1BgrO5mxYgTsg?e=nEousp Sign up for Bricks: https://bit.ly/newaispreadsheet ⌚ TIMESTAMPS 00:00 - Introduction 00:28 - Get Bricks 01:02 - Effortless Table Joins with AI 02:54 - Simplified Sorting with AI 03:58 - Conditional Formatting with AI 05:03 - Filtering Made Smarter with AI 06:20 - AI Pivot Tables for Instant Insights 07:09 - AI Charts 07:59 - Removing Duplicates with AI 09:14 - Bonus: Data Types 11:51 - Export to Excel 12:12 - Wrap Up 📺 RELATED VIDEOS Playlist with all my videos on Bricks: https://www.youtube.com/playlist?list=PLlKpQrBME6xLZLJCmqdM4i5GQhXscRvTS 📩 NEWSLETTER Get the latest high-quality tutorial and tips and tricks videos emailed to your inbox each week: https://kevinstratvert.com/newsletter/ 🔽 CONNECT WITH ME Official website: http://www.kevinstratvert.com LinkedIn: https://www.linkedin.com/in/kevinstratvert/ Discord: https://bit.ly/KevinStratvertDiscord Twitter: https://twitter.com/kevstrat Facebook: https://www.facebook.com/Kevin-Stratvert-101912218227818 TikTok: https://www.tiktok.com/@kevinstratvert Instagram: https://www.instagram.com/kevinstratvert/ 🎁 TOOLS AND DISCOUNTS ✅ 🎙️ Voicemod AI Voice Changer | 5% off | https://link.xsolla.com/KZBi89AY ✅ 🌐 Squarespace Websites | https://squarespace.syuh.net/XYaqYM ✅ 🔍 Grammarly | https://grammarly.go2cloud.org/SH3nL ✅ 📹 CapCut | https://bit.ly/installcapcut ✅ 🛍️ Shopify | https://shopify.pxf.io/XY9rPa ✅ 📋 Notion | https://affiliate.notion.so/rffva4tr71ax ✅ 🖼️ Figma | https://psxid.figma.com/lqjg97licpry ✅ 🤖 ElevenLabs Text-to-Speech | https://try.elevenlabs.io/taqepq60mptr ✅ 💵 Quickbooks Online | https://bit.ly/intuitquickbooksonline ✅ 👥 Hubspot | https://hubspot.sjv.io/DKo6jb ✅ 📈 Semrush | https://bit.ly/semrush14dayfreetrial ✅ 🎥 Descript | https://get.descript.com/sf22jb63w2tx ✅ 🏓 Smartsheet | https://bit.ly/trysmartsheet 🎒 MY COURSES Go from Excel novice to data analysis ninja in just 2 hours: https://kevinstratvert.thinkific.com/ 🙏 REQUEST VIDEOS https://forms.gle/BDrTNUoxheEoMLGt5 🔔 SUBSCRIBE ON YOUTUBE https://www.youtube.com/user/kevlers?sub_confirmation=1 🙌 SUPPORT THE CHANNEL Hit the THANKS button in any video! Amazon affiliate link: https://amzn.to/3kCP2yz ⚖ DISCLOSURE Some links are affiliate links. Purchasing through these links gives me a small commission to support videos on this channel. The price to you is the same. #stratvert #bricks

ai-learning-roadmap

Lists of all AI related learning materials and practical tools to get started with AI apps Design Thinking – An Introduction Stanford's virtual Crash Course in Design Thinking Amazon Web Services Learning Material AWS AI Session– The session provides an overview of all Amazon AI technology offerings (Lex, Polly, Rekognition, ML, and Deep Learning AMI) Self-Paced Labs AWS self-paced labs provide hands-on practice in a live AWS environment with AWS services and real-world cloud scenarios. Follow step-by-step instructions to learn a service, practice a use case, or prepare for AWS Certification. Introductory Lab Introduction to AWS Lambda Lex Introduction to Amazon Lex Amazon Lex Webinar Amazon Lex: AWS conversational interface (chat bot) Documentation Polly Introduction to Amazon Polly Amazon Polly Webinar - Amazon Polly – AWS Text To Speech (TTS) service Documentation What is Amazon Polly? Developer Resources Rekognition Introduction to Amazon Rekognition Amazon Rekognition - Deep Learning-Based Image Analysis Webinar Amazon Rekognition – AWS image recognition service Documentation – What is Amazon Rekognition? Machine Learning Machine Learning Session 1 – Empowering Developers to Build Smart Applications Session 2 - Predicting Customer Churn with Amazon Machine Learning AWS Machine Learning – End to end, managed service for creating and testing ML models and then deploying those models into production Documentation What is Amazon Machine Learning? Developer Resources AWS Deep Learning AMI – Amazon Machine Image (AMI) optimized for deep learning efforts Recommended Additional Resources Take your skills to the next level with fundamental, advanced, and expert level labs. Creating Amazon EC2 Instances with Microsoft Windows Building Your First Amazon Virtual Private Cloud (VPC) Working with AWS CodeCommit on Windows Working with Amazon DynamoDB Google Cloud - Learning Material Below is the learning material that will help you learn about Google Cloud. Network Networking 101 – 43 mins The codelab provides common cloud developer experience as follows: Set up your lab environment and learn how to work with your GCP environment. Use of common open source tools to explore your network around the world. Deploy a common use case: use of HTTP Load Balancing and Managed Instance Groups to host a scalable, multi-region web server. Testing and monitoring your network and instances. Cleanup. Developing Solutions for Google Cloud Platform – 8 hours Infrastructure Build a Slack Bot with Node.js on Kubernotes – 43 mins Creating a Virtual Machine – 10 mins Getting Started with App Engine (Python) – 13 mins Data Introduction to Google Cloud Data Prep – 7 mins Create a Managed MySQL database with Cloud SQL – 19 mins Upload Objects to Cloud Storage – 11 mins AI, Big Data & Machine Learning Introduction to Google Cloud Machine Learning – 1 hour Machine Learning APIs by Example – 30 min Google Cloud Platform Big Data and Machine Learning Fundamentals Additional AI Materials Auto-awesome: Advanced Data Science on Google Cloud Platform – 45 min Run a Big Data Text Processing Pipeline in Cloud Dataflow – 21 min Image Classification Using Cloud ML Engine & Datalab – 58 min Structured Data Regression Using Cloud ML Engine & Datalab – 58 min (Optional) Deep Learning & Tensorflow Tensorflow and Deep Learning Tutorial – 2:35 hours Deep Learning Course – advanced users only Additional Reference Material Big Data & Machine Learning @ Google Cloud Next '17 - A collection of 49 videos IBM Watson Learning Material (Contributions are welcome in this space) [IBM Watson Overview]() [IBM Watson Cognitive APIs]() [IBM Watson Knowledge Studio]() Visual Studio UCI datasets Microsoft Chat Bots Learning Material Skills Prerequisite Git and Github NodeJS VS Code IDE Training Paths If you have the above Prerequisite skills, then take Advanced Training Path else take Novice Training Path. Prerequisite Tutorials Git and Github Node.js Node.js Tutorials for Beginners Node.js Tutorial in VS Code Introduction To Visual Studio Code Novice Training Path Environment Set Up Download and Install Git Set up GitHub Account_ Download and Install NodeJS Download and Install IDE - Visual Studio Code Download and Install the Bot Framework Emulator Git clone the Bot Education project - git clone Set Up Azure Free Trial Account Cognitive Services (Defining Intelligence) Read Cognitive Services ADS Education Deck – git clone Review the guide for Understanding Natural language with LUIS Complete the NLP (LUIS) Training Lab from the installed Bot Education project – \bot-education\Student-Resources\Labs\CognitiveServices\Lab_SetupLanguageModel.md Bot Framework (Building Chat Bots) Read Bot Framework ADS Education Deck from downloaded - (Your Path)\bot-extras Review Bot Framework documentation (Core Concepts, Bot Builder for NodeJS, and Bot Intelligence) - Setup local environment and run emulator from the installed Bot Education project – \bot-education\Student-Resources\Labs\Node\Lab1_SetupCheckModel.md Review and test in the emulator the “bot-hello” from \bot-education\Student-Resources\BOTs\Node\bot-hello Advanced Training Path Environment Set Up Download and Install Git Set up GitHub Account_ Download and Install NodeJS Download and Install IDE - Visual Studio Code Download and Install the Bot Framework Emulator Git clone the Bot Education project - git clone Set Up Azure Free Trial Account Git clone the Bot Builder Samples – git clone Cognitive Services (Defining Intelligence) Read Cognitive Services ADS Education Deck – git clone Review the guide for Understanding Natural language with LUIS Bot Framework (Building Chat Bots) Read Bot Framework ADS Education Deck from downloaded - (Your Path)\bot-extras Review Bot Framework documentation (Core Concepts, Bot Builder for NodeJS, and Bot Intelligence) - Setup local environment and run emulator from the installed Bot Education project – \bot-education\Student-Resources\Labs\Node\Lab1_SetupCheckModel.md Cognitive Services (Defining Intelligence) - Labs Complete the NLP (LUIS) Training Lab from the installed BOT Education project \bot-education\Student-Resources\Labs\CognitiveServices\Lab_SetupLanguageModel.md Review, Deploy and run the LUIS BOT sample Bot Framework (Building Chat Bots) – Labs Setup local environment and run emulator from the installed Bot Education project \bot-education\Student-Resources\Labs\Node\Lab1_SetupCheckModel.md Review and test in the emulator the “bot-hello” from \bot-education\Student-Resources\BOTs\Node\bot-hello Review and test in the emulator the “bot-recognizers” from \bot-education\Student-Resources\BOTs\Node\bot-recognizers Lecture Videos Source Berkeley Lecture TitleLecturerSemester Lecture 1 Introduction Dan Klein Fall 2012 Lecture 2 Uninformed Search Dan Klein Fall 2012 Lecture 3 Informed Search Dan Klein Fall 2012 Lecture 4 Constraint Satisfaction Problems I Dan Klein Fall 2012 Lecture 5 Constraint Satisfaction Problems II Dan Klein Fall 2012 Lecture 6 Adversarial Search Dan Klein Fall 2012 Lecture 7 Expectimax and Utilities Dan Klein Fall 2012 Lecture 8 Markov Decision Processes I Dan Klein Fall 2012 Lecture 9 Markov Decision Processes II Dan Klein Fall 2012 Lecture 10 Reinforcement Learning I Dan Klein Fall 2012 Lecture 11 Reinforcement Learning II Dan Klein Fall 2012 Lecture 12 Probability Pieter Abbeel Spring 2014 Lecture 13 Markov Models Pieter Abbeel Spring 2014 Lecture 14 Hidden Markov Models Dan Klein Fall 2013 Lecture 15 Applications of HMMs / Speech Pieter Abbeel Spring 2014 Lecture 16 Bayes' Nets: Representation Pieter Abbeel Spring 2014 Lecture 17 Bayes' Nets: Independence Pieter Abbeel Spring 2014 Lecture 18 Bayes' Nets: Inference Pieter Abbeel Spring 2014 Lecture 19 Bayes' Nets: Sampling Pieter Abbeel Fall 2013 Lecture 20 Decision Diagrams / Value of Perfect Information Pieter Abbeel Spring 2014 Lecture 21 Machine Learning: Naive Bayes Nicholas Hay Spring 2014 Lecture 22 Machine Learning: Perceptrons Pieter Abbeel Spring 2014 Lecture 23 Machine Learning: Kernels and Clustering Pieter Abbeel Spring 2014 Lecture 24 Advanced Applications: NLP, Games, and Robotic Cars Pieter Abbeel Spring 2014 Lecture 25 Advanced Applications: Computer Vision and Robotics Pieter Abbeel Spring 2014 Additionally, there are additional Step-By-Step videos which supplement the lecture's materials. These videos are listed below: Lecture TitleLecturerNotes SBS-1 DFS and BFS Pieter Abbeel Lec: Uninformed Search SBS-2 A* Search Pieter Abbeel Lec: Informed Search SBS-3 Alpha-Beta Pruning Pieter Abbeel Lec: Adversarial Search SBS-4 D-Separation Pieter Abbeel Lec: Bayes' Nets: Independence SBS-5 Elimination of One Variable Pieter Abbeel Lec: Bayes' Nets: Inference SBS-6 Variable Elimination Pieter Abbeel Lec: Bayes' Nets: Inference SBS-7 Sampling Pieter Abbeel Lec: Bayes' Nets: Sampling SBS-8 Gibbs' Sampling Michael Liang Lec: Bayes' Nets: Sampling --> SBS-8 Maximum Likelihood Pieter Abbeel Lec: Machine Learning: Naive Bayes SBS-9 Laplace Smoothing Pieter Abbeel Lec: Machine Learning: Naive Bayes SBS-10 Perceptrons Pieter Abbeel Lec: Machine Learning: Perceptrons Per-Semester Video Archive(Berkeley) The lecture videos from the most recent offerings are posted below. Spring 2014 Lecture Videos Fall 2013 Lecture Videos Spring 2013 Lecture Videos Fall 2012 Lecture Videos Spring 2014 Lecture TitleLecturerNotes Lecture 1 Introduction Pieter Abbeel Lecture 2 Uninformed Search Pieter Abbeel Lecture 3 Informed Search Pieter Abbeel Lecture 4 Constraint Satisfaction Problems I Pieter Abbeel Recording is a bit flaky, see Fall 2013 Lecture 4 for alternative Lecture 5 Constraint Satisfaction Problems II Pieter Abbeel Lecture 6 Adversarial Search Pieter Abbeel Lecture 7 Expectimax and Utilities Pieter Abbeel Lecture 8 Markov Decision Processes I Pieter Abbeel Lecture 9 Markov Decision Processes II Pieter Abbeel Lecture 10 Reinforcement Learning I Pieter Abbeel Lecture 11 Reinforcement Learning II Pieter Abbeel Lecture 12 Probability Pieter Abbeel Lecture 13 Markov Models Pieter Abbeel Lecture 14 Hidden Markov Models Pieter Abbeel Recording is a bit flaky, see Fall 2013 Lecture 18 for alternative Lecture 15 Applications of HMMs / Speech Pieter Abbeel Lecture 16 Bayes' Nets: Representation Pieter Abbeel Lecture 17 Bayes' Nets: Independence Pieter Abbeel Lecture 18 Bayes' Nets: Inference Pieter Abbeel Lecture 19 Bayes' Nets: Sampling Pieter Abbeel Unrecorded, see Fall 2013 Lecture 16 Lecture 20 Decision Diagrams / Value of Perfect Information Pieter Abbeel Lecture 21 Machine Learning: Naive Bayes Nicholas Hay Lecture 22 Machine Learning: Perceptrons Pieter Abbeel Lecture 23 Machine Learning: Kernels and Clustering Pieter Abbeel Lecture 24 Advanced Applications: NLP, Games, and Robotic Cars Pieter Abbeel Lecture 25 Advanced Applications: Computer Vision and Robotics Pieter Abbeel Lecture 26 Conclusion Pieter Abbeel Unrecorded Fall 2013 Lecture TitleLecturerNotes Lecture 1 Introduction Dan Klein Lecture 2 Uninformed Search Dan Klein Lecture 3 Informed Search Dan Klein Lecture 4 Constraint Satisfaction Problems I Dan Klein Lecture 5 Constraint Satisfaction Problems II Dan Klein Lecture 6 Adversarial Search Dan Klein Lecture 7 Expectimax and Utilities Dan Klein Lecture 8 Markov Decision Processes I Dan Klein Lecture 9 Markov Decision Processes II Dan Klein Lecture 10 Reinforcement Learning I Dan Klein Lecture 11 Reinforcement Learning II Dan Klein Lecture 12 Probability Pieter Abbeel Lecture 13 Bayes' Nets: Representation Pieter Abbeel Lecture 14 Bayes' Nets: Independence Dan Klein Lecture 15 Bayes' Nets: Inference Pieter Abbeel Lecture 16 Bayes' Nets: Sampling Pieter Abbeel Lecture 17 Decision Diagrams / Value of Perfect Information Pieter Abbeel Lecture 18 Hidden Markov Models Dan Klein Lecture 19 Applications of HMMs / Speech Dan Klein Lecture 20 Machine Learning: Naive Bayes Dan Klein Lecture 21 Machine Learning: Perceptrons Dan Klein Lecture 22 Machine Learning: Kernels and Clustering Pieter Abbeel Lecture 23 Machine Learning: Decision Trees and Neural Nets Pieter Abbeel Lecture 24 Advanced Applications: NLP and Robotic Cars Dan Klein Unrecorded, see Spring 2013 Lecture 24 Lecture 25 Advanced Applications: Computer Vision and Robotics Pieter Abbeel Lecture 26 Conclusion Dan Klein,Pieter Abbeel Unrecorded Spring 2013 Lecture TitleLecturerNotes Lecture 1 Introduction Pieter Abbeel Video Down Lecture 2 Uninformed Search Pieter Abbeel Lecture 3 Informed Search Pieter Abbeel Lecture 4 Constraint Satisfaction Problems I Pieter Abbeel Lecture 5 Constraint Satisfaction Problems II Pieter Abbeel Unrecorded, see Fall 2012 Lecture 5 Lecture 6 Adversarial Search Pieter Abbeel Lecture 7 Expectimax and Utilities Pieter Abbeel Lecture 8 Markov Decision Processes I Pieter Abbeel Lecture 9 Markov Decision Processes II Pieter Abbeel Lecture 10 Reinforcement Learning I Pieter Abbeel Lecture 11 Reinforcement Learning II Pieter Abbeel Lecture 12 Probability Pieter Abbeel Lecture 13 Bayes' Nets: Representation Pieter Abbeel Lecture 14 Bayes' Nets: Independence Pieter Abbeel Lecture 15 Bayes' Nets: Inference Pieter Abbeel Lecture 16 Bayes' Nets: Sampling Pieter Abbeel Lecture 17 Decision Diagrams / Value of Perfect Information Pieter Abbeel Lecture 18 Hidden Markov Models Pieter Abbeel Lecture 19 Applications of HMMs / Speech Pieter Abbeel Lecture 20 Machine Learning: Naive Bayes Pieter Abbeel Lecture 21 Machine Learning: Perceptrons I Nicholas Hay Lecture 22 Machine Learning: Perceptrons II Pieter Abbeel Lecture 23 Machine Learning: Kernels and Clustering Pieter Abbeel Lecture 24 Advanced Applications: NLP and Robotic Cars Pieter Abbeel Lecture 25 Advanced Applications: Computer Vision and Robotics Pieter Abbeel Lecture 26 Conclusion Pieter Abbeel Unrecorded Fall 2012 Lecture TitleLecturerNotes Lecture 1 Introduction Dan Klein Lecture 2 Uninformed Search Dan Klein Lecture 3 Informed Search Dan Klein Lecture 4 Constraint Satisfaction Problems I Dan Klein Lecture 5 Constraint Satisfaction Problems II Dan Klein Lecture 6 Adversarial Search Dan Klein Lecture 7 Expectimax and Utilities Dan Klein Lecture 8 Markov Decision Processes I Dan Klein Lecture 9 Markov Decision Processes II Dan Klein Lecture 10 Reinforcement Learning I Dan Klein Lecture 11 Reinforcement Learning II Dan Klein Lecture 12 Probability Pieter Abbeel Lecture 13 Bayes' Nets: Representation Pieter Abbeel Lecture 14 Bayes' Nets: Independence Pieter Abbeel Lecture 15 Bayes' Nets: Inference Pieter Abbeel Lecture 16 Bayes' Nets: Sampling Pieter Abbeel Lecture 17 Decision Diagrams / Value of Perfect Information Pieter Abbeel Lecture 18 Hidden Markov Models Pieter Abbeel Lecture 19 Applications of HMMs / Speech Dan Klein Lecture 20 Machine Learning: Naive Bayes Dan Klein Lecture 21 Machine Learning: Perceptrons Dan Klein Lecture 22 Machine Learning: Kernels and Clustering Dan Klein Lecture 23 Machine Learning: Decision Trees and Neural Nets Pieter Abbeel Lecture 24 Advanced Applications: Computer Vision and Robotics Pieter Abbeel Lecture 25 Advanced Applications: NLP and Robotic Cars Dan Klein,Pieter Abbeel Unrecorded Lecture 26 Conclusion Dan Klein,Pieter Abbeel Unrecorded Lecture Slides Here is the complete set of lecture slides, including videos, and videos of demos run in lecture: Slides [~3 GB]. The list below contains all the lecture powerpoint slides: Lecture 1: Introduction Lecture 2: Uninformed Search Lecture 3: Informed Search Lecture 4: CSPs I Lecture 5: CSPs II Lecture 6: Adversarial Search Lecture 7: Expectimax Search and Utilities Lecture 8: MDPs I Lecture 9: MDPs II Lecture 10: Reinforcement Learning I Lecture 11: Reinforcement Learning II Lecture 12: Probability Lecture 13: Markov Models Lecture 14: Hidden Markov Models Lecture 15: Particle Filters and Applications of HMMs Lecture 16: Bayes Nets I: Representation Lecture 17: Bayes Nets II: Independence Lecture 18: Bayes Nets III: Inference Lecture 19: Bayes Nets IV: Sampling Lecture 20: Decision Diagrams and VPI Lecture 21: Naive Bayes Lecture 22: Perceptron Lecture 23: Kernels and Clustering Lecture 24: Advanced Applications (NLP, Games, Cars) Lecture 25: Advanced Applications (Computer Vision and Robotics) Lecture 26: Conclusion The source files for all live in-lecture demos are being prepared from Berkeley AI for release Selected Research Papers Latest arxiv paper submissionson AI Peter Norvig-Teach Yourself Programming in Ten Years How to do Research At the MIT AI Lab A Roadmap towards Machine Intelligence Collaborative Filtering with Recurrent Neural Networks (2016) Wide & Deep Learning for Recommender Systems (2016) Deep Collaborative Filtering via Marginalized Denoising Auto-encoder (2015) Nonparametric bayesian multitask collaborative filtering (2013) Tensorflow: Large-scale machine learning on heterogeneous distributed systems https://infoscience.epfl.ch/record/82802/files/rr02-46.pdf Theano: A CPU and GPU math expression compiler. Caffe: Convolutional architecture for fast feature embedding Chainer: A powerful, flexible and intuitive framework of neural networks Large Scale Distributed Deep Networks Large-scale video classification with convolutional neural networks Efficient Estimation of Word Representations in Vector Space Grammar as a Foreign Language Going Deeper with Convolutions ON RECTIFIED LINEAR UNITS FOR SPEECH PROCESSING Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups. Multi-digit Number Recognition from Street View Imagery using Deep Convolutional Neural Networks google turning its lucrative web search over to AI machines Stanford Syllabus CS 20SI: Tensorflow for Deep Learning Research Crowd-Based Personalized Natural Language Explanations for Recommendations Comparative Study of Deep Learning Software Frameworks RedditML- What Are You Reading AI-Powered Social Bots(16 Jun 2017) The Many Tribes of Artificial Intelligence Source:https://medium.com/intuitionmachine/infographic-best-practices-in-training-deep-learning-networks-b8a3df1db53 The Deep Learning Roadmap Source:https://medium.com/intuitionmachine/the-deep-learning-roadmap-f0b4cac7009a Best Practices for Training Deep Learning Networks Source: https://medium.com/intuitionmachine/infographic-best-practices-in-training-deep-learning-networks-b8a3df1db53 ML/DL Cheatsheets Neural Network Architectures Source: http://www.asimovinstitute.org/neural-network-zoo/ Microsoft Azure Algorithm Flowchart Source: https://docs.microsoft.com/en-us/azure/machine-learning/machine-learning-algorithm-cheat-sheet SAS Algorithm Flowchart Source: http://blogs.sas.com/content/subconsciousmusings/2017/04/12/machine-learning-algorithm-use/ Algorithm Summary Source: http://machinelearningmastery.com/a-tour-of-machine-learning-algorithms/ Source: http://thinkbigdata.in/best-known-machine-learning-algorithms-infographic/ Algorithm Pro/Con Source: https://blog.dataiku.com/machine-learning-explained-algorithms-are-your-friend Python Algorithms Source: https://www.analyticsvidhya.com/blog/2015/09/full-cheatsheet-machine-learning-algorithms/ Python Basics Source: http://datasciencefree.com/python.pdf Source: https://www.datacamp.com/community/tutorials/python-data-science-cheat-sheet-basics#gs.0x1rxEA Numpy Source: https://www.dataquest.io/blog/numpy-cheat-sheet/ Source: http://datasciencefree.com/numpy.pdf Source: https://www.datacamp.com/community/blog/python-numpy-cheat-sheet#gs.Nw3V6CE Source: https://github.com/donnemartin/data-science-ipython-notebooks/blob/master/numpy/numpy.ipynb Pandas Source: http://datasciencefree.com/pandas.pdf Source: https://www.datacamp.com/community/blog/python-pandas-cheat-sheet#gs.S4P4T=U Source: https://github.com/donnemartin/data-science-ipython-notebooks/blob/master/pandas/pandas.ipynb Matplotlib Source: https://www.datacamp.com/community/blog/python-matplotlib-cheat-sheet Source: https://github.com/donnemartin/data-science-ipython-notebooks/blob/master/matplotlib/matplotlib.ipynb Scikit Learn Source: https://www.datacamp.com/community/blog/scikit-learn-cheat-sheet#gs.fZ2A1Jk Source: http://peekaboo-vision.blogspot.de/2013/01/machine-learning-cheat-sheet-for-scikit.html Source: https://github.com/rcompton/mlcheatsheet/blob/master/supervised_learning.ipynb Tensorflow Source: https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/1Introduction/basicoperations.ipynb Pytorch Source: https://github.com/bfortuner/pytorch-cheatsheet Math Probability Source: http://www.wzchen.com/s/probability_cheatsheet.pdf Linear Algebra Source: https://minireference.com/static/tutorials/linearalgebrain4pages.pdf Statistics Source: http://web.mit.edu/~csvoss/Public/usabo/stats_handout.pdf Calculus Source: http://tutorial.math.lamar.edu/getfile.aspx?file=B,41,N

Practical Machine Learning on H2O

Technical founders - is "bulling" your way through learning right for a startup? [I will not promote]

Sup, This is a question for technical founders. \--a little backstory-- I am starting a company in AI field that creates something nobody has ever done before. 7 months in. \--- How most software companies are created - you have an improvement idea, then you have a thousand or so problems to solve to make that improvement happen, and for each one that you don't know, you go to Stackoverflow or ChatGPT to look for solutions for that problem. Which involves next-to-no upfront preparation because for vast majority of traditional software you can solve it on-the-go - "traditional" software is very easy compared to, say, mechanical, pharma or AI engineering. However, for more advanced disciplines - can you just "Google" it on-the-go? I'm a solo founder, and 8 months in, creating a foundational model, BECAUSE I did not know things upfront, I've wasted at least 3 months doing something which was mostly technically unviable in the first place. Out of 14000 lines of code that I've done (including tests), I had to scrap 10000 recently. Imagine the scale of it. Obviously I didn't even know how ML works when I've started. Major fuck-up. How do you operate in industries which you've done before? How do you determine that it's time to start creating you big technological leaps instead of continuing to learn? Cheers. Edit: No need to push me on business topics. I know how to create value very well. It's only a tech question, and I'm only asking because - well - to deliver my value, I need to do a lot of novel tech.

Implementation of AI and Machine Learning In The Healthcare Industry

Using AI in medical diagnostics can assist physicians in enhancing medical therapies in a variety of ways. Physical burnout because of overwork is a severe problem that many medical professionals experience these days. It reduces medical practitioners’ overall performance, which leads to an increase in diagnostic inaccuracy. The most recent Medscape National Physician Burnout and Suicide Report 2020 data highlighted the risks of putting too much pressure on physicians, particularly those juggling families, retirement plans, and the intricacies of their employment. What is your thought on implementing AI/ML in the medical sector? Do you believe it's a threat to the medical workers? Source article: Artificial Intelligence (AI) and its Assistance in Medical Diagnosis

Advice Needed: How to Choose a Research Paper to Implement for Learning AI

Hi everyone, I'm currently diving into AI and planning to implement a research paper to strengthen my understanding and gain hands-on experience. However, I'm a bit overwhelmed by the vast number of papers out there and unsure how to pick the right one, I have some coding experience, but I’m still growing in terms of implementing more complex algorithms Any resources, personal experiences, or advice would be greatly appreciated!

Human in the loop workflows for deep learning solutions - OCR review and moderation

there's a lot of paranoia these days about how adverse automation's effects might be on society. there's some tasks that can definitely be automated and will cause certain segments of the workforce their jobs. but alongside, other opportunities will get created that didn't exist before. this article discusses how businesses are transforming, about digital information, automation, the future of work and human in the loop workflows as a possible solution to these concerns. https://i.redd.it/g2cm3eco98y31.gif

[D] What kind of reinforcement learning algorithm would you recommend for training AI for a strategy game like Risk or Axis&Allies?

The challenge being multiple stages of the game (buy, move/attack, place...) and dice rolls.

[D] resources for avoiding common mistakes in machine learning projects?

There are often managers or entrepreneur types that think of "AI" as a magical solution and then millions of dollars get wasted because they don't understand how fragile the solutions can be, how do much more data is needed to create solutions that generalize, susceptibility to bias, training data needed, etc. What accessible information is there that would help those people understand what is involved for practicality of project and successful and ethical outcomes?

Steep Learning : How I Mapped approximately 10K AI tools to 15K Replaceable Tasks across 4K professions

Hello Everyone , I would like to share some knowledge today which I went towards countless hours to do . I founded a portal called Seekme.ai, a comprehensive platform that houses over 10,000 AI tools and resources. Today, I'm excited to share with you an insightful and enlightening journey of how I mapped these tools to 15,000 tasks across 4,000 professions. This process, which I've named "Learn by Doing," got me the power of determination, collaboration, and adaptability. The Idea: It all started when I recognized the need for a more efficient and accessible way for professionals to understand which AI tools could help them automate their tasks. The traditional approach of manually researching and testing each AI tool for every profession was time-consuming and inefficient. I envisioned a solution that could streamline this process, making AI adoption easier and more accessible for a broader audience. The Planning: To begin, we needed a clear understanding of the task landscape across various professions. With the help of some Reddit communities , we embarked on an extensive study of common tasks in various industries. We utilized various sources, including government reports, industry surveys, and academic research, to create a comprehensive list of tasks. The result was an impressive list of 15,000 tasks. The Mapping: With the list of tasks in hand, the next step was to identify which AI tools could perform these tasks. I meticulously researched and analyzed each AI tool's capabilities and features. We cross-referenced this information with the tasks I had identified and created a mapping between the two. The process involved a significant amount of collaboration and refinement, as we continually updated and expanded our database of AI tools and tasks. The Challenges: The mapping process was not without its challenges. One of the primary obstacles was ensuring the accuracy and completeness of our data. To address this issue, I implemented a rigorous quality control process that included multiple rounds of checks and validations.I also established partnerships with industry experts and AI vendors to ensure our data was up-to-date and accurate. There is also a challenge that I faced was what is the quality of the tools which is the problem and how do I rank multiple tools if they do the same tasks without user feedback The Results: After months of hard work and dedication, I successfully mapped 10,000 AI tools to 15,000 tasks across 4,000 professions. Our new feature, AI by Profession, was born. This innovative will allow users to quickly and easily identify the AI tools that can automate tasks in their profession, making AI adoption more accessible and efficient than ever before. The Impact: The impact of this project has been significant. By making it easier for professionals to identify AI tools that can automate tasks in their industry, we're helping to drive productivity, efficiency, and innovation. Our users are saving time and resources by not having to manually research and test AI tools. Furthermore, we're contributing to the broader goal of democratizing AI and making it accessible to a broader audience. But there is a still an issue we face of ranking tools who does the similar job. For instance for content creation there 10 tools that can do same video editing so how do we rank it . We are planning to add categories to this to make it more exhaustive Conclusion: The journey to mapping 10,000 AI tools for 15,000 tasks across 4,000 professions was a challenging and rewarding experience. It required a significant amount of planning, determination, and collaboration, but the end result was a powerful tool that's making a difference in the lives of professionals around the world. I don’t know yet how useful it is yet for users So I am inviting you all to see if this feature can help you better equip yourself on the new wave and do things better. I am always up for a chat on anything AI and provide my help if needed. Looking forward to some feedback aswell

Validating my business idea: AI test generator for interactive learning

Of course, I ran some validations before studying to build the product, but it's one thing to offer an idea that could potentially be perfect and another - an actual product with realistic constraints. Here's the tool: my.testudy.io Target audience: students mainly, but also could be parents, teachers, and generally people who study Any suggestions and feedback are much appreciated.

Steep Learning : How I Mapped approximately 10K AI tools to 15K Replaceable Tasks across 4K professions

Hello Everyone , I would like to share some knowledge today which I went towards countless hours to do . I founded a portal called Seekme.ai, a comprehensive platform that houses over 10,000 AI tools and resources. Today, I'm excited to share with you an insightful and enlightening journey of how I mapped these tools to 15,000 tasks across 4,000 professions. This process, which I've named "Learn by Doing," got me the power of determination, collaboration, and adaptability. The Idea: It all started when I recognized the need for a more efficient and accessible way for professionals to understand which AI tools could help them automate their tasks. The traditional approach of manually researching and testing each AI tool for every profession was time-consuming and inefficient. I envisioned a solution that could streamline this process, making AI adoption easier and more accessible for a broader audience. The Planning: To begin, we needed a clear understanding of the task landscape across various professions. With the help of some Reddit communities , we embarked on an extensive study of common tasks in various industries. We utilized various sources, including government reports, industry surveys, and academic research, to create a comprehensive list of tasks. The result was an impressive list of 15,000 tasks. The Mapping: With the list of tasks in hand, the next step was to identify which AI tools could perform these tasks. I meticulously researched and analyzed each AI tool's capabilities and features. We cross-referenced this information with the tasks I had identified and created a mapping between the two. The process involved a significant amount of collaboration and refinement, as we continually updated and expanded our database of AI tools and tasks. The Challenges: The mapping process was not without its challenges. One of the primary obstacles was ensuring the accuracy and completeness of our data. To address this issue, I implemented a rigorous quality control process that included multiple rounds of checks and validations.I also established partnerships with industry experts and AI vendors to ensure our data was up-to-date and accurate. There is also a challenge that I faced was what is the quality of the tools which is the problem and how do I rank multiple tools if they do the same tasks without user feedback The Results: After months of hard work and dedication, I successfully mapped 10,000 AI tools to 15,000 tasks across 4,000 professions. Our new feature, AI by Profession, was born. This innovative will allow users to quickly and easily identify the AI tools that can automate tasks in their profession, making AI adoption more accessible and efficient than ever before. The Impact: The impact of this project has been significant. By making it easier for professionals to identify AI tools that can automate tasks in their industry, we're helping to drive productivity, efficiency, and innovation. Our users are saving time and resources by not having to manually research and test AI tools. Furthermore, we're contributing to the broader goal of democratizing AI and making it accessible to a broader audience. But there is a still an issue we face of ranking tools who does the similar job. For instance for content creation there 10 tools that can do same video editing so how do we rank it . We are planning to add categories to this to make it more exhaustive Conclusion: The journey to mapping 10,000 AI tools for 15,000 tasks across 4,000 professions was a challenging and rewarding experience. It required a significant amount of planning, determination, and collaboration, but the end result was a powerful tool that's making a difference in the lives of professionals around the world. I don’t know yet how useful it is yet for users So I am inviting you all to see if this feature can help you better equip yourself on the new wave and do things better. I am always up for a chat on anything AI and provide my help if needed. Looking forward to some feedback aswell

No Code Machine Learning Microsoft Tool Lobe.AI Tutorial

Is this the best non-fiction overview of machine learning?

By “non-fiction” I mean that it’s not a technical book or manual how-to or textbook, but acts as a narrative introduction to the field. Basically, something that you could find extracted in The New Yorker. Let me know if you think a better alternative is out there.

[SERIOUS] I'm really struggling with no interviews, looking for advice/improvements. A recent double master's aiming for Machine Learning/Data Science roles. Thanks :)

I have been applying for my first machine learning full-time job in Germany for past 4-5 months, but now I have just graduated and I am still not getting a single e-mail for next round. I would really appreciate feedback on my resume. I am mostly applying for CV or MLOps roles but also ML/AI Eng/Dev

I'm software engineer learning ML and using AI tools. Getting better at it - I created a tool to automate tedious tasks in your browser with AI!

[D] Introduction to Deep Q-learning with SynapticJS & ConvNetJS - build a connect 4 AI

[R] Introduction to Machine Learning & AI lectures by DeepMind and UCL

Practical AI Machine Learning and Data Science

Enable JavaScript and cookies to continue

ChatGPT Full Course For 2025 | ChatGPT Tutorial For Beginnners | ChatGPT Course | Simplilearn

🔥Purdue - Applied Generative AI Specialization - https://www.simplilearn.com/applied-ai-course?utmcampaign=C4lBsBlloL0&utmmedium=Lives&utm_source=Youtube 🔥Professional Certificate Program in Generative AI and Machine Learning - IITG (India Only) - https://www.simplilearn.com/iitg-generative-ai-machine-learning-program?utmcampaign=C4lBsBlloL0&utmmedium=Lives&utm_source=Youtube 🔥Advanced Executive Program In Applied Generative AI - https://www.simplilearn.com/applied-generative-ai-course?utmcampaign=C4lBsBlloL0&utmmedium=Lives&utm_source=Youtube This ChatGPT Full Course 2025 by Simplilearn provides a comprehensive learning journey, starting with an introduction to ChatGPT and Generative AI, followed by insights into AI job opportunities and a comparison between ChatGPT 4.0 and 4.0 Turbo. The tutorial covers prompt engineering techniques, machine learning fundamentals, and running Llama models privately. Learners will explore ChatGPT-powered application development, its role in programming, and Excel automation. The course also dives into blogging, PowerPoint automation, customer support, and finance applications. Advanced topics like RAG vs. Prompt Tuning, prompt injection, and LangChain are included, along with discussions on OpenAI's latest innovations, including Sora and Strawberry. By the end, participants will gain a strong understanding of ChatGPT’s capabilities and monetization strategies. 🚀 Following are the topics covered in the ChatGPT Full Course 2025: 00:00:00 - Introduction to ChatGPT Full Course 2025 00:09:26 - What is ChatGPT 00:10:11 - What is Gen AI 00:26:29 - How to get Job in AI 00:27:06 - ChatGPT 40 vs ChatGPT 4 01:03:14 - Chatgpt analyse 02:13:57 - Prompt Engineering Tutorial 03:10:34 - What is Machine Learning 04:07:06 - Machine Learning Tutorial 04:08:13 - Run Lama Privately 04:23:50 - Search GPT 04:25:31 - Build App Using ChatGPT 06:31:11 - ChatGPT for Programming 06:46:08 - Prompt Formulae Chatgpt 07:58:38 - Automate Excel using Chatgpt 08:00:06 - Blogging with ChatGpt 08:27:25 - Powerpoint using Chatgpt 08:28:31 - Rag Vs Prompt Tuning 09:37:43 - Chatgpt for Customer Support 11:11:06 - ChatGPT for finance 11:17:38 - Prompt injection 11:18:38 - How to Earn Money using ChatGPT 11:41:46 - Open AI Strawberry 11:52:42 - Openai sora 11:54:57 - Langchain 12:22:19 - Open ai chatgpt o1 model ✅ Subscribe to our Channel to learn more about the top Technologies: https://bit.ly/2VT4WtH ⏩ Check out the Artificial Intelligence training videos: https://youtube.com/playlist?list=PLEiEAq2VkUULa5aOQmO_al2VVmhC-eqeI #gpt #chatgpt #chatgptforbeginners #chatgptcourse #genai #generativeai #artificialintelligence #ai #machinelearning #llm #simplilearn #2025 ➡️ About Professional Certificate Program in Generative AI and Machine Learning Dive into the future of AI with our Generative AI & Machine Learning course, in collaboration with E&ICT Academy, IIT Guwahati. Learn tools like ChatGPT, OpenAI, Hugging Face, Python, and more. Join masterclasses led by IITG faculty, engage in hands-on projects, and earn Executive Alumni Status. Key Features: ✅ Program completion certificate from E&ICT Academy, IIT Guwahati ✅ Curriculum delivered in live virtual classes by seasoned industry experts ✅ Exposure to the latest AI advancements, such as generative AI, LLMs, and prompt engineering ✅ Interactive live-virtual masterclasses delivered by esteemed IIT Guwahati faculty ✅ Opportunity to earn an 'Executive Alumni Status' from E&ICT Academy, IIT Guwahati ✅ Eligibility for a campus immersion program organized at IIT Guwahati ✅ Exclusive hackathons and “ask-me-anything” sessions by IBM ✅ Certificates for IBM courses and industry masterclasses by IBM experts ✅ Practical learning through 25+ hands-on projects and 3 industry-oriented capstone projects ✅ Access to a wide array of AI tools such as ChatGPT, Hugging Face, DALL-E 2, Midjourney and more ✅ Simplilearn's JobAssist helps you get noticed by top hiring companies Skills Covered: ✅ Generative AI ✅ Prompt Engineering ✅ Chatbot Development ✅ Supervised and Unsupervised Learning ✅ Model Training and Optimization ✅ Model Evaluation and Validation ✅ Ensemble Methods ✅ Deep Learning ✅ Natural Language Processing ✅ Computer Vision ✅ Reinforcement Learning ✅ Machine Learning Algorithms ✅ Speech Recognition ✅ Statistics Learning Path: ✅ Program Induction ✅ Programming Fundamentals ✅ Python for Data Science (IBM) ✅ Applied Data Science with Python ✅ Machine Learning ✅ Deep Learning with TensorFlow (IBM) ✅ Deep Learning Specialization ✅ Essentials of Generative AI, Prompt Engineering & ChatGPT ✅ Advanced Generative AI ✅ Capstone Electives: ✅ ADL & Computer Vision ✅ NLP and Speech Recognition ✅ Reinforcement Learning ✅ Academic Masterclass ✅ Industry Masterclass 👉 Learn More At: https://www.simplilearn.com/iitg-generative-ai-machine-learning-program?utmcampaign=C4lBsBlloL0&utmmedium=Lives&utm_source=Youtube

With Vibe Coding Say Goodbye to Boring Coding!

Coding doesn’t have to be boring anymore! With the rise of AI-powered tools and innovative development approaches, the way we write code is changing drastically. Are you ready to embrace this new era of vibe coding? 🚀 💡 Want to level up your coding and problem-solving skills? Join the Three 90 Challenge by GeeksforGeeks—ending on 31st March! ✅ Complete 90% of your course in 90 days ✅ Get 90% of your fee refunded! Yes, you read that right! 🌟 Over ₹5 CRORE in refunds already processed—yours could be next! 👉 Start the challenge now: https://gfgcdn.com/tu/U4a/ 📌 Stay Connected for More Coding Challenges & Learning Resources: 📱 Download the GeeksforGeeks App: https://play.google.com/store/apps/details?id=free.programming.programming 💬 Twitter: https://twitter.com/geeksforgeeks 🧑‍💼 LinkedIn: https://www.linkedin.com/company/geeksforgeeks 📷 Instagram: https://www.instagram.com/geeksforgeeks/ 💌 Telegram: https://t.me/geeksforgeeks_official 📌 Pinterest: https://in.pinterest.com/geeksforgeeks/ 🎮 Discord: https://discord.gg/geeksforgeeks 🔍 Tags: AI Coding, AI-Powered Development, Vibe Coding, Future of Programming, Software Development Trends, Coding with AI, AI-Assisted Programming, Tech Innovations, Machine Learning in Coding, AI Coding Assistants, Software Engineering Revolution, AI for Developers, ChatGPT Coding, AI Coding Tools, gfg, gfg courses, gfg classes, it jobs, it job market, ai trends, ai news, ai vs software developers 🔥 Hashtags: #AICoding #FutureOfProgramming #VibeCoding #SoftwareDevelopment #TechTrends #CodingWithAI #AIRevolution #AIInTech #MachineLearning #CodingFuture #GeeksforGeeks #CodeSmarter #AIforDevelopers

🔥Salary of GenAI Engineer | Generative AI Jobs: Roles, Salaries, and Growth Potential 🚀💼 | #shorts

Curious about Generative AI and the lucrative career opportunities it offers? In this video, we dive into the world of Generative AI with our guest, who’s been researching this groundbreaking field. You've likely heard of tools like ChatGPT, Llama, and Gemini—all of which are examples of Generative AI at work. Our guest breaks down Generative AI, explaining how it uses advanced machine learning models to generate content like images, text, music, and more. As the field grows, so do the career opportunities. Exciting new roles such as Generative AI Engineer and AI Chatbot Engineer are emerging and gaining popularity. And what about the salary? In metro cities like Bangalore and Hyderabad, Generative AI Engineers typically earn between 15 to 30 LPA, making this one of the hottest and most promising fields in tech right now. With its rapid growth potential, mastering Generative AI can lead to a rewarding and high-paying career. Watch the full video to learn more about Generative AI and how you can be part of this exciting industry! #GenerativeAI #AICareers #AIEngineer #TechJobs #ChatGPT #AIChatbots #MachineLearning #HighPayingJobs #GenerativeAIEngineer #TechSalaries #AIInnovation

Google’s AI Course for Beginners (in 10 minutes)!

Grab my AI Toolkit for free: https://academy.jeffsu.org/ai-toolkit?utmsource=youtube&utmmedium=video&utm_campaign=146 Grab my free Workspace Toolkit: https://academy.jeffsu.org/workspace-toolkit?utmsource=youtube&utmmedium=video&utm_campaign=146 🔍 In this video, we unravel the layers of AI, Machine Learning, Deep Learning, and their applications in tools like #ChatGPT and Google #Bard We first go through how AI is a broad field of study that encompasses #MachineLearning as a sub-field. We then break down Machine Learning into supervised and unsupervised models, using real-world examples to illustrate their functions and differences. We move deeper into Deep Learning: Learn about artificial neural networks and the power of semi-supervised learning in applications like fraud detection in banking. Then we delve into Generative AI, differentiating it from discriminative models and demonstrating its capabilities in creating new, innovative outputs. Finally we walk through Large Language Models (LLMs) and uncover the significance of LLMs in AI, their pre-training processes, and their customization for specific industry applications TIMESTAMPS 00:00 Google’s AI Course in 10 Minutes 00:38 What is Artificial Intelligence? 01:27 What is Machine Learning? 03:28 What is Deep Learning? 05:15 What is Generative AI? 07:05 What are Large Language Models? RESOURCES I MENTION IN THE VIDEO Google’s full course: https://www.cloudskillsboost.google/course_templates/536 Grab my free Workspace Toolkit: https://academy.jeffsu.org/workspace-toolkit?utmsource=youtube&utmmedium=video&utm_campaign=146 MY FAVORITE GEAR 🎬 My YouTube Gear - https://www.jeffsu.org/yt-gear/ 🎒 Everyday Carry - https://www.jeffsu.org/my-edc/ MY TOP 3 FAVORITE SOFTWARE ❎ CleanShot X - https://geni.us/cleanshotx ✍️ Skillshare - https://geni.us/skillshare-jeff 📖 Readwise - https://readwise.io/jeffsu/ BE MY FRIEND: 📧 Subscribe to my Productivity newsletter - https://www.jeffsu.org/productivity-ping/ 📸 Instagram - https://instagram.com/j.sushie 🤝 LinkedIn - https://www.linkedin.com/in/jsu05/ 👨🏻‍💻 WHO AM I: I'm Jeff, a tech professional trying to figure life out. What I do end up figuring out, I share! PS: Some of the links in this description are affiliate links I get a kickback from and my opinions are my own and may not reflect that of my employer 😇

AI Engineer Roadmap 2023 !

AI Engineer Roadmap 2023 ! #aiengineer #ai #softwaredeveloper #softwareengineer #programmingmemes #webdev #websitedesigner #ibm #python #artificialintelligence #promptengineering #technews #softwaredevelopment #webdevelopers #datascience #machinelearning #technologynews #techworld #freeproducts #reactjs #quantum #quantumcomputing #uidesigner #uiuxdesign #html #programming #css #javascript #aiart #quantummechanics

Top AI courses that you can take for free

Al will not replace people but people who can use Al will replace those who cannot!💡 No matter who you are, you need to understand Al if you want to succeed in your field🤖 Here are top Al courses by Harvard and Stanford that you can take for FREE today: 1️⃣Stanford - Andrew Ng's Al for Everyone - Ng is the BIGGEST name in Al and so many of my clients have taken his courses on Coursera - https://www.coursera.org/learn/ai-for-everyone 2️⃣Harvard - Introduction to Artificial Intelligence with Python on edX- https://www.edx.org/course/cs50s-introduction-to -artificial-intelligence-with-python 3️⃣Stanford - NLP with Deep Learning on YouTube -https://www.youtube.com/watch?v=rmVRLEJRk14&list= PLOROMvodv4rOSH4v6133s9LFPRHjEmbmJ 4️⃣Harvard - Data Science & Machine Learning on edX (great for hands on learning) - https://www.edx.org/course/data-science-machine -learning 5️⃣Stanford - Andrew Ng's Deep Learning course archive on YouTube - https://www.youtube.com/watch?v=PySo6S4ZAg&list= PLOROMvodv4r0ABXSygHTsbvUz4GYQhOb So, what are you waiting for? Start learning and building next gen Al tools! #resume #scholarstrategy #careeradvice #careercoaching #careercounseling #indianengineer #studyinusa #msinusa #studyabroad #freecourses #courses #ai #machinelearning #datascience

Python for Data Science, AI & Development

Kickstart your learning of Python with this beginner-friendly self-paced course taught by an expert. Python is one of the most popular languages in the programming and data science world and demand for individuals who have the ability to apply Python has never been higher.

Practical AI for Professionals

Explore key ideas in Artificial Intelligence (AI) while delving into trending developments in the field. Examines AI tools and frameworks to enable collaboration effectively and efficiently across technical and non-technical stakeholders. Analyze topics such as AI-enabled perception, representation, reasoning, and learning as contextualized by societal impact. Equips students with the knowledge and skills necessary to confidently navigate the ever-evolving landscape of artificial intelligence

Introduction to Microsoft Copilot

In this introductory course, you'll embark on a journey into the world of generative AI and Microsoft Copilot. We'll demystify the concepts behind this transformative technology, exploring its potential and limitations. You'll gain a clear understanding of what generative AI is, how it works, and the diverse range of tasks it can perform. You'll be introduced to the specific capabilities of Copilot within the Microsoft 365 and Dynamics 365 ecosystems. We'll showcase how Copilot harnesses the power of AI and machine learning to revolutionize your productivity across various applications. From automating mundane tasks to generating creative content, you'll discover the myriad ways Copilot can enhance your workflow.

Generative AI: Introduction and Applications

This course is designed for everyone, including professionals, executives, students, and enthusiasts, interested in learning about generative AI and leveraging its capabilities in their work and lives.

Generative AI Applications and Popular Tools

Welcome to the 'Generative AI Applications and Popular Tools' course, learning resource for mastering the intricacies of chatbot technology, including RASA, GPT-3, and OpenCV, along with an in-depth exploration of popular Generative AI tools like MidJourney, GitHub Copilot, DALL·E 2, and more.

AWS Cloud Technical Essentials

Are you in a technical role and want to learn the fundamentals of AWS? Do you aspire to have a job or career as a cloud developer, architect, or in an operations role? If so, AWS Cloud Technical Essentials is an ideal way to start. This course was designed for those at the beginning of their cloud-learning journey - no prior knowledge of cloud computing or AWS products and services required!

AI Python for Beginners

AI Python for Beginners is designed to help you leverage the power of Python programming, even if your goal isn’t to become a software developer or AI engineer. This four-part course that teaches you to code practical AI applications from day one, even if you've never programmed before. You’ll learn with support from an AI chatbot that can help you get immediate feedback, quickly fix bugs, and keep you on track while learning new skills. You'll gain a foundational understanding of Python while building AI-powered tools like custom recipe generators, smart to-do lists, and vacation planners, and learn essential programming concepts such as variables, functions, loops, and data structures.

Finally Launched My First App Without Any Coding Experience

About Myself I am a structural engineer that are taught to design buildings in the day and I have been dreaming forever to build a SaaS business to get out of the rat race. However, as a structural engineer, coding is definitely not something I am capable of doing (I have some simple knowledge, but its no way close to building an app) The Journey As I've mentioned, I always wanted to build a SaaS business because in my mind the business model is most attractive to me, where you only need to build once and can sell to millions. So I started off searching and exploring on the internet and my first ever "SaaS" was from Wordpress. I am buying plugin from other user and then pluggin into my own Wordpress website. It was a project management tool SaaS. I was so excited about the website and can't even sleep well at night because I'm just so hype about it. But, the reality is because this is my first ever business, I totally didn't realise about the importance of UI UX or my business differentiation, thinking that everyone will be as excited as I am. Then, I went deeper and deeper into the journey (I can write more about this in another post if anyone is interested) and finally landed on Flutterflow to create my first ever app. No Code Journey Thanks to no code builder, I never thought that a non-coder like me can ever create an app and got accepted by the App Store/Play Store. Since that I am using a low-code builder, for any specific requirement that I need that are not covered natively, I will just talk to ChatGPT and boom I pretty much got most of the answer I needed. About The App As someone that always try to keep track of my expenses, I never able to find an app that are simple and interesting enough for me to continue on the journey. I realise that I could have incorporate AI into this journey and hence there go, I created an AI Money Tracker. Let me introduce Rolly: AI Money Tracker - a new AI expense tracker where you can easily record your transactions just by chatting with our bot Rolly and it will automatically record and categorise the transaction into the most suitable category (you can also create any of your own category and it will also take care of it in consideration). I am not sharing the app link here to avoid getting ban, but feel free to search up Rolly: AI Money Tracker on either App Store on Play Store. My Learnings As someone that can't code and never imagine that I could create a production app by myself and publish it on to the App Store and Play Store. Since I am not making any money yet and just at the beginning of my entrepreneur journey, I can't give any substantial advice, all I can say is just my own learnings and feelings. My advice is if you have a dream of building a business, just go for it, don't worry about all the problems that you can think of to convince yourself not making the start at all. From my point of view, as long as you're not giving up everything (eg, putting yourself in huge debt etc), why don't just go for it and you've got nothing much to lose. You'll only lose if you never even get started. And also, I believe that creating an app is always the easiest step out of the entreprenuership journey, marketing and distribution is the key to success. Even though you've spent days and nights on it and it might mean everything to you, the truth is people don't really cares and you'll need to market for it. I am still in journey to learn how to do marketing, content, building a business and everything. I think this is just a very beginning of my journey and hopefully there's more interesting one to share further down the road.

Experienced Software Developer looking for startup to help. I will not promote

My passion for programming started at the age of 9 when I began playing video games. It was during this time that I first dived into programming, creating scripts for SA:MP (San Andreas Multiplayer) using the Pawn language. SA:MP is a modification for the popular game Grand Theft Auto: San Andreas, allowing players to experience multiplayer gameplay. My early experiences in programming were all about problem-solving—finding ways to enhance the game and improve the player experience. This was when I realized how satisfying it is to solve a problem through code, and that feeling has stayed with me throughout my career. I am a self-taught programmer, and everything I know today comes from my own initiative to learn and improve. After five years of working with local clients, I decided to expand my knowledge and started learning more widely applicable programming languages like Java and Python. I’ve always been the type of person who thrives on challenges. Whenever I encounter a problem, I don’t just look for a quick fix—I dive deep into researching and understanding the problem, and I find a solution that works in the long run. This is what drives me. The ability to solve problems, no matter how complex, and the satisfaction that comes with it is what fuels my passion for programming. My big break came when I had the opportunity to work at \\\\. There, I replaced two senior and two junior developers, which led to significant cost savings for the company. I completed all tasks ahead of schedule, focusing on Java-based applications that were multithreaded and communicated with embedded systems. This experience taught me how to work under pressure and how to manage and solve complex technical problems efficiently. Following my time at \\\\, I transitioned into freelance work as a FullStack Developer, working with technologies such as HTML, CSS, Bootstrap, JavaScript, Django, Spring, MySQL, and PostgreSQL. As a freelancer, I was responsible for finding solutions to a wide range of problems, often working independently and making decisions on the fly. I learned that self-reliance is key in this industry, and being resourceful is one of the most important qualities a developer can have. Later, I joined \\\\ elecom, where I worked on system integration with foreign teams, BPM process solutions, and the merging of complex systems in Oracle databases. I continued to solve challenges, often working with teams across borders and tackling technical obstacles that required creative and well-thought-out solutions. Eventually, I founded my own company, \\\\, where I focus on developing software solutions, Artificial Intelligence (AI), Cybersecurity, and Ethical Hacking. As an entrepreneur, I take pride in finding innovative solutions to problems, whether they come from clients or from technical obstacles I encounter along the way. I’ve also had the privilege of working with the Serbian Ministry of Defense and the police, handling sensitive projects that demand both technical expertise and trustworthiness. Being a self-taught programmer means that I have had to learn and adapt on my own, and I’ve learned to embrace challenges as opportunities for growth. I am constantly driven by the process of solving problems, and it is what keeps me engaged and fulfilled in my work. I am always open to new collaborations and am eager to take on new challenges that push my boundaries in technology, cybersecurity, and software development.

I spent 6 months on building a tool, and got 0 zero users. Here is my story.

Edit Thank you all so much for your time reading my story. Your support, feedback, criticism, and skepticism; all helped me a lot, and I couldn't appreciate it enough \^\_\^ TL;DR I spent 6 months on a tool that currently has 0 users. Below is what I learned during my journey, sharing because I believe most mistakes are easily avoidable. Do not overestimate your product and assume it will be an exception to fundamental principles. Principles are there for a reason. Always look for validation before you start. Avoid building products with a low money-to-effort ratio/in very competitive fields. Unless you have the means, you probably won't make it. Pick a problem space, pick your target audience, and talk to them before thinking about a solution. Identify and match their pain points. Only then should you think of a solution. If people are not overly excited or willing to pay in advance for a discounted price, it might be a sign to rethink. Sell one and only one feature at a time. Avoid everything else. If people don't pay for that one core feature, no secondary feature will change their mind. Always spend twice as much time marketing as you do building. You will not get users if they don't know it exists. Define success metrics ("1000 users in 3 months" or "$6000 in the account at the end of 6 months") before you start. If you don't meet them, strongly consider quitting the project. If you can't get enough users to keep going, nothing else matters. VALIDATION, VALIDATION, VALIDATION. Success is not random, but most of our first products will not make a success story. Know when to admit failure, and move on. Even if a product of yours doesn't succeed, what you learned during its journey will turn out to be invaluable for your future. My story So, this is the story of a product, Summ, that I’ve been working on for the last 6 months. As it's the first product I’ve ever built, after watching you all from the sidelines, I have learned a lot, made many mistakes, and did only a few things right. Just sharing what I’ve learned and some insights from my journey so far. I hope that this post will help you avoid the mistakes I made — most of which I consider easily avoidable — while you enjoy reading it, and get to know me a little bit more 🤓. A slow start after many years Summ isn’t the first product I really wanted to build. Lacking enough dev skills to even get started was a huge blocker for so many years. In fact, the first product I would’ve LOVED to build was a smart personal shopping assistant. I had this idea 4 years ago; but with no GPT, no coding skills, no technical co-founder, I didn’t have the means to make it happen. I still do not know if such a tool exists and is good enough. All I wanted was a tool that could make data-based predictions about when to buy stuff (“buy a new toothpaste every three months”) and suggest physical products that I might need or be strongly interested in. AFAIK, Amazon famously still struggles with the second one. Fast-forward a few years, I learned the very basics of HTML, CSS, and Vanilla JS. Still was not there to build a product; but good enough to code my design portfolio from scratch. Yet, I couldn’t imagine myself building a product using Vanilla JS. I really hated it, I really sucked at it. So, back to tutorial hell, and to learn about this framework I just heard about: React.React introduced so many new concepts to me. “Thinking in React” is a phrase we heard a lot, and with quite good reasons. After some time, I was able to build very basic tutorial apps, both in React, and React Native; but I have to say that I really hated coding for mobile. At this point, I was already a fan of productivity apps, and had a concept for a time management assistant app in my design portfolio. So, why not build one? Surely, it must be easy, since every coding tutorial starts with a todo app. ❌ WRONG! Building a basic todo app is easy enough, but building one good enough for a place in the market was a challenge I took and failed. I wasted one month on that until I abandoned the project for good. Even if I continued working on it, as the productivity landscape is overly competitive, I wouldn’t be able to make enough money to cover costs, assuming I make any. Since I was (and still am) in between jobs, I decided to abandon the project. 👉 What I learned: Do not start projects with a low ratio of money to effort and time. Example: Even if I get 500 monthly users, 200 of which are paid users (unrealistically high number), assuming an average subscription fee of $5/m (such apps are quite cheap, mostly due to the high competition), it would make me around $1000 minus any occurring costs. Any founder with a product that has 500 active users should make more. Even if it was relatively successful, due to the high competition, I wouldn’t make any meaningful money. PS: I use Todoist today. Due to local pricing, I pay less than $2/m. There is no way I could beat this competitive pricing, let alone the app itself. But, somehow, with a project that wasn’t even functional — let alone being an MVP — I made my first Wi-Fi money: Someone decided that the domain I preemptively purchased is worth something. By this point, I had already abandoned the project, certainly wasn’t going to renew the domain, was looking for a FT job, and a new project that I could work on. And out of nowhere, someone hands me some free money — who am I not to take it? Of course, I took it. The domain is still unused, no idea why 🤔. Ngl, I still hate the fact that my first Wi-Fi money came from this. A new idea worth pursuing? Fast-forward some weeks now. Around March, I got this crazy idea of building an email productivity tool. We all use emails, yet we all hate them. So, this must be fixed. Everyone uses emails, in fact everyone HAS TO use emails. So, I just needed to build a tool and wait for people to come. This was all, really. After all, the problem space is huge, there is enough room for another product, everyone uses emails, no need for any further validation, right? ❌ WRONG ONCE AGAIN! We all hear from the greatest in the startup landscape that we must validate our ideas with real people, yet at least some of us (guilty here 🥸) think that our product will be hugely successful and prove them to be an exception. Few might, but most are not. I certainly wasn't. 👉 Lesson learned: Always validate your ideas with real people. Ask them how much they’d pay for such a tool (not if they would). Much better if they are willing to pay upfront for a discount, etc. But even this comes later, keep reading. I think the difference between “How much” and “If” is huge for two reasons: (1) By asking them for “How much”, you force them to think in a more realistic setting. (2) You will have a more realistic idea on your profit margins. Based on my competitive analysis, I already had a solution in my mind to improve our email usage standards and email productivity (huge mistake), but I did my best to learn about their problems regarding those without pushing the idea too hard. The idea is this: Generate concise email summaries with suggested actions, combine them into one email, and send it at their preferred times. Save as much as time the AI you end up with allows. After all, everyone loves to save time. So, what kind of validation did I seek for? Talked with only a few people around me about this crazy, internet-breaking idea. The responses I got were, now I see, mediocre; no one got excited about it, just said things along the lines of “Cool idea, OK”. So, any reasonable person in this situation would think “Okay, not might not be working”, right? Well, I did not. I assumed that they were the wrong audience for this product, and there was this magical land of user segments waiting eagerly for my product, yet unknowingly. To this day, I still have not reached this magical place. Perhaps, it didn’t exist in the first place. If I cannot find it, whether it exists or not doesn’t matter. I am certainly searching for it. 👉 What I should have done: Once I decide on a problem space (time management, email productivity, etc.), I should decide on my potential user segments, people who I plan to sell my product to. Then I should go talk to those people, ask them about their pains, then get to the problem-solving/ideation phase only later. ❗️ VALIDATION COMES FROM THE REALITY OUTSIDE. What validation looks like might change from product to product; but what invalidation looks like is more or less the same for every product. Nico Jeannen told me yesterday “validation = money in the account” on Twitter. This is the ultimate form of validation your product could get. If your product doesn’t make any money, then something is invalidated by reality: Your product, you, your idea, who knows? So, at this point, I knew a little bit of Python from spending some time in tutorial hell a few years ago, some HTML/CSS/JS, barely enough React to build a working app. React could work for this project, but I needed easy-to-implement server interactivity. Luckily, around this time, I got to know about this new gen of indie hackers, and learned (but didn’t truly understand) about their approach to indie hacking, and this library called Nextjs. How good Next.js still blows my mind. So, I was back to tutorial hell once again. But, this time, with a promise to myself: This is the last time I would visit tutorial hell. Time to start building this "ground-breaking idea" Learning the fundamentals of Next.js was easier than learning of React unsurprisingly. Yet, the first time I managed to run server actions on Next.js was one of the rarest moments that completely blew my mind. To this day, I reject the idea that it is something else than pure magic under its hood. Did I absolutely need Nextjs for this project though? I do not think so. Did it save me lots of time? Absolutely. Furthermore, learning Nextjs will certainly be quite helpful for other projects that I will be tackling in the future. Already got a few ideas that might be worth pursuing in the head in case I decide to abandon Summ in the future. Fast-forward few weeks again: So, at this stage, I had a barely working MVP-like product. Since the very beginning, I spent every free hour (and more) on this project as speed is essential. But, I am not so sure it was worth it to overwork in retrospect. Yet, I know I couldn’t help myself. Everything is going kinda smooth, so what’s the worst thing that could ever happen? Well, both Apple and Google announced their AIs (Apple Intelligence and Google Gemini, respectively) will have email summarization features for their products. Summarizing singular emails is no big deal, after all there were already so many similar products in the market. I still think that what truly matters is a frictionless user experience, and this is why I built this product in a certain way: You spend less than a few minutes setting up your account, and you get to enjoy your email summaries, without ever visiting its website again. This is still a very cool concept I really like a lot. So, at this point: I had no other idea that could be pursued, already spent too much time on this project. Do I quit or not? This was the question. Of course not. I just have to launch this product as quickly as possible. So, I did something right, a quite rare occurrence I might say: Re-planned my product, dropped everything secondary to the core feature immediately (save time on reading emails), tried launching it asap. 👉 Insight: Sell only one core feature at one time. Drop anything secondary to this core feature. Well, my primary occupation is product design. So one would expect that a product I build must have stellar design. I considered any considerable time spent on design at this stage would be simply wasted. I still think this is both true and wrong: True, because if your product’s core benefits suck, no one will care about your design. False, because if your design looks amateurish, no one will trust you and your product. So, I always targeted an average level design with it and the way this tool works made it quite easy as I had to design only 2 primary pages: Landing page and user portal (which has only settings and analytics pages). However, even though I knew spending time on design was not worth much of my time, I got a bit “greedy”: In fact, I redesigned those pages three times, and still ended up with a so-so design that I am not proud of. 👉 What I would do differently: Unless absolutely necessary, only one iteration per stage as long as it works. This, in my mind, applies to everything. If your product’s A feature works, then no need to rewrite it from scratch for any reason, or even refactor it. When your product becomes a success, and you absolutely need that part of your codebase to be written, do so, but only then. Ready to launch, now is th etime for some marketing, right? By July 26, I already had a “launchable” product that barely works (I marked this date on a Notion docs, this is how I know). Yet, I had spent almost no time on marketing, sales, whatever. After all, “You build and they will come”. Did I know that I needed marketing? Of course I did, but knowingly didn’t. Why, you might ask. Well, from my perspective, it had to be a dev-heavy product; meaning that you spend most of your time on developing it, mostly coding skills. But, this is simply wrong. As a rule of thumb, as noted by one of the greatests, Marc Louvion, you should spend at least twice of the building time on marketing. ❗️ Time spent on building \* 2 people don’t know your product > they don’t use your product > you don’t get users > you don’t make money Easy as that. Following the same reasoning, a slightly different approach to planning a project is possible. Determine an approximate time to complete the project with a high level project plan. Let’s say 6 months. By the reasoning above, 2 months should go into building, and 4 into marketing. If you need 4 months for building instead of 2, then you need 8 months of marketing, which makes the time to complete the project 12 months. If you don’t have that much time, then quit the project. When does a project count as completed? Well, in reality, never. But, I think we have to define success conditions even before we start for indie projects and startups; so we know when to quit when they are not met. A success condition could look like “Make $6000 in 12 months” or “Have 3000 users in 6 months”. It all depends on the project. But, once you set it, it should be set in stone: You don’t change it unless absolutely necessary. I suspect there are few principles that make a solopreneur successful; and knowing when to quit and when to continue is definitely one of them. Marc Louvion is famously known for his success, but he got there after failing so many projects. To my knowledge, the same applies to Nico Jeannen, Pieter Levels, or almost everyone as well. ❗️ Determining when to continue even before you start will definitely help in the long run. A half-aed launch Time-leap again. Around mid August, I “soft launched” my product. By soft launch, I mean lazy marketing. Just tweeting about it, posting it on free directories. Did I get any traffic? Surely I did. Did I get any users? Nope. Only after this time, it hit me: “Either something is wrong with me, or with this product” Marketing might be a much bigger factor for a project’s success after all. Even though I get some traffic, not convincing enough for people to sign up even for a free trial. The product was still perfect in my eyes at the time (well, still is ^(\_),) so the right people are not finding my product, I thought. Then, a question that I should have been asking at the very first place, one that could prevent all these, comes to my mind: “How do even people search for such tools?” If we are to consider this whole journey of me and my so-far-failed product to be an already destined failure, one metric suffices to show why. Search volume: 30. Even if people have such a pain point, they are not looking for email summaries. So, almost no organic traffic coming from Google. But, as a person who did zero marketing on this or any product, who has zero marketing knowledge, who doesn’t have an audience on social media, there is not much I could do. Finally, it was time to give up. Or not… In my eyes, the most important element that makes a founder (solo or not) successful (this, I am not by any means) is to solve problems. ❗️ So, the problem was this: “People are not finding my product by organic search” How do I make sure I get some organic traffic and gets more visibility? Learn digital marketing and SEO as much as I can within very limited time. Thankfully, without spending much time, I came across Neil Patel's YT channel, and as I said many times, it is an absolute gold mine. I learned a lot, especially about the fundamentals, and surely it will be fruitful; but there is no magic trick that could make people visit your website. SEO certainly helps, but only when people are looking for your keywords. However, it is truly a magical solution to get in touch with REAL people that are in your user segments: 👉 Understand your pains, understand their problems, help them to solve them via building products. I did not do this so far, have to admit. But, in case you would like to have a chat about your email usage, and email productivity, just get in touch; I’d be delighted to hear about them. Getting ready for a ProductHunt launch The date was Sept 1. And I unlocked an impossible achievement: Running out of Supabase’s free plan’s Egres limit while having zero users. I was already considering moving out of their Cloud server and managing a Supabase CLI service on my Hetzner VPS for some time; but never ever suspected that I would have to do this quickly. The cheapest plan Supabase offers is $25/month; yet, at that point, I am in between jobs for such a long time, basically broke, and could barely afford that price. One or two months could be okay, but why pay for it if I will eventually move out of their Cloud service? So, instead of paying $25, I spent two days migrating out of Supabase Cloud. Worth my time? Definitely not. But, when you are broke, you gotta do stupid things. This was the first time that I felt lucky to have zero users: I have no idea how I would manage this migration if I had any. I think this is one of the core tenets of an indie hacker: Controlling their own environment. I can’t remember whose quote this is, but I suspect it was Naval: Entrepreneurs have an almost pathological need to control their own fate. They will take any suffering if they can be in charge of their destiny, and not have it in somebody else’s hands. What’s truly scary is, at least in my case, we make people around us suffer at the expense of our attempting to control our own fates. I know this period has been quite hard on my wife as well, as I neglected her quite a bit, but sadly, I know that this will happen again. It is something that I can barely help with. Still, so sorry. After working the last two weeks on a ProductHunt Launch, I finally launched it this Tuesday. Zero ranking, zero new users, but 36 kind people upvoted my product, and many commented and provided invaluable feedback. I couldn't be more grateful for each one of them 🙏. Considering all these, what lies in the future of Summ though? I have no idea, to be honest. On one hand, I have zero users, have no job, no income. So, I need a way to make money asap. On the other hand, the whole idea of it revolves around one core premise (not an assumption) that I am not so willing to share; and I couldn’t have more trust in it. This might not be the best iteration of it, however I certainly believe that email usage is one of the best problem spaces one could work on. 👉 But, one thing is for certain: I need to get in touch with people, and talk with them about this product I built so far. In fact, this is the only item on my agenda. Nothing else will save my brainchild <3. Below are some other insights and notes that I got during my journey; as they do not 100% fit into this story, I think it is more suitable to list them here. I hope you enjoyed reading this. Give Summ a try, it comes with a generous free trial, no credit card required. Some additional notes and insights: Project planning is one of the most underestimated skills for solopreneurs. It saves you enormous time, and helps you to keep your focus up. Building B2C products beats building B2B products. Businesses are very willing to pay big bucks if your product helps them. On the other hand, spending a few hours per user who would pay $5/m probably is not worth your time. It doesn’t matter how brilliant your product is if no one uses it. If you cannot sell a product in a certain category/niche (or do not know how to sell it), it might be a good idea not to start a project in it. Going after new ideas and ventures is quite risky, especially if you don’t know how to market it. On the other hand, an already established category means that there is already demand. Whether this demand is sufficient or not is another issue. As long as there is enough demand for your product to fit in, any category/niche is good. Some might be better, some might be worse. Unless you are going hardcore B2B, you will need people to find your product by means of organic search. Always conduct thorough keyword research as soon as possible.

I'm a dev with zero fucking ideas. Help?

Long-time lurker, first-time poster here. I'm hoping you guys can help me out. I consider myself an above average engineer. With over 8 years of industry experience, I can whip out an MVP fast and iterate quickly. I love coding and learning new tech, but here's the issue—I've got absolutely no clue what to build. It's like I'm the least creative person I know, and can't find even one problem to solve. I've tried everything I can think of: Scrolling through ProductHunt until my eyes bled Asking non-tech friends about their "pain points" Stalking Twitter/X to see what people are building Experimenting with new AI tech to explore possibilities I've even attempted to build products. Almost 6 months ago, I started working on an AI conversation app to help non-native speakers like myself improve their English. But I soon realized there were already hundreds of apps doing this, and doing it much better than I could. I abandoned the project, figuring it wasn't unique enough. Same story with a couple of other projects that I started working on and abandoned later. So my question is how the heck you all come up with ideas? Any advice, commiseration, or hell—even random ideas you don’t want to build—would be greatly appreciated.

Best no-code tools for prototyping AI

building a b2b aI powered saas which will tap into an API and then use RAG. I’m searching for a co founder but an accelerator is interested in my project and I’d like to have a small prototype to show them. I’d also like to develop a small free version that can run on my site for customers to use. I’ve been looking at bubble but would appreciate any suggestions (especially free) that’s good for a non-techie (who actually enjoys building things and learning too hehe)

For anyone working on LLM / AI startups

My company (which I will not promote) wrote this blog post in compliance with rule #7 :) Introduction to fine-tuning Large Language Models, or LLMs, have become commonplace in the tech world. The number of applications that LLMs are revolutionizing is multiplying by the day — extraction use cases, chatbots, tools for creatives and engineers. In spite of this, at its core, the LLM is a multi-purpose neural network, dozens of layers deep, designed to simply predict one word after the next. It predicts words by performing billions of matrix multiplication steps based on so-called parameter weights, which are discovered during the model training process. Almost all open-source, open-weight models are trained on a massive amount of text from every conceivable genre and topic. How, then, do researchers and engineers create novel specialized applications? The answer is fine-tuning. In this post, we will demystify the process of fine-tuning and discuss the tradeoffs of other approaches to customizing an LLM. The history of fine-tuning In the ancient days of LLMs, by which we mean five years ago, the primary approaches to customizing an LLM was identical to the approaches to customizing any other deep learning model. A machine learning engineer would have two options: Retrain the entire LLM. This would mean discarding the trained weights and instead only using the open source model’s architecture to train it on a specialized dataset. As long as the amount and diversity of the specialized data is comparable to what the original model was trained on, this can be the ideal method of customizing a model. However, of course, this is a massive waste of resources due to the computational power required and the difficulty of collecting such a massive dataset. Even if an organization could provision enough GPUs, the cost of training modern-day models could cost up to $190 million. Retrain the last few layers of the LLM while keeping the rest of the weights frozen. This is a more efficient method in terms of time and computational power required because it significantly cuts down the number of parameters that need to be trained. However, for most tasks, this leads to subpar quality. Of course, almost everyone chooses to retrain the last few layers. And where there is only one option, the research community saw an opportunity to step in. Soon, the LLM space saw an enormous amount of activity in fine-tuning, which leads us to today. Modern approaches to fine-tuning Most fine-tuning approaches today are parameter-efficient. Deep neural networks are composed of matrices and vectors (generally called tensors), which are at their core arrays of floating point numbers. By training a small subset of these tensors, while the rest of the LLM’s weights are kept frozen, practitioners achieve good enough results without having to retrain the entire model. Generally, this method requires at least a hundred or so handcrafted examples of input-output pairs for fine-tuning. This is called supervised learning. The modern fine-tuning landscape involves an unsupervised learning step afterwards. Given a set of inputs, a practitioner gathers the various possible outputs from the LLM and casts votes among them. This preference data is then used to further train the LLM’s weights. Usually, this approach is used for LLM alignment and safety, which defends the application from malicious uses, outputs embarrassing to the organization, and prompt injection attacks. Fine-tuning’s relationship to prompt engineering A natural question arises: why fine-tune instead of crafting a well-considered system prompt? Wouldn’t that be easier and more efficient? The answer is no, it wouldn’t. Here’s why: Advanced techniques make prompt engineering obsolete: \[redacted\]'s product uses soft-prompting and other techniques to train the input layer itself. This obviates the need for prompt engineering entirely, which lets organizations avoid the time-consuming trial-and-error process to get the prompt just right. Prompt engineering has been a stopgap measure in the early days of LLM applications to convey the practitioner’s intent to the LLM. It is not the long-term solution for LLM application development. The system prompt is precious: the limited budget for system prompt length is better used for up-to-date information, e.g., Retrieval-Augmented Generation (RAG). Even as context windows increase in size with each new open-source model, the system prompt is the least efficient place to provide the LLM model with verbose instructions and examples. The longer the prompt, the slower the application: an LLM must attend to the entire system prompt for each token generated. This pain becomes more acute in the chatbot case, where the length of the conversation so far is also counted toward the system context. The longer the conversation, and the longer your beautifully-crafted system prompt, the slower the bot becomes. Even in cases where the model allows for system prompts that are millions of tokens long, doubling the size of the context will quadruple the latency. This means adding a few hundred words to the system prompt may result in several seconds of additional latency in production, making a chatbot impossible to use. Edge case handling: the number of edge cases that the system prompt would need to consider and emphasize to the LLM is too large. The instructions would have to be too nuanced and long to cover them all. However, fine-tuning on a dataset that considers these edge cases would be more straightforward. Do I need to fine-tune the LLM in my production application? Every LLM application in production must be fine-tuned often, not just once at the beginning. Why fine-tune? The world in which the application exists is constantly evolving. New prompt injection attacks are being discovered every day, new ways of embarrassing a chatbot are emerging constantly. This data can be used to further train an LLM model, which protects the application from new failure modes and reputational risk. Like any software, LLM models are constantly improving. Smarter and faster models are open-sourced all the time. For a new model to get deployed to production, it must first be finetuned on the specific dataset of the organization building the application. Fine-tuning does not add latency to LLM applications. Rather than a solution that sits in the middle of the LLM and the rest of the application, fine-tuning leverages the power of the LLM itself to increase the quality of the output. In fact, fine-tuning allows for shorter system prompts, which speeds up the average response generation time.

How a founder built a B2B AI startup to serve with 65+ global brands (including Fortune500 companies) (I will not promote)

AI Palette is an AI-driven platform that helps food and beverage companies predict emerging product trends. I had the opportunity recently to sit down with the founder to get his advice on building an AI-first startup, which he'll be going through in this post. (I will not promote) About AI Palette: Co-founders: >!2 (Somsubhra GanChoudhuri, Himanshu Upreti)!!100+!!$12.7M USD!!AI-powered predictive analytics for the CPG (Consumer Packaged Goods) industry!!Signed first paying customer in the first year!!65+ global brands, including Cargill, Diageo, Ajinomoto, Symrise, Mondelez, and L’Oréal, use AI Palette!!Every new product launched has secured a paying client within months!!Expanded into Beauty & Personal Care (BPC), onboarding one of India’s largest BPC companies within weeks!!Launched multiple new product lines in the last two years, creating a unified suite for brand innovation!Identify the pain points in your industry for ideas* When I was working in the flavour and fragrance industry, I noticed a major issue CPG companies faced: launching a product took at least one to two years. For instance, if a company decided today to launch a new juice, it wouldn’t hit the market until 2027. This long timeline made it difficult to stay relevant and on top of trends. Another big problem I noticed was that companies relied heavily on market research to determine what products to launch. While this might work for current consumer preferences, it was highly inefficient since the product wouldn’t actually reach the market for several years. By the time the product launched, the consumer trends had already shifted, making that research outdated. That’s where AI can play a crucial role. Instead of looking at what consumers like today, we realised that companies should use AI to predict what they will want next. This allows businesses to create products that are ahead of the curve. Right now, the failure rate for new product launches is alarmingly high, with 8 out of 10 products failing. By leveraging AI, companies can avoid wasting resources on products that won’t succeed, leading to better, more successful launches. Start by talking to as many industry experts as possible to identify the real problems When we first had the idea for AI Palette, it was just a hunch, a gut feeling—we had no idea whether people would actually pay for it. To validate the idea, we reached out to as many people as we could within the industry. Since our focus area was all about consumer insights, we spoke to professionals in the CPG sector, particularly those in the insights departments of CPG companies. Through these early conversations, we began to see a common pattern emerge and identified the exact problem we wanted to solve. Don’t tell people what you’re building—listen to their frustrations and challenges first. Going into these early customer conversations, our goal was to listen and understand their challenges without telling them what we were trying to build. This is crucial as it ensures that you can gather as much data about the problem to truly understand it and that you aren't biasing their answers by showing your solution. This process helped us in two key ways: First, it validated that there was a real problem in the industry through the number of people who spoke about experiencing the same problem. Second, it allowed us to understand the exact scale and depth of the problem—e.g., how much money companies were spending on consumer research, what kind of tools they were currently using, etc. Narrow down your focus to a small, actionable area to solve initially. Once we were certain that there was a clear problem worth solving, we didn’t try to tackle everything at once. As a small team of two people, we started by focusing on a specific area of the problem—something big enough to matter but small enough for us to handle. Then, we approached customers with a potential solution and asked them for feedback. We learnt that our solution seemed promising, but we wanted to validate it further. If customers are willing to pay you for the solution, it’s a strong validation signal for market demand. One of our early customer interviewees even asked us to deliver the solution, which we did manually at first. We used machine learning models to analyse the data and presented the results in a slide deck. They paid us for the work, which was a critical moment. It meant we had something with real potential, and we had customers willing to pay us before we had even built the full product. This was the key validation that we needed. By the time we were ready to build the product, we had already gathered crucial insights from our early customers. We understood the specific information they wanted and how they wanted the results to be presented. This input was invaluable in shaping the development of our final product. Building & Product Development Start with a simple concept/design to validate with customers before building When we realised the problem and solution, we began by designing the product, but not by jumping straight into coding. Instead, we created wireframes and user interfaces using tools like InVision and Figma. This allowed us to visually represent the product without the need for backend or frontend development at first. The goal was to showcase how the product would look and feel, helping potential customers understand its value before we even started building. We showed these designs to potential customers and asked for feedback. Would they want to buy this product? Would they pay for it? We didn’t dive into actual development until we found a customer willing to pay a significant amount for the solution. This approach helped us ensure we were on the right track and didn’t waste time or resources building something customers didn’t actually want. Deliver your solution using a manual consulting approach before developing an automated product Initially, we solved problems for customers in a more "consulting" manner, delivering insights manually. Recall how I mentioned that when one of our early customer interviewees asked us to deliver the solution, we initially did it manually by using machine learning models to analyse the data and presenting the results to them in a slide deck. This works for the initial stages of validating your solution, as you don't want to invest too much time into building a full-blown MVP before understanding the exact features and functionalities that your users want. However, after confirming that customers were willing to pay for what we provided, we moved forward with actual product development. This shift from a manual service to product development was key to scaling in a sustainable manner, as our building was guided by real-world feedback and insights rather than intuition. Let ongoing customer feedback drive iteration and the product roadmap Once we built the first version of the product, it was basic, solving only one problem. But as we worked closely with customers, they requested additional features and functionalities to make it more useful. As a result, we continued to evolve the product to handle more complex use cases, gradually developing new modules based on customer feedback. Product development is a continuous process. Our early customers pushed us to expand features and modules, from solving just 20% of their problems to tackling 50–60% of their needs. These demands shaped our product roadmap and guided the development of new features, ultimately resulting in a more complete solution. Revenue and user numbers are key metrics for assessing product-market fit. However, critical mass varies across industries Product-market fit (PMF) can often be gauged by looking at the size of your revenue and the number of customers you're serving. Once you've reached a certain critical mass of customers, you can usually tell that you're starting to hit product-market fit. However, this critical mass varies by industry and the type of customers you're targeting. For example, if you're building an app for a broad consumer market, you may need thousands of users. But for enterprise software, product-market fit may be reached with just a few dozen key customers. Compare customer engagement and retention with other available solutions on the market for product-market fit Revenue and the number of customers alone isn't always enough to determine if you're reaching product-market fit. The type of customer and the use case for your product also matter. The level of engagement with your product—how much time users are spending on the platform—is also an important metric to track. The more time they spend, the more likely it is that your product is meeting a crucial need. Another way to evaluate product-market fit is by assessing retention, i.e whether users are returning to your platform and relying on it consistently, as compared to other solutions available. That's another key indication that your solution is gaining traction in the market. Business Model & Monetisation Prioritise scalability Initially, we started with a consulting-type model where we tailor-made specific solutions for each customer use-case we encountered and delivered the CPG insights manually, but we soon realized that this wasn't scalable. The problem with consulting is that you need to do the same work repeatedly for every new project, which requires a large team to handle the workload. That is not how you sustain a high-growth startup. To solve this, we focused on building a product that would address the most common problems faced by our customers. Once built, this product could be sold to thousands of customers without significant overheads, making the business scalable. With this in mind, we decided on a SaaS (Software as a Service) business model. The benefit of SaaS is that once you create the software, you can sell it to many customers without adding extra overhead. This results in a business with higher margins, where the same product can serve many customers simultaneously, making it much more efficient than the consulting model. Adopt a predictable, simplistic business model for efficiency. Look to industry practices for guidance When it came to monetisation, we considered the needs of our CPG customers, who I knew from experience were already accustomed to paying annual subscriptions for sales databases and other software services. We decided to adopt the same model and charge our customers an annual upfront fee. This model worked well for our target market, aligning with industry standards and ensuring stable, recurring revenue. Moreover, our target CPG customers were already used to this business model and didn't have to choose from a huge variety of payment options, making closing sales a straightforward and efficient process. Marketing & Sales Educate the market to position yourself as a thought leader When we started, AI was not widely understood, especially in the CPG industry. We had to create awareness around both AI and its potential value. Our strategy focused on educating potential users and customers about AI, its relevance, and why they should invest in it. This education was crucial to the success of our marketing efforts. To establish credibility, we adopted a thought leadership approach. We wrote blogs on the importance of AI and how it could solve problems for CPG companies. We also participated in events and conferences to demonstrate our expertise in applying AI to the industry. This helped us build our brand and reputation as leaders in the AI space for CPG, and word-of-mouth spread as customers recognized us as the go-to company for AI solutions. It’s tempting for startups to offer products for free in the hopes of gaining early traction with customers, but this approach doesn't work in the long run. Free offerings don’t establish the value of your product, and customers may not take them seriously. You should always charge for pilots, even if the fee is minimal, to ensure that the customer is serious about potentially working with you, and that they are committed and engaged with the product. Pilots/POCs/Demos should aim to give a "flavour" of what you can deliver A paid pilot/POC trial also gives you the opportunity to provide a “flavour” of what your product can deliver, helping to build confidence and trust with the client. It allows customers to experience a detailed preview of what your product can do, which builds anticipation and desire for the full functionality. During this phase, ensure your product is built to give them a taste of the value you can provide, which sets the stage for a broader, more impactful adoption down the line. Fundraising & Financial Management Leverage PR to generate inbound interest from VCs When it comes to fundraising, our approach was fairly traditional—we reached out to VCs and used connections from existing investors to make introductions. However, looking back, one thing that really helped us build momentum during our fundraising process was getting featured in Tech in Asia. This wasn’t planned; it just so happened that Tech in Asia was doing a series on AI startups in Southeast Asia and they reached out to us for an article. During the interview, they asked if we were fundraising, and we mentioned that we were. As a result, several VCs we hadn’t yet contacted reached out to us. This inbound interest was incredibly valuable, and we found it far more effective than our outbound efforts. So, if you can, try to generate some PR attention—it can help create inbound interest from VCs, and that interest is typically much stronger and more promising than any outbound strategies because they've gone out of their way to reach out to you. Be well-prepared and deliberate about fundraising. Keep trying and don't lose heart When pitching to VCs, it’s crucial to be thoroughly prepared, as you typically only get one shot at making an impression. If you mess up, it’s unlikely they’ll give you a second chance. You need to have key metrics at your fingertips, especially if you're running a SaaS company. Be ready to answer questions like: What’s your retention rate? What are your projections for the year? How much will you close? What’s your average contract value? These numbers should be at the top of your mind. Additionally, fundraising should be treated as a structured process, not something you do on the side while juggling other tasks. When you start, create a clear plan: identify 20 VCs to reach out to each week. By planning ahead, you’ll maintain momentum and speed up the process. Fundraising can be exhausting and disheartening, especially when you face multiple rejections. Remember, you just need one investor to say yes to make it all worthwhile. When using funds, prioritise profitability and grow only when necessary. Don't rely on funding to survive. In the past, the common advice for startups was to raise money, burn through it quickly, and use it to boost revenue numbers, even if that meant operating at a loss. The idea was that profitability wasn’t the main focus, and the goal was to show rapid growth for the next funding round. However, times have changed, especially with the shift from “funding summer” to “funding winter.” My advice now is to aim for profitability as soon as possible and grow only when it's truly needed. For example, it’s tempting to hire a large team when you have substantial funds in the bank, but ask yourself: Do you really need 10 new hires, or could you get by with just four? Growing too quickly can lead to unnecessary expenses, so focus on reaching profitability as soon as possible, rather than just inflating your team or burn rate. The key takeaway is to spend your funds wisely and only when absolutely necessary to reach profitability. You want to avoid becoming dependent on future VC investments to keep your company afloat. Instead, prioritize reaching break-even as quickly as you can, so you're not reliant on external funding to survive in the long run. Team-Building & Leadership Look for complementary skill sets in co-founders When choosing a co-founder, it’s important to find someone with a complementary skill set, not just someone you’re close to. For example, I come from a business and commercial background, so I needed someone with technical expertise. That’s when I found my co-founder, Himanshu, who had experience in machine learning and AI. He was a great match because his technical knowledge complemented my business skills, and together we formed a strong team. It might seem natural to choose your best friend as your co-founder, but this can often lead to conflict. Chances are, you and your best friend share similar interests, skills, and backgrounds, which doesn’t bring diversity to the table. If both of you come from the same industry or have the same strengths, you may end up butting heads on how things should be done. Having diverse skill sets helps avoid this and fosters a more collaborative working relationship. Himanshu (left) and Somsubhra (right) co-founded AI Palette in 2018 Define roles clearly to prevent co-founder conflict To avoid conflict, it’s essential that your roles as co-founders are clearly defined from the beginning. If your co-founder and you have distinct responsibilities, there is no room for overlap or disagreement. This ensures that both of you can work without stepping on each other's toes, and there’s mutual respect for each other’s expertise. This is another reason as to why it helps to have a co-founder with a complementary skillset to yours. Not only is having similar industry backgrounds and skillsets not particularly useful when building out your startup, it's also more likely to lead to conflicts since you both have similar subject expertise. On the other hand, if your co-founder is an expert in something that you're not, you're less likely to argue with them about their decisions regarding that aspect of the business and vice versa when it comes to your decisions. Look for employees who are driven by your mission, not salary For early-stage startups, the first hires are crucial. These employees need to be highly motivated and excited about the mission. Since the salary will likely be low and the work demanding, they must be driven by something beyond just the paycheck. The right employees are the swash-buckling pirates and romantics, i.e those who are genuinely passionate about the startup’s vision and want to be part of something impactful beyond material gains. When employees are motivated by the mission, they are more likely to stick around and help take the startup to greater heights. A litmus test for hiring: Would you be excited to work with them on a Sunday? One of the most important rounds in the hiring process is the culture fit round. This is where you assess whether a candidate shares the same values as you and your team. A key question to ask yourself is: "Would I be excited to work with this person on a Sunday?" If there’s any doubt about your answer, it’s likely not a good fit. The idea is that you want employees who align with the company's culture and values and who you would enjoy collaborating with even outside of regular work hours. How we structure the team at AI Palette We have three broad functions in our organization. The first two are the big ones: Technical Team – This is the core of our product and technology. This team is responsible for product development and incorporating customer feedback into improving the technology Commercial Team – This includes sales, marketing, customer service, account managers, and so on, handling everything related to business growth and customer relations. General and Administrative Team – This smaller team supports functions like finance, HR, and administration. As with almost all businesses, we have teams that address the two core tasks of building (technical team) and selling (commercial team), but given the size we're at now, having the administrative team helps smoothen operations. Set broad goals but let your teams decide on execution What I've done is recruit highly skilled people who don't need me to micromanage them on a day-to-day basis. They're experts in their roles, and as Steve Jobs said, when you hire the right person, you don't have to tell them what to do—they understand the purpose and tell you what to do. So, my job as the CEO is to set the broader goals for them, review the plans they have to achieve those goals, and periodically check in on progress. For example, if our broad goal is to meet a certain revenue target, I break it down across teams: For the sales team, I’ll look at how they plan to hit that target—how many customers they need to sell to, how many salespeople they need, and what tactics and strategies they plan to use. For the technical team, I’ll evaluate our product offerings—whether they think we need to build new products to attract more customers, and whether they think it's scalable for the number of customers we plan to serve. This way, the entire organization's tasks are cascaded in alignment with our overarching goals, with me setting the direction and leaving the details of execution to the skilled team members that I hire.

I studied how 7 Founders found their first 100 customers for their businesses. Summarizing it here!

I am learning marketing, and so I combed through the internet to find specific advice that helped founders reach 100 users and not random Google answers. Here’s what I found: Llama Life by Marie Marie founder of Llama Life, a productivity app ($51.4K+ revenue) got her first 100 users using Snowballing effect. She shared great advice that I want to add here verbatim, “Need to think about what you have that you can leverage based on your current situation. eg..When you have no customers, think about where you can post to get the 1st customer eg Product Hunt. If you do well on PH, say you get #3 product of the day, then you post somewhere else saying ‘I got #3 product of the day’.. to get your next few customers. Maybe that post is on reddit with some learnings that you found. If the reddit post does well, then you might post it on Twitter, saying reddit did well and what learnings you got from that etc. or even if it doesn’t do well you can still post about it.” Another tip she shared is to build related products that get more viral than the product itself. These are small stand-alone sites that would appeal to the same target audience, but by nature, are more shareable. On these sites, you can mention your startup like: ‘brought to you by Llama Life’ and then provide a link to the main website if someone is interested. If one of those gets viral or ranks on Google, you’ll have a passive traffic source. Scraping bee by Pierre Pierre, founder of Scraping Bee, a web scraping tool has now reached $1.5M ARR. Pierre and his cofounder Kevin started with 10 Free Beta Users in 2019, and after 6 months asked them to take a paid subscription if they wanted to continue using the product. That’s how they got their first user within 50 minutes of that email. Then they listed it on dozens of startup directories but their core strategy was writing the best possible content for their target audience — Developers. 3 very successful pieces of content that worked were : A small tutorial on how to scrape single-page application An extensive general guide about web scraping without getting blocked A complete introduction to web scraping with Python They didn’t do content marketing for the sake of content marketing but deep-dived into the value they were providing their customer. One of these got 70K visits, and all this together got them to over 100 users. WePay by Bill Clerico Bill Clerico left his cushy corporate job to build WePay which was then acquired for $400M got his first users by using his app. He got his first users by using his app! The app was for group payments. So he hosted a Poker tournament at his house and collected payments only with his app. Then they hosted a barbecue for fraternity treasurers at San Jose State & helped them do their annual dues collection. Good old word-of-mouth marketing, that however, started with an event where they used what they made! RealWorld by Genevieve Genevieve — Founder and CEO of Realworld stands by the old-school advice of value giving. RealWorld is an app that helps GenZ navigate adulthood. So, before launching their direct-to-consumer platform, they had an educational course that they sold to college career centers and students. They already had a pipeline of adults who turned to Realworld for their adulting challenges. From there, she gained her first 100 followers. Saner dot ai by Austin Austin got 100 users from Reddit for his startup Saner.ai. Reddit hates advertising, and so his tips to market your startup on Reddit is to Write value-driven posts on your niche. Instead of writing posts, find posts where people are looking for solutions DM people facing problems that your SaaS solves. But instead of selling, ask about their problem to see if your product is a good fit Heartfelt posts about why you built it, aren’t gonna cut it To find posts and people, search Reddit with relevant keywords and join all the subreddits A Stock Portfolio Newsletter A financial investor got his first 100 paid newsletter subscribers for his stock portfolio newsletter. His tips : Don’t reinvent the wheel. Work what’s already working. He saw a company making $500M+ from stock picking newsletter, so decided to try that. Find the gaps in “already working” and leverage them. That newsletter did not have portfolios of advisors writing them. That was his USP. He added his own portfolio to his newsletter. Now to 100 users, he partnered with a guy running an investing website and getting good traffic. That guy got a cut of his revenue, in exchange. That one simple step got him to 100 users. Hypefury by Yannick and Samy Yannick and Samy from Hypefury, Twitter and Social Media Automation tool got their first beta testers and users from a paid community. They launched Hypefury there and asked if someone wanted to try it. A couple of people tried it and gave feedback. Samy conducted user interviews and product demos for them, And shared the reviews on Twitter. That alone, along with word-of-mouth marketing on Twitter got them their first 100 users. To conclude: Don’t reinvent the wheel, try what’s working. Find the gaps in what’s working, and leverage that. Instead of thinking about millions of customers, think about the first 10. Then first 100. Leverage what you have. Get the first 10 customers, then talk about this to get the next 100. Use your app. Find ways, events, and opportunities to use your app in front of people. And get them to use it. Write content not only for SEO but also to help people. It won’t work tomorrow, but it will work for years after it picks up. Leverage other sources of traffic by partnering up! Do things that don’t scale. I’m also doing SaaS marketing deep dives over 30 pieces of content. I'm posting here for the first time, so I'm not sure if it will stay or not, sorry if it doesn't. I've helped a SaaS grow from $19K to $100K MRR as a marketer in last 2 years, and now I wanna dive deep. Cheers! (1/30)

Joined an AI Startup with Ex-ShipStation Team - Need Tips on Finding Early Users

Hey Reddit, My name’s Welcome (Yes, that’s really my name), and I’ve been in tech for most of my career, mostly at bigger companies with established brands and resources. But recently, I decided to join a small startup called BotDojo. It’s my first time being part of a small team, and it’s been a pretty eye-opening experience so far. But, like with anything new, I’ve hit a few bumps along the way, and I’m hoping you all might have some advice. A little backstory: BotDojo was started by some of the engineers who used to work together at ShipStation. After ShipStation sold, they spent some time experimenting with AI but kept running into the same problems—having to patch together tools, getting inconsistent results, handling data ingestion, and struggling to track performance. So, they decided to build a platform to help developers build, test, and deploy AI solutions. Since I came on board, my focus has been on finding early users, and it’s been a mixed bag of wins and frustrations. We’ve got a solid group of people using the free version (which is great), but only a few have upgraded to the paid plan so far (ranging from startups to large enterprises). The cool thing is that those who have become paying customers absolutely love the product. It’s just been hard getting more people to that point. We’ve tried a bunch of things: Attending industry events, doing cold email outreach, running social ads (the usual stuff). And while we’ve seen some interest, we’re running into a few challenges:   Learning curve: The software is really powerful, but it takes a week or two for users to really see what it can do. Without a dedicated sales team to walk them through it, it’s been tough getting people to stick around long enough to see the value. Standing out is hard: The AI space is super crowded right now. I think a lot of people see “AI tool” and assume it’s just like everything else out there (even though BotDojo has some awesome features that really set it apart).  Sign-ups, but limited engagement: We’re on a freemium model to make it easy for people to try it out, but that also means we get a lot of bots and people who sign up but don’t really dive in. So, I thought I’d reach out here and see if anyone has been through this early stage before. How did you manage to break through and find those first paying users who really saw the value in what you were building?  Are there any strategies, communities, or tactics that worked particularly well for you? And if you had to do it all over again, what would you focus on? I figure I’m not the only one trying to navigate these waters, so I’m hoping this can be a helpful thread for others too. Thanks so much for reading, and I’d be super grateful for any advice or insights you can share! 🙏

I studied how 7 Founders found their first 100 customers for their businesses. Summarizing it here!

I am learning marketing, and so I combed through the internet to find specific advice that helped founders reach 100 users and not random Google answers. Here’s what I found: Llama Life by Marie Marie founder of Llama Life, a productivity app ($51.4K+ revenue) got her first 100 users using Snowballing effect. She shared great advice that I want to add here verbatim, “Need to think about what you have that you can leverage based on your current situation. eg..When you have no customers, think about where you can post to get the 1st customer eg Product Hunt. If you do well on PH, say you get #3 product of the day, then you post somewhere else saying ‘I got #3 product of the day’.. to get your next few customers. Maybe that post is on reddit with some learnings that you found. If the reddit post does well, then you might post it on Twitter, saying reddit did well and what learnings you got from that etc. or even if it doesn’t do well you can still post about it.” Another tip she shared is to build related products that get more viral than the product itself. These are small stand-alone sites that would appeal to the same target audience, but by nature, are more shareable. On these sites, you can mention your startup like: ‘brought to you by Llama Life’ and then provide a link to the main website if someone is interested. If one of those gets viral or ranks on Google, you’ll have a passive traffic source. Scraping bee by Pierre Pierre, founder of Scraping Bee, a web scraping tool has now reached $1.5M ARR. Pierre and his cofounder Kevin started with 10 Free Beta Users in 2019, and after 6 months asked them to take a paid subscription if they wanted to continue using the product. That’s how they got their first user within 50 minutes of that email. Then they listed it on dozens of startup directories but their core strategy was writing the best possible content for their target audience — Developers. 3 very successful pieces of content that worked were : A small tutorial on how to scrape single-page application An extensive general guide about web scraping without getting blocked A complete introduction to web scraping with Python They didn’t do content marketing for the sake of content marketing but deep-dived into the value they were providing their customer. One of these got 70K visits, and all this together got them to over 100 users. WePay by Bill Clerico Bill Clerico left his cushy corporate job to build WePay which was then acquired for $400M got his first users by using his app. He got his first users by using his app! The app was for group payments. So he hosted a Poker tournament at his house and collected payments only with his app. Then they hosted a barbecue for fraternity treasurers at San Jose State & helped them do their annual dues collection. Good old word-of-mouth marketing, that however, started with an event where they used what they made! RealWorld by Genevieve Genevieve — Founder and CEO of Realworld stands by the old-school advice of value giving. RealWorld is an app that helps GenZ navigate adulthood. So, before launching their direct-to-consumer platform, they had an educational course that they sold to college career centers and students. They already had a pipeline of adults who turned to Realworld for their adulting challenges. From there, she gained her first 100 followers. Saner dot ai by Austin Austin got 100 users from Reddit for his startup Saner.ai. Reddit hates advertising, and so his tips to market your startup on Reddit is to Write value-driven posts on your niche. Instead of writing posts, find posts where people are looking for solutions DM people facing problems that your SaaS solves. But instead of selling, ask about their problem to see if your product is a good fit Heartfelt posts about why you built it, aren’t gonna cut it To find posts and people, search Reddit with relevant keywords and join all the subreddits A Stock Portfolio Newsletter A financial investor got his first 100 paid newsletter subscribers for his stock portfolio newsletter. His tips : Don’t reinvent the wheel. Work what’s already working. He saw a company making $500M+ from stock picking newsletter, so decided to try that. Find the gaps in “already working” and leverage them. That newsletter did not have portfolios of advisors writing them. That was his USP. He added his own portfolio to his newsletter. Now to 100 users, he partnered with a guy running an investing website and getting good traffic. That guy got a cut of his revenue, in exchange. That one simple step got him to 100 users. Hypefury by Yannick and Samy Yannick and Samy from Hypefury, Twitter and Social Media Automation tool got their first beta testers and users from a paid community. They launched Hypefury there and asked if someone wanted to try it. A couple of people tried it and gave feedback. Samy conducted user interviews and product demos for them, And shared the reviews on Twitter. That alone, along with word-of-mouth marketing on Twitter got them their first 100 users. To conclude: Don’t reinvent the wheel, try what’s working. Find the gaps in what’s working, and leverage that. Instead of thinking about millions of customers, think about the first 10. Then first 100. Leverage what you have. Get the first 10 customers, then talk about this to get the next 100. Use your app. Find ways, events, and opportunities to use your app in front of people. And get them to use it. Write content not only for SEO but also to help people. It won’t work tomorrow, but it will work for years after it picks up. Leverage other sources of traffic by partnering up! Do things that don’t scale. I’m also doing SaaS marketing deep dives over 30 pieces of content. I'm posting here for the first time, so I'm not sure if it will stay or not, sorry if it doesn't. I've helped a SaaS grow from $19K to $100K MRR as a marketer in last 2 years, and now I wanna dive deep. Cheers! (1/30)

No revenue for 6 months, then signed $10k MRR in 2 weeks with a new strategy. Here’s what I changed.

This is my first company so I made A LOT of mistakes when starting out. I'll explain everything I did that worked so you don't have to waste your time either. For context, I built a SaaS tool that helps companies scale their new client outreach 10x (at human quality with AI) so they can secure more sales meetings. Pricing I started out pricing it way too low (1/10 as much as competitors) so that it'd be easier to get customers in the beginning. This is a HUGE mistake and wasted me a bunch of time. First, this low pricing meant that I was unable to pay for the tools I needed to make sure my product could be great. I was forced to use low-quality databases, AI models, sending infrastructure -- you name it. Second, my customers were less invested in the product, and I received less input from them to make the product better. None ended up converting from my free trial because my product sucked, and I couldn't even get good feedback from them. I decided to price my product much higher, which allowed me to use best-in class tools to make my product actually work well. Outreach Approach The only issue is that it's a lot harder to get people to pay $500/month than $50/month. I watched every single video on the internet about cold email for getting B2B clients and built up an outbound MACHINE for sending thousands of emails a day. I tried all the top recommended sales email formats and tricks (intro, painpoint, testimonial, CTA, etc). Nothing. I could send 1k emails and get a few out of office responses and a handful of 'F off' responses. I felt bad and decided I couldn't just spam the entire world and expect to make any progress. I decided I needed to take a step back and learn from people who'd succeeded before in sales. I started manually emailing CEOs/founders that fit my customer profile with personal messages asking for feedback on my product -- not even trying to sell them anything. Suddenly I was getting 4-6 meetings a day and just trying to learn from them (turns out people love helping others). And without even prompting, many of them said 'hey, I actually could use this for my own sales' and asked how they could start trying it out. That week I signed 5 clients between $500-$4k/month (depending how many contacts they want to reach). I then taught my product to do outreach the same way I did that worked (include company signals, make sure the person is a great match with web research, and DONT TALK SALESY). Now, 6 of my first 10 clients (still figuring out who it works for, lol) have converted from the free trial and successfully used it to book sales meetings. I'm definitely still learning, but this one change in my sales approach changed everything for me, so I wanted to share. If anyone has any other tips/advice that changed their business's sales, would love to hear!

Looking to Connect with Healthcare Tech Founders & Early-Stage Startups(Product, AI Strategy – Canada-based, Open to US). I will not promote.

Hey everyone, I’m exploring product and strategy roles in healthcare tech startups and looking to connect with early-stage founders working on AI-driven healthcare solutions. I’m currently based in Canada but looking for opportunities to work with U.S.-based startups in healthcare AI, digital health, and automation. My background is in tech, compliance, and cybersecurity, and I’m transitioning into product management for AI healthcare solutions. I’ve been working on a portfolio of AI-powered healthcare projects, including: A senior care digital assistant (health tracking, reminders) An AI companion for men's health (preventative care & chronic disease management) More projects coming in preventative health and healthcare automation I’m interested in learning from and working with fast-moving startups, particularly those at the intersection of AI and healthcare. If you’re working on something exciting, I’d love to chat. Drop a comment or DM me if you’re interested in connecting!

I just had my best month after 18 months as a solopreneur

Last month I reached important milestones both financially (60+ sales) and in terms of my personal brand (2.500+ new followers) But the most important part is that it has reinforced a belief in myself: it is possible, as long as I keep going, improving, learning and iterating. For the last year and a half, I've been grinding and launching project after project. But there was always something wrong: Product didn't solve a real problem Bad marketing (very often lol) Target market had low purchasing power Super-competitive niche (usually b2c) It's difficult to have failure after failure and keep going on. At times it would feel like everyone was making money, except for me. I was hacking on my projects every single day before and after my 9-5 and had mostly given up all my free time for this. But results were far from being what I wanted. So I would doubt myself all the time. One thing I had going for me is that I really enjoy building things - so that helped me a lot in staying consistent. I always knew this was a long-term thing and that I'd probably have to fail again and again before seeing some success. But even so, it was really hard to keep up the spirits at all time, especially after working so hard for so long. I wasn't going to give up but I also knew that continuing like this would lead nowhere. So I decided that for my next project I would do 2 things: 1) prioritize marketing and 2) build something strategic 1) Prioritize marketing I decided I was going to put in the same amount of effort into marketing as I put into building. Usually my time would be split 90% coding - 10% marketing. Now, for the first time ever it's probably 65% coding - 35% marketing. I organized myself and made an entire gameplan for it. This forced me to learn a lot about: Video editing Cold emails Copywriting Running ads Short-form content There are a lot of items I still need to execute on - but at least I have a good idea of how to approach most things. 2) Build something strategic I had to build something that I would be able to use even if nobody else did. For the last year and a half I had been building AI apps and my plan was to continue doing that. So I decided to leverage that and thought about how I could build something that would give me an unfair advantage + have a compounding effect over the long term: a) Unfair advantage Having AI demo apps that cover all type of AI functionalities would make my life easier & would allow me to ship new apps quickly, regardless of the required model/functionality So even if nobody bought this - I'd have built something really useful for myself & would have a slight edge over other people b) Compound over the long term Building "AnotherWrapper' (my new project) would have a good synergy with my future projects: It would allow me to build new projects faster While building new projects, I'd learn new things, which I would then be able to implement into AnotherWrapper and improve the product that way A win-win. Closing thoughts I did not expect things to go this well - it's been an amazing month and I'm truly grateful to everyone that has been supporting me. But at the end of the day, there is still a lot of work to be done. The initial 'hype' & effects from some viral tweets are starting to wear off. I still don't have a reliable distribution channel that guarantees me traffic. So I need to figure that out. I think the product has a lot of potential - it has been well received and has been a success so far, but my distribution is still lacking. The good thing is that I now have some extra cash to spend on things like ads, influencers, freelancers etc. So it opens some new doors that were previously closed! I also have some other projects down the pipeline which are coming soon. Will keep you guys updated!

Building in the open with Founder University - I will not promote

Published Oct 30, 2024 I am on my fifth startup. I ran the last one for a decade, that’s a whole story. A hell of a story. But a different story. I’ll tell it to you when I can, but not right now. The one before that was an e-commerce site that did pretty well but I didn’t love it. Before that were two service businesses. The first one I did for the love of the game, the second one was an attempt to make people stop asking me to fix their computer by charging them outrageous prices, which backfired horribly when they were eager to pay. None are relevant except to say I’ve been around the block and have the scars to prove it. When it was time to get back out there, I wanted to use all I’ve learned to do better. Before I talk about what those lessons produced, I’m going to talk about what those lessons were. Cause before effect, after all. One thing I wanted to do better this time was pattern matching - making the startup look the way that the industry and investors “expect” a startup to look. My last startup was an awesome idea with awesome tech (still is, but like I said, another story), but that one didn’t match patterns. It didn’t match investor patterns, industry buying patterns, patterns of existing, immediate, recognized and admitted needs. Because it didn’t “look” right to anyone, everything about it was way harder than necessary. The “make it look right” approach runs the risk of building a cargo cult, imitating the trappings of something but without understanding the essence of that something, but then again, a thing that looks like a knife is going to make a better knife that a thing that looks like a bowling ball, so sometimes just sharing apparent similarities can get you pretty far, even if it doesn’t get you all the way there. Like how mimicking someone’s accent makes it easier for them to understand you. For this one, I wanted to adopt every tool, method, and pattern that I knew “the industry” wanted to see to minimize the friction from development, go-to-market, scaling, adoption, and that would make investment optional (and, therefore, available if desired) instead of necessary (and, therefore, largely unavailable). That required establishing some expectations for successful patterns I could match against. What patterns am I matching to? Here’s a general sketch of my pattern matching thought process: Software first and software only. It’s the easiest industry to start a business in, lowest startup costs, and easiest customer acquisition. I wanted to build software for an element of the industry that’s actively emerging (and therefore has room to grow) and part of an optimistic investor thesis (and therefore has a cohort of people who are intent on injecting capital into the market to help it grow). It needs to fills a niche that is underexplored (low competition) and highly potent (lots of opportunity), while being aligned to recognized and emerging needs within the industry (readily adopted). I wanted it to have evidence supporting the business thesis that proves the demand exists, but demonstrates that the demand is unanswered (as of yet) by sufficient or adequate supply.* I wanted the lowest number of dominoes to line up and tip for everything to work correctly - the more dominoes in the line, the less likely the last one will fall. I wanted to implement modern toolsets for everything, wherever possible. I wanted to obey the maxim, “When there’s a gold rush, don’t mine the gold, sell the picks and shovels.” Whatever I chose would need to produce cash flow almost immediately with minimal development time or go-to-market delays, because the end of ZIRP killed the “trust me bro” investment thesis predominant over the last 15 years. I wanted to match to YC best practices, not because YC can predict what will definitely work, but because they’ve churned through so many startups in the last 15 years that they have a good sense of what will definitely not work. And I wanted to build client-centric, because if my intent is to to produce cash flow immediately, we need to get clients immediately, and if we need to get clients immediately, we need to focus on what clients need right now. Extra credit: What’s the difference between a customer and a client? Note: Competition is awesome! Competition is validating and not scary, because competition proves a market exists. But competition, especially mature competition against an immature startup, makes it harder to break into a space. A first mover advantage isn’t everything, but seeing demand before it’s sufficiently supplied is a great advantage if you’re capital constrained or otherwise unproven. Think about how much money the first guy to sell fidget spinners or Silly Bandz made versus how much money the last guy to order a pallet of each made. Finding demand that exists already but is as of yet insufficiently satisfied is a great place to start. What opportunity spaces are most relevant? The industries and markets I chose to observe were: AI, because if I’m following a theme & pattern for today, it’s AI. Fintech, because cash is king, and fintech puts your hands on cash flow. Crypto/blockchain, because that’s the “new” fintech (or maybe the “old-new” fintech?), and crypto creates powerful incentives and capital formation strategies, along with a lot of flexibility for transaction systems. Tools, particularly unmet demand in tools, that enable these industries. If you wanted to do some brief and simple homework, you could map each of those bullets to several of the numbered list items preceding them. The reasoning was pretty simplistic - AI is what people want to build and invest in now, while fintech and crypto/blockchain are what people were building and investing in for the last major investment thesis. That means that there’s demand in the market for AI and AI-adjacent startups, while there’s a glut of underutilized and highly developed tools within fintech and crypto/blockchain, with a lot of motivated capital behind the adoption. When someone is thinking “I built this thing and not enough people are using it”, and you then build something that uses it creates a great way to find allies. This rationale harnesses technology that is being built and financed now (which means it needs tools and support methods, and a lot of other “picks and shovels”), while leveraging technology that was recently built and financed and is eager for more widespread adoption of the existing toolkits, which makes it suitable for using to build the AI-adjacent tools that are in demand now. It’s like two harmonics producing constructive interference - it makes two waves into one larger wave, which gives me more momentum to surf against. This was a learning process, and I iterated against my general paradigm repeatedly as I learned more. Neither of us have the patience to go through that in excruciating detail, so I’ll cover the highlights in my next post. Extra credit answer: A customer gets a product, a client gets a service. Challenge: Is software a product or a service?

From “Green” to “Smart” – Tom Gorski’s Word of Advice

Sharing this interview with entrepreneur Tom Gorski. I think it contains a few nice tips for beginner entrepreneurs. What is the problem with the term “Green?” what are the top 3 mistakes entrepreneurs make that can prevent them from enjoying the sweet taste of success? And what should young entrepreneurs always keep in mind? Continuing our expert interview series, we asked entrepreneur Tom Gorski to share some of his secrets to success with us. Gorski is the CEO and Co-Founder at SaaSGenius.com, and an Inbound Marketer & Growth Hacker at InboundWay.com. His career spans over 12 years of developing and implementing online marketing, SEO and conversion optimization campaigns. He defines his biggest accomplishment to date as “achieving 4500% growth for one of my clients over a three­year period.” logo-saasgenius Q: It’s no secret that the SaaS market is saturated, as new companies are having very hard time acquiring, retaining and monetizing users. In your view – what are the top 3 mistakes SaaS companies make? What are some key differentiators you recognize in a successful product? A: Mistake No. 1: Product-market fit is not good enough There are a number of reasons for this, including the fact that inertia, incumbency and bureaucracy are all working against you. For emerging companies, this means finding a way to be exponentially better with fewer resources. As a result, focus is key. Mistake No. 2: Not Specializing Your Sales Roles When you specialize your sales people, you allow them to focus, which creates greater output form your sales team. Mistake No. 3: You Need a Niche To be able to market and sell well, you need to have a niche. The world is noisy and messy, and you’ll struggle if you don’t have a sharp, direct message. When you try to speak to everyone, no one can hear you. Q: Which innovative trends do you recognize in the high tech world nowadays? A: “Green” was a mega trend of the last decade and while it will continue to be very important, there will be a shift towards “smart” solutions, which are intelligent, connected and have the ability to sense, report, and take the right action. Smart solutions will be everywhere around us from smart clothing, phones, to smart homes and smart cities. Q: What is the most significant advice you can give young entrepreneurs? A: Being very successful means learning from those who have already achieved success. Having a mentor is an amazing blessing to an entrepreneur, but not everyone can find one in person. My advice is to work smarter, not harder. This is the most non-intuitive observation I will probably make. If you want to compete in the arena, hard work isn’t enough. And judging yourself on how hard you work, rather than how smart you work can be fatal. Q: We are flooded with buzzwords lately – VR / AI / Bots… where do you think the software world is heading? A: AI and bots are a very hot topic in 2016 and it’s sometimes hard to distinguish the real potential behind the hype. My point of view is that, like with many things, there’s no revolution but evolution. It’s unrealistic to think that AI can become mainstream in SaaS products without proper AI infrastructure. SaaS delivery will significantly outpace traditional software product delivery, growing nearly five times faster than the traditional software market and will become a significant growth driver for all functional software markets. By 2019, the SaaS software model will account for $1 of every $4 spent on software. Q: Let us in on some of your secrets… where do you look for innovation? For inspiration and revolutionary ideas? A: Ideas for new startups often begin with a real problem that needs to be solved. And they don’t come while you’re sitting around sipping coffee and contemplating life. They tend to reveal themselves while you’re at work on something else. Start with brainstorming with problems that you are personally invested in. Building a business is hard and takes the kind of relentless dedication that comes from personal passion. Perhaps the greatest factor that determines whether or not an entrepreneur will be successful isn’t the business idea itself, but rather the entrepreneur’s willingness to try to turn the idea into reality. Great ideas are abundant, but it’s what we decide to do with them that counts. Original post: http://saasaddict.walkme.com/from-green-to-smart-tom-gorskis-words-of-advice/

New to Startups; Where do I start?

I have an idea for an specialized AI based software system in a particular market that I think, if done well, could be a very helpful and lucrative software/AI (both for its owners as well as its users). It hasn't been properly implemented into any form that I or my associates have been able to find and I believe that now is the perfect time to start its development. I'm an entrepreneur, have started several successful companies over the years and am well experienced in all things business. But, none of my companies have involved creating a brand new product or would fall into the "Startup" category. It's a whole new world to me. That being said, I'm not sure what the proper steps are to make this idea come to fruition and am hoping for a point in the right direction. How do people usually go from idea to launch? I imagine there are 2 distinct things I need right now, funding for the project and a partner to help create the software. Step 1 would be the partner. For this partner, I'm not sure where to start to find this person. I'd imagine I need someone that's experienced in machine learning, AI engineering, software development, programming, etc. Or a combination of people with those skills. Since none of my companies are startup or tech based, I don't have connections to anyone with those skills. If I go around looking for a partner with those skills, I'll surely need to explain my idea to them and will need to be able to protect my idea before hand. Do I copyright it? Make them sign an NDA? What's common business practice? Where do I go to look for a partner with those skills? For funding, I can fund the initial stages of the project for a handful of months. From there, I'd like to find some kind of investment. But that sounds like a bridge to cross when I get further down that road. Looking forward to starting down this road and hopefully making something that benefits and pushes forward this new world of AI!

I spent 6 months on building a tool, and got 0 zero users. Here is my story.

Edit Thank you all so much for your time reading my story. Your support, feedback, criticism, and skepticism; all helped me a lot, and I couldn't appreciate it enough \^\_\^ TL;DR I spent 6 months on a tool that currently has 0 users. Below is what I learned during my journey, sharing because I believe most mistakes are easily avoidable. Do not overestimate your product and assume it will be an exception to fundamental principles. Principles are there for a reason. Always look for validation before you start. Avoid building products with a low money-to-effort ratio/in very competitive fields. Unless you have the means, you probably won't make it. Pick a problem space, pick your target audience, and talk to them before thinking about a solution. Identify and match their pain points. Only then should you think of a solution. If people are not overly excited or willing to pay in advance for a discounted price, it might be a sign to rethink. Sell one and only one feature at a time. Avoid everything else. If people don't pay for that one core feature, no secondary feature will change their mind. Always spend twice as much time marketing as you do building. You will not get users if they don't know it exists. Define success metrics ("1000 users in 3 months" or "$6000 in the account at the end of 6 months") before you start. If you don't meet them, strongly consider quitting the project. If you can't get enough users to keep going, nothing else matters. VALIDATION, VALIDATION, VALIDATION. Success is not random, but most of our first products will not make a success story. Know when to admit failure, and move on. Even if a product of yours doesn't succeed, what you learned during its journey will turn out to be invaluable for your future. My story So, this is the story of a product, Summ, that I’ve been working on for the last 6 months. As it's the first product I’ve ever built, after watching you all from the sidelines, I have learned a lot, made many mistakes, and did only a few things right. Just sharing what I’ve learned and some insights from my journey so far. I hope that this post will help you avoid the mistakes I made — most of which I consider easily avoidable — while you enjoy reading it, and get to know me a little bit more 🤓. A slow start after many years Summ isn’t the first product I really wanted to build. Lacking enough dev skills to even get started was a huge blocker for so many years. In fact, the first product I would’ve LOVED to build was a smart personal shopping assistant. I had this idea 4 years ago; but with no GPT, no coding skills, no technical co-founder, I didn’t have the means to make it happen. I still do not know if such a tool exists and is good enough. All I wanted was a tool that could make data-based predictions about when to buy stuff (“buy a new toothpaste every three months”) and suggest physical products that I might need or be strongly interested in. AFAIK, Amazon famously still struggles with the second one. Fast-forward a few years, I learned the very basics of HTML, CSS, and Vanilla JS. Still was not there to build a product; but good enough to code my design portfolio from scratch. Yet, I couldn’t imagine myself building a product using Vanilla JS. I really hated it, I really sucked at it. So, back to tutorial hell, and to learn about this framework I just heard about: React.React introduced so many new concepts to me. “Thinking in React” is a phrase we heard a lot, and with quite good reasons. After some time, I was able to build very basic tutorial apps, both in React, and React Native; but I have to say that I really hated coding for mobile. At this point, I was already a fan of productivity apps, and had a concept for a time management assistant app in my design portfolio. So, why not build one? Surely, it must be easy, since every coding tutorial starts with a todo app. ❌ WRONG! Building a basic todo app is easy enough, but building one good enough for a place in the market was a challenge I took and failed. I wasted one month on that until I abandoned the project for good. Even if I continued working on it, as the productivity landscape is overly competitive, I wouldn’t be able to make enough money to cover costs, assuming I make any. Since I was (and still am) in between jobs, I decided to abandon the project. 👉 What I learned: Do not start projects with a low ratio of money to effort and time. Example: Even if I get 500 monthly users, 200 of which are paid users (unrealistically high number), assuming an average subscription fee of $5/m (such apps are quite cheap, mostly due to the high competition), it would make me around $1000 minus any occurring costs. Any founder with a product that has 500 active users should make more. Even if it was relatively successful, due to the high competition, I wouldn’t make any meaningful money. PS: I use Todoist today. Due to local pricing, I pay less than $2/m. There is no way I could beat this competitive pricing, let alone the app itself. But, somehow, with a project that wasn’t even functional — let alone being an MVP — I made my first Wi-Fi money: Someone decided that the domain I preemptively purchased is worth something. By this point, I had already abandoned the project, certainly wasn’t going to renew the domain, was looking for a FT job, and a new project that I could work on. And out of nowhere, someone hands me some free money — who am I not to take it? Of course, I took it. The domain is still unused, no idea why 🤔. Ngl, I still hate the fact that my first Wi-Fi money came from this. A new idea worth pursuing? Fast-forward some weeks now. Around March, I got this crazy idea of building an email productivity tool. We all use emails, yet we all hate them. So, this must be fixed. Everyone uses emails, in fact everyone HAS TO use emails. So, I just needed to build a tool and wait for people to come. This was all, really. After all, the problem space is huge, there is enough room for another product, everyone uses emails, no need for any further validation, right? ❌ WRONG ONCE AGAIN! We all hear from the greatest in the startup landscape that we must validate our ideas with real people, yet at least some of us (guilty here 🥸) think that our product will be hugely successful and prove them to be an exception. Few might, but most are not. I certainly wasn't. 👉 Lesson learned: Always validate your ideas with real people. Ask them how much they’d pay for such a tool (not if they would). Much better if they are willing to pay upfront for a discount, etc. But even this comes later, keep reading. I think the difference between “How much” and “If” is huge for two reasons: (1) By asking them for “How much”, you force them to think in a more realistic setting. (2) You will have a more realistic idea on your profit margins. Based on my competitive analysis, I already had a solution in my mind to improve our email usage standards and email productivity (huge mistake), but I did my best to learn about their problems regarding those without pushing the idea too hard. The idea is this: Generate concise email summaries with suggested actions, combine them into one email, and send it at their preferred times. Save as much as time the AI you end up with allows. After all, everyone loves to save time. So, what kind of validation did I seek for? Talked with only a few people around me about this crazy, internet-breaking idea. The responses I got were, now I see, mediocre; no one got excited about it, just said things along the lines of “Cool idea, OK”. So, any reasonable person in this situation would think “Okay, not might not be working”, right? Well, I did not. I assumed that they were the wrong audience for this product, and there was this magical land of user segments waiting eagerly for my product, yet unknowingly. To this day, I still have not reached this magical place. Perhaps, it didn’t exist in the first place. If I cannot find it, whether it exists or not doesn’t matter. I am certainly searching for it. 👉 What I should have done: Once I decide on a problem space (time management, email productivity, etc.), I should decide on my potential user segments, people who I plan to sell my product to. Then I should go talk to those people, ask them about their pains, then get to the problem-solving/ideation phase only later. ❗️ VALIDATION COMES FROM THE REALITY OUTSIDE. What validation looks like might change from product to product; but what invalidation looks like is more or less the same for every product. Nico Jeannen told me yesterday “validation = money in the account” on Twitter. This is the ultimate form of validation your product could get. If your product doesn’t make any money, then something is invalidated by reality: Your product, you, your idea, who knows? So, at this point, I knew a little bit of Python from spending some time in tutorial hell a few years ago, some HTML/CSS/JS, barely enough React to build a working app. React could work for this project, but I needed easy-to-implement server interactivity. Luckily, around this time, I got to know about this new gen of indie hackers, and learned (but didn’t truly understand) about their approach to indie hacking, and this library called Nextjs. How good Next.js still blows my mind. So, I was back to tutorial hell once again. But, this time, with a promise to myself: This is the last time I would visit tutorial hell. Time to start building this "ground-breaking idea" Learning the fundamentals of Next.js was easier than learning of React unsurprisingly. Yet, the first time I managed to run server actions on Next.js was one of the rarest moments that completely blew my mind. To this day, I reject the idea that it is something else than pure magic under its hood. Did I absolutely need Nextjs for this project though? I do not think so. Did it save me lots of time? Absolutely. Furthermore, learning Nextjs will certainly be quite helpful for other projects that I will be tackling in the future. Already got a few ideas that might be worth pursuing in the head in case I decide to abandon Summ in the future. Fast-forward few weeks again: So, at this stage, I had a barely working MVP-like product. Since the very beginning, I spent every free hour (and more) on this project as speed is essential. But, I am not so sure it was worth it to overwork in retrospect. Yet, I know I couldn’t help myself. Everything is going kinda smooth, so what’s the worst thing that could ever happen? Well, both Apple and Google announced their AIs (Apple Intelligence and Google Gemini, respectively) will have email summarization features for their products. Summarizing singular emails is no big deal, after all there were already so many similar products in the market. I still think that what truly matters is a frictionless user experience, and this is why I built this product in a certain way: You spend less than a few minutes setting up your account, and you get to enjoy your email summaries, without ever visiting its website again. This is still a very cool concept I really like a lot. So, at this point: I had no other idea that could be pursued, already spent too much time on this project. Do I quit or not? This was the question. Of course not. I just have to launch this product as quickly as possible. So, I did something right, a quite rare occurrence I might say: Re-planned my product, dropped everything secondary to the core feature immediately (save time on reading emails), tried launching it asap. 👉 Insight: Sell only one core feature at one time. Drop anything secondary to this core feature. Well, my primary occupation is product design. So one would expect that a product I build must have stellar design. I considered any considerable time spent on design at this stage would be simply wasted. I still think this is both true and wrong: True, because if your product’s core benefits suck, no one will care about your design. False, because if your design looks amateurish, no one will trust you and your product. So, I always targeted an average level design with it and the way this tool works made it quite easy as I had to design only 2 primary pages: Landing page and user portal (which has only settings and analytics pages). However, even though I knew spending time on design was not worth much of my time, I got a bit “greedy”: In fact, I redesigned those pages three times, and still ended up with a so-so design that I am not proud of. 👉 What I would do differently: Unless absolutely necessary, only one iteration per stage as long as it works. This, in my mind, applies to everything. If your product’s A feature works, then no need to rewrite it from scratch for any reason, or even refactor it. When your product becomes a success, and you absolutely need that part of your codebase to be written, do so, but only then. Ready to launch, now is th etime for some marketing, right? By July 26, I already had a “launchable” product that barely works (I marked this date on a Notion docs, this is how I know). Yet, I had spent almost no time on marketing, sales, whatever. After all, “You build and they will come”. Did I know that I needed marketing? Of course I did, but knowingly didn’t. Why, you might ask. Well, from my perspective, it had to be a dev-heavy product; meaning that you spend most of your time on developing it, mostly coding skills. But, this is simply wrong. As a rule of thumb, as noted by one of the greatests, Marc Louvion, you should spend at least twice of the building time on marketing. ❗️ Time spent on building \* 2 people don’t know your product > they don’t use your product > you don’t get users > you don’t make money Easy as that. Following the same reasoning, a slightly different approach to planning a project is possible. Determine an approximate time to complete the project with a high level project plan. Let’s say 6 months. By the reasoning above, 2 months should go into building, and 4 into marketing. If you need 4 months for building instead of 2, then you need 8 months of marketing, which makes the time to complete the project 12 months. If you don’t have that much time, then quit the project. When does a project count as completed? Well, in reality, never. But, I think we have to define success conditions even before we start for indie projects and startups; so we know when to quit when they are not met. A success condition could look like “Make $6000 in 12 months” or “Have 3000 users in 6 months”. It all depends on the project. But, once you set it, it should be set in stone: You don’t change it unless absolutely necessary. I suspect there are few principles that make a solopreneur successful; and knowing when to quit and when to continue is definitely one of them. Marc Louvion is famously known for his success, but he got there after failing so many projects. To my knowledge, the same applies to Nico Jeannen, Pieter Levels, or almost everyone as well. ❗️ Determining when to continue even before you start will definitely help in the long run. A half-aed launch Time-leap again. Around mid August, I “soft launched” my product. By soft launch, I mean lazy marketing. Just tweeting about it, posting it on free directories. Did I get any traffic? Surely I did. Did I get any users? Nope. Only after this time, it hit me: “Either something is wrong with me, or with this product” Marketing might be a much bigger factor for a project’s success after all. Even though I get some traffic, not convincing enough for people to sign up even for a free trial. The product was still perfect in my eyes at the time (well, still is ^(\_),) so the right people are not finding my product, I thought. Then, a question that I should have been asking at the very first place, one that could prevent all these, comes to my mind: “How do even people search for such tools?” If we are to consider this whole journey of me and my so-far-failed product to be an already destined failure, one metric suffices to show why. Search volume: 30. Even if people have such a pain point, they are not looking for email summaries. So, almost no organic traffic coming from Google. But, as a person who did zero marketing on this or any product, who has zero marketing knowledge, who doesn’t have an audience on social media, there is not much I could do. Finally, it was time to give up. Or not… In my eyes, the most important element that makes a founder (solo or not) successful (this, I am not by any means) is to solve problems. ❗️ So, the problem was this: “People are not finding my product by organic search” How do I make sure I get some organic traffic and gets more visibility? Learn digital marketing and SEO as much as I can within very limited time. Thankfully, without spending much time, I came across Neil Patel's YT channel, and as I said many times, it is an absolute gold mine. I learned a lot, especially about the fundamentals, and surely it will be fruitful; but there is no magic trick that could make people visit your website. SEO certainly helps, but only when people are looking for your keywords. However, it is truly a magical solution to get in touch with REAL people that are in your user segments: 👉 Understand your pains, understand their problems, help them to solve them via building products. I did not do this so far, have to admit. But, in case you would like to have a chat about your email usage, and email productivity, just get in touch; I’d be delighted to hear about them. Getting ready for a ProductHunt launch The date was Sept 1. And I unlocked an impossible achievement: Running out of Supabase’s free plan’s Egres limit while having zero users. I was already considering moving out of their Cloud server and managing a Supabase CLI service on my Hetzner VPS for some time; but never ever suspected that I would have to do this quickly. The cheapest plan Supabase offers is $25/month; yet, at that point, I am in between jobs for such a long time, basically broke, and could barely afford that price. One or two months could be okay, but why pay for it if I will eventually move out of their Cloud service? So, instead of paying $25, I spent two days migrating out of Supabase Cloud. Worth my time? Definitely not. But, when you are broke, you gotta do stupid things. This was the first time that I felt lucky to have zero users: I have no idea how I would manage this migration if I had any. I think this is one of the core tenets of an indie hacker: Controlling their own environment. I can’t remember whose quote this is, but I suspect it was Naval: Entrepreneurs have an almost pathological need to control their own fate. They will take any suffering if they can be in charge of their destiny, and not have it in somebody else’s hands. What’s truly scary is, at least in my case, we make people around us suffer at the expense of our attempting to control our own fates. I know this period has been quite hard on my wife as well, as I neglected her quite a bit, but sadly, I know that this will happen again. It is something that I can barely help with. Still, so sorry. After working the last two weeks on a ProductHunt Launch, I finally launched it this Tuesday. Zero ranking, zero new users, but 36 kind people upvoted my product, and many commented and provided invaluable feedback. I couldn't be more grateful for each one of them 🙏. Considering all these, what lies in the future of Summ though? I have no idea, to be honest. On one hand, I have zero users, have no job, no income. So, I need a way to make money asap. On the other hand, the whole idea of it revolves around one core premise (not an assumption) that I am not so willing to share; and I couldn’t have more trust in it. This might not be the best iteration of it, however I certainly believe that email usage is one of the best problem spaces one could work on. 👉 But, one thing is for certain: I need to get in touch with people, and talk with them about this product I built so far. In fact, this is the only item on my agenda. Nothing else will save my brainchild <3. Below are some other insights and notes that I got during my journey; as they do not 100% fit into this story, I think it is more suitable to list them here. I hope you enjoyed reading this. Give Summ a try, it comes with a generous free trial, no credit card required. Some additional notes and insights: Project planning is one of the most underestimated skills for solopreneurs. It saves you enormous time, and helps you to keep your focus up. Building B2C products beats building B2B products. Businesses are very willing to pay big bucks if your product helps them. On the other hand, spending a few hours per user who would pay $5/m probably is not worth your time. It doesn’t matter how brilliant your product is if no one uses it. If you cannot sell a product in a certain category/niche (or do not know how to sell it), it might be a good idea not to start a project in it. Going after new ideas and ventures is quite risky, especially if you don’t know how to market it. On the other hand, an already established category means that there is already demand. Whether this demand is sufficient or not is another issue. As long as there is enough demand for your product to fit in, any category/niche is good. Some might be better, some might be worse. Unless you are going hardcore B2B, you will need people to find your product by means of organic search. Always conduct thorough keyword research as soon as possible.

Technical entrepreneur looking for next team

Hi everyone, I'm a 10+ year veteran software developer with a proven track record of building consumer-facing products (shipped 10+ projects, 5 for consumers). However, I'm not looking to build another consumer facing product (we all know how difficult that is) unless you have the network and funds. I'm gearing up for my next venture and searching for the perfect co-pilot (or two!) with equal splits. -- Here's the skinny: You (ideal): Experienced (ideally with at least one failed project under your belt - learning is key!) Ready to grind and U.S based. Titles are meaningless - passion and hustle matter most. Are tired of tarpit ideas (dating app, fitness app, etc.) Bonus Points: Another technical co-founder to build magic with. Non-technical rockstars with skills in customer acquisition, fundraising, or deep industry knowledge. -- Please send me a DM! Let's chat and see if we can build something together. -- Full disclosure: I did use AI to write some of these because I'm not super great at writing these out

Looking for a technical cofounder with experience in building websites and marketplaces

Are you passionate about revolutionizing traditional processes? Do you have the expertise to build scalable platforms and want to be part of something transformative? I’m a second-year Economics student at the University of Warwick with a deep drive for creating impactful solutions. I’m seeking a technical co-founder to join me in building a startup dedicated to transforming how startups hire entry-level talent. About the Project I’m developing a recruitment marketplace that connects early-stage and growing startups with talented students and graduates. Our goal is to streamline the hiring process, making it hassle-free for startups while creating meaningful career opportunities for the next generation of talent. What I’m Looking For in a Technical Co-Founder I need someone who can complement my non-technical skills and help take this project to the next level. The ideal co-founder will have: A strong background in programming online marketplace platforms. Experience managing large databases efficiently. Knowledge in machine learning and AI, with a vision to integrate these in future features. Skills in scaling online platforms for a larger audience. The ability to work in synergy with me to shape and execute the vision. A passion for the idea—I’m happy to share more details in a meeting! Key responsibilities will include platform development, handling backend work, deploying the MVP, aiding in design, and collaborating on product iterations. About Me I bring experience in business strategy, operations, finance, product/project management, marketing, and sales—essentially, I cover everything except the technical aspects of development. I previously worked on a social communication platform for school students during high school. I also gained valuable experience as a business analyst in another startup. Why Join me? This is an exciting opportunity to build a product from the ground up, make an impact in the startup ecosystem, and grow alongside a venture poised to redefine hiring. We need: A seamless MVP launch. Networking efforts to onboard startups and expand our reach. Together, we can create something transformative, fostering innovation and enabling career growth for students while helping startups find the talent they need to succeed. If you’re excited about the prospect of building something revolutionary and have the technical skills to complement my business acumen, I’d love to connect. Let’s discuss how we can work together to create the next generation of hiring solutions. Please DM if you are interested in getting to know more about this project! Looking forward

Non-technical founders with experienced outside vendor — ok?

I’m a non-technical cofounder of early stage startup. (“Non-technical” but I’ve developed multimedia courseware and led teams in the past (LMS, edu content, no code). My question: how crucial is it that my other biz founder and I have a technical co-founder for our data- and AI-driven product rather than use an experienced vendor whose team has been doing machine learning and AI for 10 years? During our manual work as consultants we have identified a problem in a niche market that can be solved via a combo of hard-to-gather data and AI (and other market-specific stuff that that we will train our LLM on). We’ve done market research, designed and validated the solution with potential customers in numerous interviews via click-through prototypes/wireframes, quantified TAM, SAM, SOM, written biz plan, etc. We have deep experience in our market having proven expertise over years. But as we’ve been learning about fundraising (we hope to begin a seed round in early 2025) we continually hear about the importance of technical cofounder. We get it— but our product will only be half-developed by a technical dev team. The other aspect to the product is: gathering hard to find data, and figuring out relationships in the data — that we will do via mapping work with a cohort with unique expertise in our niche market. Also our outside vendor is very reputable with years’ experience in AI and machine learning prior to the latest gen-AI craze — he’s not a newbie and has an established dev team. And our platform is not a consumer product but a more complicated SaaS product. Like, you can’t just code it by yourself. Sure, in the long run we can hire/bring everything in house, but would investors shy away from working with us if our short-term dev effort does not have a “technical” co-founder? Thanks for your thoughts.

Experienced Software Developer looking for startup to help. I will not promote

My passion for programming started at the age of 9 when I began playing video games. It was during this time that I first dived into programming, creating scripts for SA:MP (San Andreas Multiplayer) using the Pawn language. SA:MP is a modification for the popular game Grand Theft Auto: San Andreas, allowing players to experience multiplayer gameplay. My early experiences in programming were all about problem-solving—finding ways to enhance the game and improve the player experience. This was when I realized how satisfying it is to solve a problem through code, and that feeling has stayed with me throughout my career. I am a self-taught programmer, and everything I know today comes from my own initiative to learn and improve. After five years of working with local clients, I decided to expand my knowledge and started learning more widely applicable programming languages like Java and Python. I’ve always been the type of person who thrives on challenges. Whenever I encounter a problem, I don’t just look for a quick fix—I dive deep into researching and understanding the problem, and I find a solution that works in the long run. This is what drives me. The ability to solve problems, no matter how complex, and the satisfaction that comes with it is what fuels my passion for programming. My big break came when I had the opportunity to work at \\\\. There, I replaced two senior and two junior developers, which led to significant cost savings for the company. I completed all tasks ahead of schedule, focusing on Java-based applications that were multithreaded and communicated with embedded systems. This experience taught me how to work under pressure and how to manage and solve complex technical problems efficiently. Following my time at \\\\, I transitioned into freelance work as a FullStack Developer, working with technologies such as HTML, CSS, Bootstrap, JavaScript, Django, Spring, MySQL, and PostgreSQL. As a freelancer, I was responsible for finding solutions to a wide range of problems, often working independently and making decisions on the fly. I learned that self-reliance is key in this industry, and being resourceful is one of the most important qualities a developer can have. Later, I joined \\\\ elecom, where I worked on system integration with foreign teams, BPM process solutions, and the merging of complex systems in Oracle databases. I continued to solve challenges, often working with teams across borders and tackling technical obstacles that required creative and well-thought-out solutions. Eventually, I founded my own company, \\\\, where I focus on developing software solutions, Artificial Intelligence (AI), Cybersecurity, and Ethical Hacking. As an entrepreneur, I take pride in finding innovative solutions to problems, whether they come from clients or from technical obstacles I encounter along the way. I’ve also had the privilege of working with the Serbian Ministry of Defense and the police, handling sensitive projects that demand both technical expertise and trustworthiness. Being a self-taught programmer means that I have had to learn and adapt on my own, and I’ve learned to embrace challenges as opportunities for growth. I am constantly driven by the process of solving problems, and it is what keeps me engaged and fulfilled in my work. I am always open to new collaborations and am eager to take on new challenges that push my boundaries in technology, cybersecurity, and software development.

Finally Launched My First App Without Any Coding Experience

About Myself I am a structural engineer that are taught to design buildings in the day and I have been dreaming forever to build a SaaS business to get out of the rat race. However, as a structural engineer, coding is definitely not something I am capable of doing (I have some simple knowledge, but its no way close to building an app) The Journey As I've mentioned, I always wanted to build a SaaS business because in my mind the business model is most attractive to me, where you only need to build once and can sell to millions. So I started off searching and exploring on the internet and my first ever "SaaS" was from Wordpress. I am buying plugin from other user and then pluggin into my own Wordpress website. It was a project management tool SaaS. I was so excited about the website and can't even sleep well at night because I'm just so hype about it. But, the reality is because this is my first ever business, I totally didn't realise about the importance of UI UX or my business differentiation, thinking that everyone will be as excited as I am. Then, I went deeper and deeper into the journey (I can write more about this in another post if anyone is interested) and finally landed on Flutterflow to create my first ever app. No Code Journey Thanks to no code builder, I never thought that a non-coder like me can ever create an app and got accepted by the App Store/Play Store. Since that I am using a low-code builder, for any specific requirement that I need that are not covered natively, I will just talk to ChatGPT and boom I pretty much got most of the answer I needed. About The App As someone that always try to keep track of my expenses, I never able to find an app that are simple and interesting enough for me to continue on the journey. I realise that I could have incorporate AI into this journey and hence there go, I created an AI Money Tracker. Let me introduce Rolly: AI Money Tracker - a new AI expense tracker where you can easily record your transactions just by chatting with our bot Rolly and it will automatically record and categorise the transaction into the most suitable category (you can also create any of your own category and it will also take care of it in consideration). I am not sharing the app link here to avoid getting ban, but feel free to search up Rolly: AI Money Tracker on either App Store on Play Store. My Learnings As someone that can't code and never imagine that I could create a production app by myself and publish it on to the App Store and Play Store. Since I am not making any money yet and just at the beginning of my entrepreneur journey, I can't give any substantial advice, all I can say is just my own learnings and feelings. My advice is if you have a dream of building a business, just go for it, don't worry about all the problems that you can think of to convince yourself not making the start at all. From my point of view, as long as you're not giving up everything (eg, putting yourself in huge debt etc), why don't just go for it and you've got nothing much to lose. You'll only lose if you never even get started. And also, I believe that creating an app is always the easiest step out of the entreprenuership journey, marketing and distribution is the key to success. Even though you've spent days and nights on it and it might mean everything to you, the truth is people don't really cares and you'll need to market for it. I am still in journey to learn how to do marketing, content, building a business and everything. I think this is just a very beginning of my journey and hopefully there's more interesting one to share further down the road.

How do I, as a Data Scientist, get familiar with the business knowledge and jargon I need to start my AI startup and sell my product?

Here’s my situation: I'm a Data Scientist working on an MVP, almost ready to launch, called Attendify. It simplifies the attendance process in schools—no more teachers calling out names and sending records to principals. Instead, teachers create an account, upload student images, and start a live camera feed, all through the app. The app detects students using deep learning, stores everything in a database, and automates the process. Plus, I plan to add features based on school needs and pitch it directly to them. Now, I’m looking to establish a proper AI startup with a website and digital presence, but I'm lacking in business knowledge, especially the lingo like "B2B" and other terms. My goal is to be a sole founder with an online workforce. Can anyone recommend a cost-effective course (maybe on Coursera) that covers the basics I need to know to effectively talk with clients and understand the business side of things? Attendify is just one of them, I might create more in the future so I'm going towards SaaS side I was thinking about Entrepreneurship Specialization by University of Pennsylvania on Coursera if anyone got any feedback on it

I spent 6 months on building a tool, and got 0 zero users. Here is my story.

Edit Thank you all so much for your time reading my story. Your support, feedback, criticism, and skepticism; all helped me a lot, and I couldn't appreciate it enough \^\_\^ TL;DR I spent 6 months on a tool that currently has 0 users. Below is what I learned during my journey, sharing because I believe most mistakes are easily avoidable. Do not overestimate your product and assume it will be an exception to fundamental principles. Principles are there for a reason. Always look for validation before you start. Avoid building products with a low money-to-effort ratio/in very competitive fields. Unless you have the means, you probably won't make it. Pick a problem space, pick your target audience, and talk to them before thinking about a solution. Identify and match their pain points. Only then should you think of a solution. If people are not overly excited or willing to pay in advance for a discounted price, it might be a sign to rethink. Sell one and only one feature at a time. Avoid everything else. If people don't pay for that one core feature, no secondary feature will change their mind. Always spend twice as much time marketing as you do building. You will not get users if they don't know it exists. Define success metrics ("1000 users in 3 months" or "$6000 in the account at the end of 6 months") before you start. If you don't meet them, strongly consider quitting the project. If you can't get enough users to keep going, nothing else matters. VALIDATION, VALIDATION, VALIDATION. Success is not random, but most of our first products will not make a success story. Know when to admit failure, and move on. Even if a product of yours doesn't succeed, what you learned during its journey will turn out to be invaluable for your future. My story So, this is the story of a product, Summ, that I’ve been working on for the last 6 months. As it's the first product I’ve ever built, after watching you all from the sidelines, I have learned a lot, made many mistakes, and did only a few things right. Just sharing what I’ve learned and some insights from my journey so far. I hope that this post will help you avoid the mistakes I made — most of which I consider easily avoidable — while you enjoy reading it, and get to know me a little bit more 🤓. A slow start after many years Summ isn’t the first product I really wanted to build. Lacking enough dev skills to even get started was a huge blocker for so many years. In fact, the first product I would’ve LOVED to build was a smart personal shopping assistant. I had this idea 4 years ago; but with no GPT, no coding skills, no technical co-founder, I didn’t have the means to make it happen. I still do not know if such a tool exists and is good enough. All I wanted was a tool that could make data-based predictions about when to buy stuff (“buy a new toothpaste every three months”) and suggest physical products that I might need or be strongly interested in. AFAIK, Amazon famously still struggles with the second one. Fast-forward a few years, I learned the very basics of HTML, CSS, and Vanilla JS. Still was not there to build a product; but good enough to code my design portfolio from scratch. Yet, I couldn’t imagine myself building a product using Vanilla JS. I really hated it, I really sucked at it. So, back to tutorial hell, and to learn about this framework I just heard about: React.React introduced so many new concepts to me. “Thinking in React” is a phrase we heard a lot, and with quite good reasons. After some time, I was able to build very basic tutorial apps, both in React, and React Native; but I have to say that I really hated coding for mobile. At this point, I was already a fan of productivity apps, and had a concept for a time management assistant app in my design portfolio. So, why not build one? Surely, it must be easy, since every coding tutorial starts with a todo app. ❌ WRONG! Building a basic todo app is easy enough, but building one good enough for a place in the market was a challenge I took and failed. I wasted one month on that until I abandoned the project for good. Even if I continued working on it, as the productivity landscape is overly competitive, I wouldn’t be able to make enough money to cover costs, assuming I make any. Since I was (and still am) in between jobs, I decided to abandon the project. 👉 What I learned: Do not start projects with a low ratio of money to effort and time. Example: Even if I get 500 monthly users, 200 of which are paid users (unrealistically high number), assuming an average subscription fee of $5/m (such apps are quite cheap, mostly due to the high competition), it would make me around $1000 minus any occurring costs. Any founder with a product that has 500 active users should make more. Even if it was relatively successful, due to the high competition, I wouldn’t make any meaningful money. PS: I use Todoist today. Due to local pricing, I pay less than $2/m. There is no way I could beat this competitive pricing, let alone the app itself. But, somehow, with a project that wasn’t even functional — let alone being an MVP — I made my first Wi-Fi money: Someone decided that the domain I preemptively purchased is worth something. By this point, I had already abandoned the project, certainly wasn’t going to renew the domain, was looking for a FT job, and a new project that I could work on. And out of nowhere, someone hands me some free money — who am I not to take it? Of course, I took it. The domain is still unused, no idea why 🤔. Ngl, I still hate the fact that my first Wi-Fi money came from this. A new idea worth pursuing? Fast-forward some weeks now. Around March, I got this crazy idea of building an email productivity tool. We all use emails, yet we all hate them. So, this must be fixed. Everyone uses emails, in fact everyone HAS TO use emails. So, I just needed to build a tool and wait for people to come. This was all, really. After all, the problem space is huge, there is enough room for another product, everyone uses emails, no need for any further validation, right? ❌ WRONG ONCE AGAIN! We all hear from the greatest in the startup landscape that we must validate our ideas with real people, yet at least some of us (guilty here 🥸) think that our product will be hugely successful and prove them to be an exception. Few might, but most are not. I certainly wasn't. 👉 Lesson learned: Always validate your ideas with real people. Ask them how much they’d pay for such a tool (not if they would). Much better if they are willing to pay upfront for a discount, etc. But even this comes later, keep reading. I think the difference between “How much” and “If” is huge for two reasons: (1) By asking them for “How much”, you force them to think in a more realistic setting. (2) You will have a more realistic idea on your profit margins. Based on my competitive analysis, I already had a solution in my mind to improve our email usage standards and email productivity (huge mistake), but I did my best to learn about their problems regarding those without pushing the idea too hard. The idea is this: Generate concise email summaries with suggested actions, combine them into one email, and send it at their preferred times. Save as much as time the AI you end up with allows. After all, everyone loves to save time. So, what kind of validation did I seek for? Talked with only a few people around me about this crazy, internet-breaking idea. The responses I got were, now I see, mediocre; no one got excited about it, just said things along the lines of “Cool idea, OK”. So, any reasonable person in this situation would think “Okay, not might not be working”, right? Well, I did not. I assumed that they were the wrong audience for this product, and there was this magical land of user segments waiting eagerly for my product, yet unknowingly. To this day, I still have not reached this magical place. Perhaps, it didn’t exist in the first place. If I cannot find it, whether it exists or not doesn’t matter. I am certainly searching for it. 👉 What I should have done: Once I decide on a problem space (time management, email productivity, etc.), I should decide on my potential user segments, people who I plan to sell my product to. Then I should go talk to those people, ask them about their pains, then get to the problem-solving/ideation phase only later. ❗️ VALIDATION COMES FROM THE REALITY OUTSIDE. What validation looks like might change from product to product; but what invalidation looks like is more or less the same for every product. Nico Jeannen told me yesterday “validation = money in the account” on Twitter. This is the ultimate form of validation your product could get. If your product doesn’t make any money, then something is invalidated by reality: Your product, you, your idea, who knows? So, at this point, I knew a little bit of Python from spending some time in tutorial hell a few years ago, some HTML/CSS/JS, barely enough React to build a working app. React could work for this project, but I needed easy-to-implement server interactivity. Luckily, around this time, I got to know about this new gen of indie hackers, and learned (but didn’t truly understand) about their approach to indie hacking, and this library called Nextjs. How good Next.js still blows my mind. So, I was back to tutorial hell once again. But, this time, with a promise to myself: This is the last time I would visit tutorial hell. Time to start building this "ground-breaking idea" Learning the fundamentals of Next.js was easier than learning of React unsurprisingly. Yet, the first time I managed to run server actions on Next.js was one of the rarest moments that completely blew my mind. To this day, I reject the idea that it is something else than pure magic under its hood. Did I absolutely need Nextjs for this project though? I do not think so. Did it save me lots of time? Absolutely. Furthermore, learning Nextjs will certainly be quite helpful for other projects that I will be tackling in the future. Already got a few ideas that might be worth pursuing in the head in case I decide to abandon Summ in the future. Fast-forward few weeks again: So, at this stage, I had a barely working MVP-like product. Since the very beginning, I spent every free hour (and more) on this project as speed is essential. But, I am not so sure it was worth it to overwork in retrospect. Yet, I know I couldn’t help myself. Everything is going kinda smooth, so what’s the worst thing that could ever happen? Well, both Apple and Google announced their AIs (Apple Intelligence and Google Gemini, respectively) will have email summarization features for their products. Summarizing singular emails is no big deal, after all there were already so many similar products in the market. I still think that what truly matters is a frictionless user experience, and this is why I built this product in a certain way: You spend less than a few minutes setting up your account, and you get to enjoy your email summaries, without ever visiting its website again. This is still a very cool concept I really like a lot. So, at this point: I had no other idea that could be pursued, already spent too much time on this project. Do I quit or not? This was the question. Of course not. I just have to launch this product as quickly as possible. So, I did something right, a quite rare occurrence I might say: Re-planned my product, dropped everything secondary to the core feature immediately (save time on reading emails), tried launching it asap. 👉 Insight: Sell only one core feature at one time. Drop anything secondary to this core feature. Well, my primary occupation is product design. So one would expect that a product I build must have stellar design. I considered any considerable time spent on design at this stage would be simply wasted. I still think this is both true and wrong: True, because if your product’s core benefits suck, no one will care about your design. False, because if your design looks amateurish, no one will trust you and your product. So, I always targeted an average level design with it and the way this tool works made it quite easy as I had to design only 2 primary pages: Landing page and user portal (which has only settings and analytics pages). However, even though I knew spending time on design was not worth much of my time, I got a bit “greedy”: In fact, I redesigned those pages three times, and still ended up with a so-so design that I am not proud of. 👉 What I would do differently: Unless absolutely necessary, only one iteration per stage as long as it works. This, in my mind, applies to everything. If your product’s A feature works, then no need to rewrite it from scratch for any reason, or even refactor it. When your product becomes a success, and you absolutely need that part of your codebase to be written, do so, but only then. Ready to launch, now is th etime for some marketing, right? By July 26, I already had a “launchable” product that barely works (I marked this date on a Notion docs, this is how I know). Yet, I had spent almost no time on marketing, sales, whatever. After all, “You build and they will come”. Did I know that I needed marketing? Of course I did, but knowingly didn’t. Why, you might ask. Well, from my perspective, it had to be a dev-heavy product; meaning that you spend most of your time on developing it, mostly coding skills. But, this is simply wrong. As a rule of thumb, as noted by one of the greatests, Marc Louvion, you should spend at least twice of the building time on marketing. ❗️ Time spent on building \* 2 people don’t know your product > they don’t use your product > you don’t get users > you don’t make money Easy as that. Following the same reasoning, a slightly different approach to planning a project is possible. Determine an approximate time to complete the project with a high level project plan. Let’s say 6 months. By the reasoning above, 2 months should go into building, and 4 into marketing. If you need 4 months for building instead of 2, then you need 8 months of marketing, which makes the time to complete the project 12 months. If you don’t have that much time, then quit the project. When does a project count as completed? Well, in reality, never. But, I think we have to define success conditions even before we start for indie projects and startups; so we know when to quit when they are not met. A success condition could look like “Make $6000 in 12 months” or “Have 3000 users in 6 months”. It all depends on the project. But, once you set it, it should be set in stone: You don’t change it unless absolutely necessary. I suspect there are few principles that make a solopreneur successful; and knowing when to quit and when to continue is definitely one of them. Marc Louvion is famously known for his success, but he got there after failing so many projects. To my knowledge, the same applies to Nico Jeannen, Pieter Levels, or almost everyone as well. ❗️ Determining when to continue even before you start will definitely help in the long run. A half-aed launch Time-leap again. Around mid August, I “soft launched” my product. By soft launch, I mean lazy marketing. Just tweeting about it, posting it on free directories. Did I get any traffic? Surely I did. Did I get any users? Nope. Only after this time, it hit me: “Either something is wrong with me, or with this product” Marketing might be a much bigger factor for a project’s success after all. Even though I get some traffic, not convincing enough for people to sign up even for a free trial. The product was still perfect in my eyes at the time (well, still is ^(\_),) so the right people are not finding my product, I thought. Then, a question that I should have been asking at the very first place, one that could prevent all these, comes to my mind: “How do even people search for such tools?” If we are to consider this whole journey of me and my so-far-failed product to be an already destined failure, one metric suffices to show why. Search volume: 30. Even if people have such a pain point, they are not looking for email summaries. So, almost no organic traffic coming from Google. But, as a person who did zero marketing on this or any product, who has zero marketing knowledge, who doesn’t have an audience on social media, there is not much I could do. Finally, it was time to give up. Or not… In my eyes, the most important element that makes a founder (solo or not) successful (this, I am not by any means) is to solve problems. ❗️ So, the problem was this: “People are not finding my product by organic search” How do I make sure I get some organic traffic and gets more visibility? Learn digital marketing and SEO as much as I can within very limited time. Thankfully, without spending much time, I came across Neil Patel's YT channel, and as I said many times, it is an absolute gold mine. I learned a lot, especially about the fundamentals, and surely it will be fruitful; but there is no magic trick that could make people visit your website. SEO certainly helps, but only when people are looking for your keywords. However, it is truly a magical solution to get in touch with REAL people that are in your user segments: 👉 Understand your pains, understand their problems, help them to solve them via building products. I did not do this so far, have to admit. But, in case you would like to have a chat about your email usage, and email productivity, just get in touch; I’d be delighted to hear about them. Getting ready for a ProductHunt launch The date was Sept 1. And I unlocked an impossible achievement: Running out of Supabase’s free plan’s Egres limit while having zero users. I was already considering moving out of their Cloud server and managing a Supabase CLI service on my Hetzner VPS for some time; but never ever suspected that I would have to do this quickly. The cheapest plan Supabase offers is $25/month; yet, at that point, I am in between jobs for such a long time, basically broke, and could barely afford that price. One or two months could be okay, but why pay for it if I will eventually move out of their Cloud service? So, instead of paying $25, I spent two days migrating out of Supabase Cloud. Worth my time? Definitely not. But, when you are broke, you gotta do stupid things. This was the first time that I felt lucky to have zero users: I have no idea how I would manage this migration if I had any. I think this is one of the core tenets of an indie hacker: Controlling their own environment. I can’t remember whose quote this is, but I suspect it was Naval: Entrepreneurs have an almost pathological need to control their own fate. They will take any suffering if they can be in charge of their destiny, and not have it in somebody else’s hands. What’s truly scary is, at least in my case, we make people around us suffer at the expense of our attempting to control our own fates. I know this period has been quite hard on my wife as well, as I neglected her quite a bit, but sadly, I know that this will happen again. It is something that I can barely help with. Still, so sorry. After working the last two weeks on a ProductHunt Launch, I finally launched it this Tuesday. Zero ranking, zero new users, but 36 kind people upvoted my product, and many commented and provided invaluable feedback. I couldn't be more grateful for each one of them 🙏. Considering all these, what lies in the future of Summ though? I have no idea, to be honest. On one hand, I have zero users, have no job, no income. So, I need a way to make money asap. On the other hand, the whole idea of it revolves around one core premise (not an assumption) that I am not so willing to share; and I couldn’t have more trust in it. This might not be the best iteration of it, however I certainly believe that email usage is one of the best problem spaces one could work on. 👉 But, one thing is for certain: I need to get in touch with people, and talk with them about this product I built so far. In fact, this is the only item on my agenda. Nothing else will save my brainchild <3. Below are some other insights and notes that I got during my journey; as they do not 100% fit into this story, I think it is more suitable to list them here. I hope you enjoyed reading this. Give Summ a try, it comes with a generous free trial, no credit card required. Some additional notes and insights: Project planning is one of the most underestimated skills for solopreneurs. It saves you enormous time, and helps you to keep your focus up. Building B2C products beats building B2B products. Businesses are very willing to pay big bucks if your product helps them. On the other hand, spending a few hours per user who would pay $5/m probably is not worth your time. It doesn’t matter how brilliant your product is if no one uses it. If you cannot sell a product in a certain category/niche (or do not know how to sell it), it might be a good idea not to start a project in it. Going after new ideas and ventures is quite risky, especially if you don’t know how to market it. On the other hand, an already established category means that there is already demand. Whether this demand is sufficient or not is another issue. As long as there is enough demand for your product to fit in, any category/niche is good. Some might be better, some might be worse. Unless you are going hardcore B2B, you will need people to find your product by means of organic search. Always conduct thorough keyword research as soon as possible.

10y of product development, 2 bankruptcies, and 1 Exit — what next? [Extended Story]

10 years of obsessive pursuit from the bottom to impressive product-market fit and exit. Bootstrapping tech products as Software Developer and 3x Startup Founder (2 bankruptcies and 1 exit). Hi everyone, your motivation has inspired me to delve deeper into my story. So, as promised to some of you, I've expanded on it a bit more, along with my brief reflections. There are many founders, product creators, and proactive individuals, I’ve read many of your crazy stories and lessons so I decided to share mine and the lessons I learned from the bottom to impressive product-market fit and exit. I've spent almost the past 10 years building tech products as a Corporate Team Leader, Senior Software Developer, Online Course Creator, Programming Tutor, Head of Development/CTO, and 3x Startup Founder (2 bankruptcies, and 1 exit). And what next? good question... A brief summary of my journey: Chapter 1: Software Developer / Team Leader / Senior Software Developer I’ve always wanted to create products that win over users’ hearts, carry value, and influence users. Ever since my school days, I’ve loved the tech part of building digital products. At the beginning of school, I started hosting servers for games, blogs and internet forums, and other things that did not require much programming knowledge. My classmates and later even over 100 people played on servers that I hosted on my home PC. Later, as the only person in school, I passed the final exam in computer science. During my computer science studies, I started my first job as a software developer. It was crazy, I was spending 200–300 hours a month in the office attending also to daily classes. Yes, I didn’t have a life, but it truly was the fulfillment of my dreams. I was able to earn good money doing what I love, and I devoted fully myself to it. My key to effectively studying IT and growing my knowledge at rocket speed was learning day by day reading guides, building products to the portfolio, watching youtube channels and attending conferences, and even watching them online, even if I didn’t understand everything at the beginning. In one year we’ve been to every possible event within 400km. We were building healthcare products that were actually used in hospitals and medical facilities. It was a beautiful adventure and tons of knowledge I took from this place. That time I built my first product teams, hired many great people, and over the years became a senior developer and team leader. Even I convinced my study mates to apply to this company and we studied together and worked as well. Finally, there were 4 of us, when I left a friend of mine took over my position and still works there. If you’re reading this, I’m sending you a flood of love and appreciation. I joined as the 8th person, and after around 4 years, when I left hungry for change, there were already over 30 of us, now around 100. It was a good time, greetings to everyone. I finished my Master’s and Engineering degrees in Computer Science, and it was time for changes. Chapter 2: 1st time as a Co-founder — Marketplace In the meantime, there was also my first startup (a marketplace) with four of my friends. We all worked on the product, each of us spent thousands of hours, after hours, entire weekends… and I think finally over a year of work. As you might guess, we lacked the most important things: sales, marketing, and product-market fit. We thought users think like us. We all also worked commercially, so the work went very smoothly, but we didn’t know what we should do next with it… Finally, we didn’t have any customers, but you know what, I don’t regret it, a lot of learning things which I used many times later. The first attempts at validating the idea with the market and business activities. In the end, the product was Airbnb-sized. Landing pages, listings, user panels, customer panels, admin site, notifications, caches, queues, load balancing, and much more. We wanted to publish the fully ready product to the market. It was a marketplace, so if you can guess, we had to attract both sides to be valuable. “Marketplace” — You can imagine something like Uber, if you don’t have passengers it was difficult to convince taxi drivers, if you don’t have a large number of taxi drivers you cannot attract passengers. After a year of development, we were overloaded, and without business, marketing, sales knowledge, and budget. Chapter 3: Corp Team Lead / Programming Tutor / Programming Architecture Workshop Leader Working in a corporation, a totally different environment, an international fintech, another learning experience, large products, and workmates who were waiting for 5 pm to finish — it wasn’t for me. Very slow product development, huge hierarchy, being an ant at the bottom, and low impact on the final product. At that time I understood that being a software developer is not anything special and I compared my work to factory worker. Sorry for that. High rates have been pumped only by high demand. Friends of mine from another industry do more difficult things and have a bigger responsibility for lower rates. That’s how the market works. This lower responsibility time allowed for building the first online course after hours, my own course platform, individual teaching newbies programming, and my first huge success — my first B2C customers, and B2B clients for workshops. I pivoted to full focus on sales, marketing, funnels, advertisements, demand, understanding the market, etc. It was 10x easier than startups but allowed me to learn and validate my conceptions and ideas on an easier market and showed me that it’s much easier to locate their problem/need/want and create a service/product that responds to it than to convince people of your innovative ideas. It’s just supply and demand, such a simple and basic statement, in reality, is very deep and difficult to understand without personal experience. If you’re inexperienced and you think you understand, you don’t. To this day, I love to analyze this catchword in relation to various industries / services / products and rediscover it again and again... While writing this sentence, I’m wondering if I’m not obsessed. Chapter 4: Next try — 2nd time as a founder — Edtech Drawing upon my experiences in selling services, offering trainings, and teaching programming, I wanted to broaden my horizons, delve into various fields of knowledge, involve more teachers, and so on. We started with simple services in different fields of knowledge, mainly relying on teaching in the local area (without online lessons). As I had already gathered some knowledge and experience in marketing and sales, things were going well and were moving in the right direction. The number of teachers in various fields was growing, as was the number of students. I don’t remember the exact statistics anymore, but it was another significant achievement that brought me a lot of satisfaction and new experiences. As you know, I’m a technology lover and couldn’t bear to look at manual processes — I wanted to automate everything: lessons, payments, invoices, customer service, etc. That’s when I hired our first developers (if you’re reading this, I’m sending you a flood of love — we spent a lot of time together and I remember it as a very fruitful and great year) and we began the process of tool and automation development. After a year we had really extended tools for students, teachers, franchise owners, etc. We had really big goals, we wanted to climb higher and higher. Maybe I wouldn’t even fully call it Startup, as the client was paying for the lessons, not for the software. But it gave us positive income, bootstrap financing, and tool development for services provided. Scaling this model was not as costless as SaaS because customer satisfaction was mainly on the side of the teacher, not the quality of the product (software). Finally, we grew to nearly 10 people and dozens of teachers, with zero external funding, and almost $50k monthly revenue. We worked very hard, day and night, and by November 2019, we were packed with clients to the brim. And as you know, that’s when the pandemic hit. It turned everything upside down by 180 degrees. Probably no one was ready for it. With a drastic drop in revenues, society started to save. Tired from the previous months, we had to work even harder. We had to reduce the team, change the model, and save what we had built. We stopped the tool’s development and sales, and with the developers, we started supporting other product teams to not fire them in difficult times. The tool worked passively for the next two years, reducing incomes month by month. With a smaller team providing programming services, we had full stability and earned more than relying only on educational services. At the peak of the pandemic, I promised myself that it was the last digital product I built… Never say never… Chapter 5: Time for fintech — Senior Software Developer / Team Lead / Head of Development I worked for small startups and companies. Building products from scratch, having a significant impact on the product, and complete fulfillment. Thousands of hours and sacrifices. This article mainly talks about startups that I built, so I don’t want to list all the companies, products, and applications that I supported as a technology consultant. These were mainly start-ups with a couple of people up to around 100 people on board. Some of the products were just a rescue mission, others were building an entire tech team. I was fully involved in all of them with the hope that we would work together for a long time, but I wasn’t the only one who made mistakes when looking for a product-market fit. One thing I fully understood: You can’t spend 8–15 hours a day writing code, managing a tech team, and still be able to help build an audience. In marketing and sales, you need to be rested and very creative to bring results and achieve further results and goals. If you have too many responsibilities related to technology, it becomes ineffective. I noticed that when I have more free time, more time to think, and more time to bounce the ball against the wall, I come up with really working marketing/sales strategies and solutions. It’s impossible when you are focused on code all day. You must know that this chapter of my life was long and has continued until now. Chapter 6: 3rd time as a founder — sold Never say never… right?\\ It was a time when the crypto market was really high and it was really trending topic. You know that I love technology right? So I cannot miss the blockchain world. I had experience in blockchain topics by learning on my own and from startups where I worked before. I was involved in crypto communities and I noticed a “starving crowd”. People who did things manually and earned money(crypto) on it.I found potential for building a small product that solves a technological problem. I said a few years before that I don’t want to start from scratch. I decided to share my observations and possibilities with my good friend. He said, “If you gonna built it, I’m in”. I couldn’t stop thinking about it. I had thought and planned every aspect of marketing and sales. And you know what. On this huge mindmap “product” was only one block. 90% of the mindmap was focused on marketing and sales. Now, writing this article, I understood what path I went from my first startup to this one. In the first (described earlier) 90% was the product, but in the last one 90% was sales and marketing. Many years later, I did this approach automatically. What has changed in my head over the years and so many mistakes? At that time, the company for which I provided services was acquired. The next day I got a thank you for my hard work and all my accounts were blocked. Life… I was shocked. We were simply replaced by their trusted technology managers. They wanted to get full control. They acted a bit unkindly, but I knew that they had all my knowledge about the product in the documentation, because I’m used to drawing everything so that in the moment of my weakness (illness, whatever) the team could handle it. That’s what solid leaders do, right? After a time, I know that these are normal procedures in financial companies, the point is that under the influence of emotions, do not do anything inappropriate. I quickly forgot about it, that I was brutally fired. All that mattered was to bring my plan to life. And it has been started, 15–20 hours a day every day. You have to believe me, getting back into the game was incredibly satisfying for me. I didn’t even know that I would be so excited. Then we also noticed that someone was starting to think about the same product as me. So the race began a game against time and the market. I assume that if you have reached this point, you are interested in product-market fit, marketing, and sales, so let me explain my assumptions to you: Product: A very very small tool that allowed you to automate proper tracking and creation of on-chain transactions. Literally, the whole app for the user was located on only three subpages. Starving Crowd: We tapped into an underserved market. The crypto market primarily operates via communities on platforms like Discord, Reddit, Twitter, Telegram, and so on. Therefore, our main strategy was directly communicating with users and demonstrating our tool. This was essentially “free marketing” (excluding the time we invested), as we did not need to invest in ads, promotional materials, or convince people about the efficacy of our tool. The community could directly observe on-chain transactions executed by our algorithms, which were processed at an exceptionally fast rate. This was something they couldn’t accomplish manually, so whenever someone conducted transactions using our algorithm, it was immediately noticeable and stirred a curiosity within the community (how did they do that!). Tests: I conducted the initial tests of the application on myself — we had already invested significantly in developing the product, but I preferred risking my own resources over that of the users. I provided the tool access to my wallet, containing 0.3ETH, and went to sleep. Upon waking up, I discovered that the transactions were successful and my wallet had grown to 0.99ETH. My excitement knew no bounds, it felt like a windfall. But, of course, there was a fair chance I could have lost it too. It worked. As we progressed, some users achieved higher results, but it largely hinged on the parameters set by them. As you can surmise, the strategy was simple — buy low, sell high. There was considerable risk involved. Churn: For those versed in marketing, the significance of repeat visitors cannot be overstated. Access to our tool was granted only after email verification and a special technique that I’d prefer to keep confidential. And this was all provided for free. While we had zero followers on social media, we saw an explosion in our email subscriber base and amassed a substantial number of users and advocates. Revenue Generation: Our product quickly gained popularity as we were effectively helping users earn — an undeniable value proposition. Now, it was time to capitalize on our efforts. We introduced a subscription model charging $300 per week or $1,000 per month — seemingly high rates, but the demand was so intense that it wasn’t an issue. Being a subscriber meant you were prioritized in the queue, ensuring you were among the first to reap benefits — thus adding more “value”. Marketing: The quality of our product and its ability to continually engage users contributed to it achieving what can best be described as viral. It was both a source of pride and astonishment to witness users sharing charts and analyses derived from our tool in forum discussions. They weren’t actively promoting our product but rather using screenshots from our application to illustrate certain aspects of the crypto world. By that stage, we had already assembled a team to assist with marketing, and programming, and to provide round-the-clock helpdesk support. Unforgettable Time: Despite the hype, my focus remained steadfast on monitoring our servers, their capacity, and speed. Considering we had only been on the market for a few weeks, we were yet to implement alerts, server scaling, etc. Our active user base spanned from Japan to the West Coast of the United States. Primarily, our application was used daily during the evenings, but considering the variety of time zones, the only time I could afford to sleep was during the evening hours in Far Eastern Europe, where we had the least users. However, someone always needed to be on guard, and as such, my phone was constantly by my side. After all, we couldn’t afford to let our users down. We found ourselves working 20 hours a day, catering to thousands of users, enduring physical fatigue, engaging in talks with VCs, and participating in conferences. Sudden Downturn: Our pinnacle was abruptly interrupted by the war in Ukraine (next macroeconomic shot straight in the face, lucky guy), a precipitous drop in cryptocurrency value, and swiftly emerging competition. By this time, there were 5–8 comparable tools had infiltrated the market. It was a challenging period as we continually stumbled upon new rivals. They immediately embarked on swift fundraising endeavors — a strategy we overlooked, which in retrospect was a mistake. Although our product was superior, the competitors’ rapid advancement and our insufficient funds for expeditious scaling posed significant challenges. Nonetheless, we made a good decision. We sold the product (exit) to competitors. The revenue from “exit” compensated for all the losses, leaving us with enough rest. We were a small team without substantial budgets for rapid development, and the risk of forming new teams without money to survive for more than 1–2 months was irresponsible. You have to believe me that this decision consumed us sleepless nights. Finally, we sold it. They turned off our app but took algorithms and users. Whether you believe it or not, after several months of toiling day and night, experiencing burnout, growing weary of the topic, and gaining an extra 15 kg in weight, we finally found our freedom… The exit wasn’t incredibly profitable, but we knew they had outdone us. The exit covered all our expenses and granted us a well-deserved rest for the subsequent quarter. It was an insane ride. Despite the uncertainty, stress, struggles, and sleepless nights, the story and experience will remain etched in my memory for the rest of my life. Swift Takeaways: Comprehending User Needs: Do you fully understand the product-market fit? Is your offering just an accessory or does it truly satisfy the user’s needs? The Power of Viral Marketing: Take inspiration from giants like Snapchat, ChatGPT, and Clubhouse. While your product might not attain the same scale (but remember, never say never…), the closer your concept is to theirs, the easier your journey will be. If your user is motivated to text a friend saying, “Hey, check out how cool this is” (like sharing ChatGPT), then you’re on the best track. Really. Even if it doesn’t seem immediately evident, there could be a way to incorporate this into your product. Keep looking until you find it. Niche targeting — the more specific and tailored your product is to a certain audience, the easier your journey will be People love buying from people — establishing a personal brand and associating yourself with the product can make things easier. Value: Seek to understand why users engage with your product and keep returning. The more specific and critical the issue you’re aiming to solve, the easier your path will be. Consider your offerings in terms of products and services and focus on sales and marketing, regardless of personal sentiments. These are just a few points, I plan to elaborate on all of them in a separate article. Many products undergo years of development in search of market fit, refining the user experience, and more. And guess what? There’s absolutely nothing wrong with that. Each product and market follows its own rules. Many startups have extensive histories before they finally make their mark (for instance, OpenAI). This entire journey spanned maybe 6–8 months. I grasped and capitalized on the opportunity, but we understood from the start that establishing a startup carried a significant risk, and our crypto product was 10 times riskier. Was it worth it? Given my passion for product development — absolutely. Was it profitable? — No, considering the hours spent — we lose. Did it provide a stable, problem-free life — nope. Did this entire adventure offer a wealth of happiness, joy, and unforgettable experiences — definitely yes. One thing is certain — we’ve amassed substantial experience and it’s not over yet :) So, what lies ahead? Chapter 7: Reverting to the contractor, developing a product for a crypto StartupReturning to the past, we continue our journey… I had invested substantial time and passion into the tech rescue mission product. I came on board as the technical Team Leader of a startup that had garnered over $20M in seed round funding, affiliated with the realm of cryptocurrencies. The investors were individuals with extensive backgrounds in the crypto world. My role was primarily technical, and there was an abundance of work to tackle. I was fully immersed, and genuinely devoted to the role. I was striving for excellence, knowing that if we secured another round of financing, the startup would accelerate rapidly. As for the product and marketing, I was more of an observer. After all, there were marketing professionals with decades of experience on board. These were individuals recruited from large crypto-related firms. I had faith in them, kept an eye on their actions, and focused on my own responsibilities. However, the reality was far from satisfactory. On the last day, the principal investor for the Series A round withdrew. The board made the tough decision to shut down. It was a period of intense observation and gaining experience in product management. This was a very brief summary of the last 10 years. And what next? (Last) Chapter 8: To be announced — Product Owner / Product Consultant / Strategist / CTO After spending countless hours and days deliberating my next steps, one thing is clear: My aspiration is to continue traversing the path of software product development, with the hopeful anticipation that one day, I might ride the crest of the next big wave and ascend to the prestigious status of a unicorn company. I find myself drawn to the process of building products, exploring product-market fit, strategizing, engaging in software development, seeking out new opportunities, networking, attending conferences, and continuously challenging myself by understanding the market and its competitive landscape. Product Owner / Product Consultant / CTO / COO: I’m not entirely sure how to categorize this role, as I anticipate that it will largely depend on the product to which I will commit myself fully. My idea is to find one startup/company that wants to build a product / or already has a product, want to speed up, or simply doesn’t know what’s next. Alternatively, I could be a part of an established company with a rich business history, which intends to invest in digitization and technological advancements. The goal would be to enrich their customer experience by offering complementary digital products Rather than initiating a new venture from ground zero with the same team, I am receptive to new challenges. I am confident that my past experiences will prove highly beneficial for the founders of promising, burgeoning startups that already possess a product, or are in the initial phases of development. ‘Consultant’ — I reckon we interpret this term differently. My aim is to be completely absorbed in a single product, crafting funnels, niches, strategies, and all that is necessary to repeatedly achieve the ‘product-market fit’ and significant revenue. To me, ‘consultant’ resonates more akin to freelancing than being an employee. My current goal is to kickstart as a consultant and aide, dealing with facilitating startups in their journey from point A to B. Here are two theoretical scenarios to illustrate my approach: Scenario 1: (Starting from point A) You have a product but struggle with marketing, adoption, software, strategy, sales, fundraising, or something else. I conduct an analysis and develop a strategy to reach point B. I take on the “dirty work” and implement necessary changes, including potential pivots or shifts (going all-in) to guide the product to point B. The goal is to reach point B, which could involve achieving a higher valuation, expanding the user base, increasing sales, or generating monthly revenue, among other metrics. Scenario 2: (Starting from point A) You have a plan or idea but face challenges with marketing, adoption, strategy, software, sales, fundraising, or something else. I analyze the situation and devise a strategy to reach point B. I tackle the necessary tasks, build the team, and overcome obstacles to propel the product to point B. I have come across the view that finding the elusive product-market fit is the job of the founder, and it’s hard for me to disagree. However, I believe that my support and experiences can help save money, many failures, and most importantly, time. I have spent a great deal of time learning from my mistakes, enduring failure after failure, and even had no one to ask for support or opinion, which is why I offer my help. Saving even a couple of years, realistically speaking, seems like a value I’m eager to provide… I invite you to share your thoughts and insights on these scenarios :) Closing Remarks: I appreciate your time and effort in reaching this point. This has been my journey, and I wouldn’t change it for the world. I had an extraordinary adventure, and now I’m ready for the next exciting battle with the market and new software products. While my entire narrative is centered around startups, especially the ones I personally built, I’m planning to share more insights drawn from all of my experiences, not just those as a co-founder. If you’re currently developing your product or even just considering the idea, I urge you to reach out to me. Perhaps together, we can create something monumental :) Thank you for your time and insights. I eagerly look forward to engaging in discussions and hearing your viewpoints. Please remember to like and subscribe. Nothing motivates to write more than positive feedback :) Matt.

Why you should consider using small open source fine-tuned models

Context I want to start off by giving some context on what fine-tuning is, why it's useful and who it would be useful for: What is fine-tuning? When controlling the output of an LLM there are, broadly, three levels. Prompt engineering, RAG and fine-tuning. Most of you are likely familiar with the first two. Prompt engineering is when you try to optimize the prompt to get the model to do what you want better. RAG (retrieval augmented generation) is when you first do a search on some data (usually stored in a vector database which allows you to search by similarity), then you insert the results into the prompt so that the model can use that context to more accurately answer any questions. It's like letting the LLM access external information right before answering, using that additional context to improve its response Fine-tuning is when you want to fundamentally teach a model something new or teach it to behave in a particular way. You would provide the model with high quality data (i.e. inputs and outputs) which it will train on. Why is it useful? At the moment, many of you use the largest and best LLMs because they give the best results. However, for a lot of use cases you are likely using a sledgehammer for a small nail. Does it do a great job? Damn yeah! Well... why not use a smaller hammer? Because it might miss or hit your finger. The solution shouldn't be to use a sledgehammer, but rather to learn how to use a smaller hammer properly so you never miss! That's exactly what fine-tuning a smaller model is like. Once you fine-tune it on a specific task with good high quality data, it can surpass even the best models at that specific task. It'll be 10x cheaper to run, much faster and, if you use an open source model, you'll own the model (no vendor lock-in!). If you run a SaaS and your biggest expense is AI costs then you should definitely consider fine-tuning. It'll take some time to set up but it'll be well worth it in the medium/long term (a bit like SEO). You can always resort to the best models for more complex tasks. How to fine-tune? I'm going to give you a breakdown of the process from beginning to end. You do need to be (a bit) technical in order to do this. Getting the data Let's suppose we want to fine-tune a model to make high-quality SEO content. At the moment, you might be using a large sophisticated prompt or using multiple large LLMs to write different parts or utilizing RAG. This is all slow and expensive but might be giving you great results. Our goal is to replace this with a fine-tuned model that is great at one thing: writing high-quality SEO content quickly at a much lower cost. The first step is gathering the appropriate data. If you want the model to write 3 or 4 paragraphs based on a prompt that contains the topic and a few keywords, then your data should match that. There are a few way you can do this: You can manually gather high-quality SEO content. You'd write the prompt and the response that the model should give. You can use a larger more powerful LLM to generate the content for you (also known as synthetic data). It'll be expensive but remember that it'll be a larger one-off cost to get the data. If you already have a pipeline that works great then you can use the prompts and the generated content that you already have from that pipeline. You can buy a high-quality dataset or get someone to make it for you. The data is the most important part of this process. Remember, garbage in garbage out. Your data needs to have a good variety and should not contain any bad examples. You should aim for around 1000 examples. The more the better! The actual fine-tuning. At this stage you are now ready to choose a model and setup the fine-tuning. If you are unsure I'd stick to the Llama 3.1 family of models. They are great and reliable. There are three models: 8b, 70b and 405b. Depending on the complexity of the task you should select an appropriate size. However, to really reap the cost saving benefits and the speed you should try to stick with the 8b model or the the 70b model if the 8b is not good enough. For our SEO example, let's use the 8b model. Important note on selecting a model: You might see multiple models with the 8b flag. You might see 4bit-bnb or instruct. The instruct version of the models have basically been trained to be chatbots. So if you want to keep the chatbot-like instruction-following functionality then you should use the instruct version as the base. The non-instruct version simply generates text. It won't 'act' like a chatbot which is better for use cases like creative writing. The 4bit-bnb means that the model has been 'quantized'. Basically it has been made 4x smaller (the original is in 16 bits) so that it is faster to download and faster to fine-tune. This slightly reduces the accuracy of the model but it's usually fine for most use cases :) Fine-tuning should be done on a good GPU. CPU aren't good enough. So you can't spin up a droplet on digital ocean and use that. You'll specifically need to spin up a GPU. One website that I think is great is Runpod .io (I am not affiliated with them). You simply pay for the GPU by the hour. If you want the training to be fast you can use the H100, if you want something cheaper but slower you can use the A40. Although the A40 won't be good enough to run the 70b parameter model. For the 405b model you'll need multiple H100s but let's leave that for more advanced use cases. Once you've spun up your H100 and ssh-ed into it. I would recommend using the unsloth open source library to do the fine-tuning. They have great docs and good boilerplate code. You want to train using a method called QLoRA. This won't train the entire model but only "part of it". I don't want to get into the technical details as t3hat isn't important but essentially it's a very efficient and effective way of fine-tuning models. When fine-tuning you can provide something called a 'validation set'. As your model is training it will be tested against the 'validation set' to see how well it's doing. You'll get an 'eval loss' which basically means how well is your model doing when compared with the unseen validation data. If you have 1000 training examples I'd recommend taking out 100-200 so it can act as the validation set. Your model may start off with an eval loss of 1.1 and by the end of the training (e.g. 3 epochs - the number of epochs is the number of times your model will be trained on the entire dataset. It's like reading a book more than once so you can understand it better. Usually 3-5 epochs is enough) the eval loss would drop to 0.6 or 0.7 which means your model has made great progress in learning your dataset! You don't want it to be too low as that means it is literally memorizing which isn't good. Post fine-tuning You'll want to save the model with the best eval loss. You actually won't have the whole model, just something called the "QLoRA adapters". These are basically like the new neurons that contain the "understanding" of the data you trained the model on. You can combine these with the base model (using unsloth again) to prompt the model. You can also (and I recommend this) convert the model to GGUF format (using unsloth again). This basically packages the QLoRA adapters and model together into an optimized format so you can easily and efficiently run it and prompt it (using unsloth again... lol). I would then recommend running some evaluations on the new model. You can do this by simply prompting the new model and a more powerful model (or using your old pipeline) and then asking a powerful model e.g. Claude to judge which is better. If your model consistently does better then you've hit a winner! You can then use runpod again to deploy the model to their serverless AI endpoint so you only pay when it's actually being inferenced. (Again, I'm not affiliated with them) I hope this was useful and you at least got a good idea of what fine-tuning is and how you might go about doing it. By the way, I've just launched a website where you can easily fine-tune Llama 3.1 models. I'm actually hoping to eventually automate this entire process as I believe small fine-tuned models will be much more common in the future. If you want more info, feel free to DM me :)

36 startup ideas found by analyzing podcasts (problem, solution & source episode)

Hey, I've been a bit of a podcast nerd for a long time. Around a year ago I began experimenting with transcription of podcasts for a SaaS I was running. I realized pretty quickly that there's a lot of knowledge and value in podcast discussions that is for all intents and purposes entirely unsearchable or discoverable to most people. I ended up stopping work on that SaaS product (party for lack of product/market fit, and partly because podcasting was far more interesting), and focusing on the podcast technology full-time instead. I'm a long-time lurker and poster of r/startups and thought this would make for some interesting content and inspiration for folks. Given I'm in this space, have millions of transcripts, and transcribe thousands daily... I've been exploring fun ways to expose some of the interesting knowledge and conversations taking place that utilize our own data/API. I'm a big fan of the usual startup podcasts (My First Million, Greg Isenberg, etc. etc.) and so I built an automation that turns all of the startup ideas discussed into a weekly email digest. I always struggle to listen to as many episodes as I'd actually like to, so I thought I'd summarise the stuff I care about instead (startup opportunities being discussed). I thought it would be interesting to post some of the ideas extracted so far. They range from being completely whacky and blue sky, to pretty boring but realistic. A word of warning before anyone complains – this is a big mixture of tech, ai, non-tech, local services, etc. ideas: Some of the ideas are completely mundane, but realistic (e.g. local window cleaning service) Some of the ideas are completely insane, blue sky, but sound super interesting Here's the latest 36 ideas: |Idea Name|Problem|Solution|Source| |:-|:-|:-|:-| |SalesForce-as-a-Service - White Label Enterprise Sales Teams|White-label enterprise sales teams for B2B SaaS. Companies need sales but can't hire/train. Recruit retail sellers, train for tech, charge 30% of deals closed.|Create a white-label enterprise sales team by recruiting natural salespeople from retail and direct sales backgrounds (e.g. mall kiosks, cutco knives). Train them specifically in B2B SaaS sales techniques and processes. Offer this trained sales force to tech companies on a contract basis.|My First Million - "Life Hacks From The King of Introverts + 7 Business Ideas| |TechButler - Mobile Device Maintenance Service|Mobile tech maintenance service. Clean/optimize devices, improve WiFi, basic support. $100/visit to homes. Target affluent neighborhoods.|Mobile tech support service providing in-home device cleaning, optimization, and setup. Focus on common issues like WiFi improvement, device maintenance, and basic tech support.|My First Million - "Life Hacks From The King of Introverts + 7 Business Ideas| |MemoryBox - At-Home Video Digitization Service|Door-to-door VHS conversion service. Parents have boxes of old tapes. Pick up, digitize, deliver. $30/tape with minimum order. Going extinct.|Door-to-door VHS to digital conversion service that handles everything from pickup to digital delivery. Make it extremely convenient for customers to preserve their memories.|My First Million - "Life Hacks From The King of Introverts + 7 Business Ideas| |Elite Match Ventures - Success-Based Luxury Matchmaking|High-end matchmaking for 50M+ net worth individuals. Only charge $1M+ when they get married. No upfront fees. Extensive vetting process.|Premium matchmaking service exclusively for ultra-high net worth individuals with a pure contingency fee model - only get paid ($1M+) upon successful marriage. Focus on quality over quantity with extensive vetting and personalized matching.|My First Million - "Life Hacks From The King of Introverts + 7 Business Ideas| |LocalHost - Simple Small Business Websites|Simple WordPress sites for local businesses. $50/month includes hosting, updates, security. Target restaurants and shops. Recurring revenue play.|Simplified web hosting and WordPress management service targeting local small businesses. Focus on basic sites with standard templates, ongoing maintenance, and reliable support for a fixed monthly fee.|My First Million - "Life Hacks From The King of Introverts + 7 Business Ideas| |VoiceJournal AI - Voice-First Smart Journaling|Voice-to-text journaling app with AI insights. 8,100 monthly searches. $15/month subscription. Partners with journaling YouTubers.|AI-powered journaling app that combines voice recording, transcription, and intelligent insights. Users can speak their thoughts, which are automatically transcribed and analyzed for patterns, emotions, and actionable insights.|Where It Happens - "7 $1M+ AI startup ideas you can launch tomorrow with $0"| |AIGenAds - AI-Generated UGC Content Platform|AI platform turning product briefs into UGC-style video ads. Brands spending $500/video for human creators. Generate 100 variations for $99/month.|AI platform that generates UGC-style video ads using AI avatars and scripting. System would allow rapid generation of multiple ad variations at a fraction of the cost. Platform would use existing AI avatar technology combined with script generation to create authentic-looking testimonial-style content.|Where It Happens - "7 $1M+ AI startup ideas you can launch tomorrow with $0"| |InfographAI - Automated Infographic Generation Platform|AI turning blog posts into branded infographics. Marketers spending hours on design. $99/month unlimited generation.|AI-powered platform that automatically converts blog posts and articles into visually appealing infographics. System would analyze content, extract key points, and generate professional designs using predefined templates and brand colors.|Where It Happens - "7 $1M+ AI startup ideas you can launch tomorrow with $0"| |KidFinance - Children's Financial Education Entertainment|Children's media franchise teaching financial literacy. Former preschool teacher creating 'Dora for money'. Books, videos, merchandise potential.|Character-driven financial education content for kids, including books, videos, and potentially TV show. Focus on making money concepts fun and memorable.|The Side Hustle Show - "How a Free Challenge Turned Into a $500,000 a Year Business (Greatest Hits)"| |FinanceTasker - Daily Financial Task Challenge|Free 30-day financial challenge with daily action items. People overwhelmed by money management. Makes $500k/year through books, speaking, and premium membership.|A free 30-day financial challenge delivering one simple, actionable task per day via email. Each task includes detailed scripts and instructions. Participants join a Facebook community for support and accountability. The program focuses on quick wins to build momentum. Automated delivery allows scaling.|The Side Hustle Show - "How a Free Challenge Turned Into a $500,000 a Year Business (Greatest Hits)"| |FinanceAcademy - Expert Financial Training Platform|Premium financial education platform. $13/month for expert-led courses and live Q&As. 4000+ members generating $40k+/month.|Premium membership site with expert-led courses, live Q&As, and community support. Focus on specific topics like real estate investing, business creation, and advanced money management.|The Side Hustle Show - "How a Free Challenge Turned Into a $500,000 a Year Business (Greatest Hits)"| |SecurityFirst Compliance - Real Security + Compliance Platform|Security-first compliance platform built by hackers. Companies spending $50k+ on fake security. Making $7M/year showing why current solutions don't work.|A compliance platform built by security experts that combines mandatory compliance requirements with real security measures. The solution includes hands-on security testing, expert guidance, and a focus on actual threat prevention rather than just documentation. It merges traditional compliance workflows with practical security implementations.|In the Pit with Cody Schneider| |LinkedInbound - Automated Professional Visibility Engine|LinkedIn automation for inbound job offers. Professionals spending hours on manual outreach. $99/month per job seeker.|Automated system for creating visibility and generating inbound interest on LinkedIn through coordinated profile viewing and engagement. Uses multiple accounts to create visibility patterns that trigger curiosity and inbound messages.|In the Pit with Cody Schneider| |ConvoTracker - Community Discussion Monitoring Platform|Community discussion monitoring across Reddit, Twitter, HN. Companies missing sales opportunities. $499/month per brand tracked.|Comprehensive monitoring system that tracks competitor mentions and industry discussions across multiple platforms (Reddit, Twitter, Hacker News, etc.) with automated alerts and engagement suggestions.|In the Pit with Cody Schneider| |ContentAds Pro - Smart Display Ad Implementation|Display ad implementation service for content creators. Bloggers losing thousands in ad revenue monthly. Makes $3-5k per site setup plus ongoing optimization fees.|Implementation of professional display advertising through networks like Mediavine that specialize in optimizing ad placement and revenue while maintaining user experience. Include features like turning off ads for email subscribers and careful placement to minimize impact on core metrics.|The Side Hustle Show - "636: Is Business Coaching Worth It? A Look Inside the last 12 months of Side Hustle Nation"| |MoneyAppReviews - Professional Side Hustle App Testing|Professional testing service for money-making apps. People wasting time on low-paying apps. Makes $20k/month from affiliate commissions and ads.|Professional app testing service that systematically reviews money-making apps and creates detailed, honest reviews including actual earnings data, time investment, and practical tips.|The Side Hustle Show - "636: Is Business Coaching Worth It? A Look Inside the last 12 months of Side Hustle Nation"| |LightPro - Holiday Light Installation Service|Professional Christmas light installation service. Homeowners afraid of ladders. $500-2000 per house plus storage.|Professional Christmas light installation service targeting residential and commercial properties. Full-service offering including design, installation, maintenance, removal and storage. Focus on safety and premium aesthetic results.|The Side Hustle Show - "639: 30 Ways to Make Extra Money for the Holidays"| |FocusMatch - Research Participant Marketplace|Marketplace connecting companies to paid research participants. Companies spending weeks finding people. $50-150/hour per study.|Online platform connecting companies directly with paid research participants. Participants create detailed profiles and get matched to relevant studies. Companies get faster access to their target demographic while participants earn money sharing opinions.|The Side Hustle Show - "639: 30 Ways to Make Extra Money for the Holidays"| |SolarShine Pro - Specialized Solar Panel Cleaning Service|Solar panel cleaning service using specialized equipment. Panels lose 50% efficiency when dirty. $650 per job, automated scheduling generates $18k/month from repeat customers.|Professional solar panel cleaning service using specialized deionized water system and European cleaning equipment. Includes automated 6-month scheduling, professional liability coverage, and warranty-safe cleaning processes. Service is bundled with inspection and performance monitoring.|The UpFlip Podcast - "156. $18K/Month with This ONE Service — Niche Business Idea"| |ExteriorCare Complete - One-Stop Exterior Maintenance Service|One-stop exterior home cleaning service (solar, windows, gutters, bird proofing). Automated scheduling. $650 average ticket. 60% repeat customers on 6-month contracts.|All-in-one exterior cleaning service offering comprehensive maintenance packages including solar, windows, gutters, roof cleaning and bird proofing. Single point of contact, consistent quality, and automated scheduling for all services.|The UpFlip Podcast - "156. $18K/Month with This ONE Service — Niche Business Idea"| |ContentMorph - Automated Cross-Platform Content Adaptation|AI platform converting blog posts into platform-optimized social content. Marketing teams spending 5hrs/post on manual adaptation. $199/mo per brand with 50% margins.|An AI-powered platform that automatically transforms long-form content (blog posts, podcasts, videos) into platform-specific formats (Instagram reels, TikToks, tweets). The system would preserve brand voice while optimizing for each platform's unique requirements and best practices.|Entrepreneurs on Fire - "Digital Threads: The Entrepreneur Playbook for Digital-First Marketing with Neal Schaffer"| |MarketerMatch - Verified Digital Marketing Talent Marketplace|Marketplace for pre-vetted digital marketing specialists. Entrepreneurs spending 15hrs/week on marketing tasks. Platform takes 15% commission averaging $900/month per active client.|A specialized marketplace exclusively for digital marketing professionals, pre-vetted for specific skills (video editing, social media, SEO, etc.). Platform includes skill verification, portfolio review, and specialization matching.|Entrepreneurs on Fire - "Digital Threads: The Entrepreneur Playbook for Digital-First Marketing with Neal Schaffer"| |Tiger Window Cleaning - Premium Local Window Service|Local window cleaning service targeting homeowners. Traditional companies charging 2x market rate. Making $10k/month from $200 initial investment.|Local window cleaning service combining competitive pricing ($5/pane), excellent customer service, and quality guarantees. Uses modern tools like water-fed poles for efficiency. Implements systematic approach to customer communication and follow-up.|The Side Hustle Show - "630: How this College Student’s Side Hustle Brings in $10k a Month"| |RealViz3D - Real Estate Visualization Platform|3D visualization service turning architectural plans into photorealistic renderings for real estate agents. Agents struggling with unbuilt property sales. Making $30-40k/year per operator.|Professional 3D modeling and rendering service that creates photorealistic visualizations of properties before they're built or renovated. The service transforms architectural plans into immersive 3D representations that show lighting, textures, and realistic details. This helps potential buyers fully understand and connect with the space before it physically exists.|Side Hustle School - "#2861 - TBT: An Architect’s Side Hustle in 3D Real Estate Modeling"| |Somewhere - Global Talent Marketplace|Platform connecting US companies with vetted overseas talent. Tech roles costing $150k locally filled for 50% less. Grew from $15M to $52M valuation in 9 months.|Platform connecting US companies with pre-vetted overseas talent at significantly lower rates while maintaining high quality. Handles payments, contracts, and quality assurance to remove friction from global hiring.|My First Million - "I Lost Everything Twice… Then Made $26M In 18 Months| |GymLaunch - Rapid Gym Turnaround Service|Consultants flying to struggling gyms to implement proven member acquisition systems. Gym owners lacking sales expertise. Made $100k in first 21 days.|Expert consultants fly in to implement proven member acquisition systems, train staff, and rapidly fill gyms with new members. The service combines sales training, marketing automation, and proven conversion tactics to transform struggling gyms into profitable businesses within weeks.|My First Million - "I Lost Everything Twice… Then Made $26M In 18 Months| |PublishPlus - Publishing Backend Monetization|Backend monetization system for publishing companies. One-time customers becoming recurring revenue. Grew business from $2M to $110M revenue.|Add complementary backend products and services to increase customer lifetime value. Develop software tools and additional services that natural extend from initial publishing product. Focus on high-margin recurring revenue streams.|My First Million - "I Lost Everything Twice… Then Made $26M In 18 Months| |WelcomeBot - Automated Employee Onboarding Platform|Automated employee welcome platform. HR teams struggling with consistent onboarding. $99/month per 100 employees.|An automated onboarding platform that creates personalized welcome experiences through pre-recorded video messages, scheduled check-ins, and automated swag delivery. The platform would ensure consistent high-quality onboarding regardless of timing or location.|Entrepreneurs on Fire - "Free Training on Building Systems and Processes to Scale Your Business with Chris Ronzio: An EOFire Classic from 2021"| |ProcessBrain - Business Knowledge Documentation Platform|SaaS platform turning tribal knowledge into documented processes. Business owners spending hours training new hires. $199/month per company.|A software platform that makes it easy to document and delegate business processes and procedures. The platform would include templates, guided documentation flows, and tools to easily share and update procedures. It would help businesses create a comprehensive playbook of their operations.|Entrepreneurs on Fire - "Free Training on Building Systems and Processes to Scale Your Business with Chris Ronzio: An EOFire Classic from 2021"| |TradeMatch - Modern Manufacturing Job Marketplace|Modern job board making manufacturing sexy again. Factory jobs paying $40/hr but can't recruit. $500 per successful referral.|A specialized job marketplace and recruitment platform focused exclusively on modern manufacturing and trade jobs. The platform would combine TikTok-style content marketing, referral programs, and modern UX to make manufacturing jobs appealing to Gen Z and young workers. Would leverage existing $500 referral fees and industry demand.|My First Million - "He Sold His Company For $15M, Then Got A Job At McDonald’s"| |GroundLevel - Executive Immersion Program|Structured program putting CEOs in front-line jobs. Executives disconnected from workers. $25k per placement.|A structured program that places executives and founders in front-line jobs (retail, warehouse, service) for 2-4 weeks with documentation and learning framework. Similar to Scott Heiferman's McDonald's experience but productized.|My First Million - "He Sold His Company For $15M, Then Got A Job At McDonald’s"| |OneStepAhead - Micro-Mentorship Marketplace|Marketplace for 30-min mentorship calls with people one step ahead. Professionals seeking specific guidance. Takes 15% of session fees.|MicroMentor Marketplace - Platform connecting people with mentors who are just one step ahead in their journey for focused, affordable micro-mentorship sessions.|Entrepreneurs on Fire - "How to Create an Unbroken Business with Michael Unbroken: An EOFire Classic from 2021"| |VulnerableLeader - Leadership Authenticity Training Platform|Leadership vulnerability training platform. Leaders struggling with authentic communication. $2k/month per company subscription.|Leadership Vulnerability Platform - A digital training platform combining assessment tools, guided exercises, and peer support to help leaders develop authentic communication skills. The platform would include real-world scenarios, video coaching, and measurable metrics for tracking leadership growth through vulnerability.|Entrepreneurs on Fire - "How to Create an Unbroken Business with Michael Unbroken: An EOFire Classic from 2021"| |NetworkAI - Smart Network Intelligence Platform|AI analyzing your network to find hidden valuable connections. Professionals missing opportunities in existing contacts. $49/month per user.|AI Network Navigator - Smart tool that analyzes your professional network across platforms, identifies valuable hidden connections, and suggests specific actionable ways to leverage relationships for mutual benefit.|Entrepreneurs on Fire - "How to Create an Unbroken Business with Michael Unbroken: An EOFire Classic from 2021"| |Porch Pumpkins - Seasonal Decoration Service|Full-service porch pumpkin decoration. Homeowners spend $300-1350 per season. One operator making $1M in 8 weeks seasonal revenue.|Full-service seasonal porch decoration service focused on autumn/Halloween, including design, installation, maintenance, and removal. Offering premium curated pumpkin arrangements with various package tiers.|My First Million - "The guy who gets paid $80K/yr to do nothing"| |Silent Companion - Professional Presence Service|Professional silent companions for lonely people. Huge problem in Japan/globally. $68/session, $80k/year per companion. Non-sexual, just presence.|A professional companion service where individuals can rent a non-judgmental, quiet presence for various activities. The companion provides silent company without the pressure of conversation or social performance. They accompany clients to events, meals, or just sit quietly together.|My First Million - "The guy who gets paid $80K/yr to do nothing"| Hope this is useful. If anyone would like to ensure I include any particular podcasts or episodes etc. in future posts, very happy to do so. I'll generally send \~5 ideas per week in a short weekly digest format (you can see the format I'd usually use in here: podcastmarketwatch.beehiiv.com). I find it mindblowing that the latest models with large context windows make it even possible to analyze full transcripts at such scale. It's a very exciting time we're living through! Would love some feedback on this stuff, happy to iterate and improve the analysis/ideas... or create a new newsletter on a different topic if anyone would like. Cheers!

Looking to Connect with Healthcare Tech Founders & Early-Stage Startups(Product, AI Strategy – Canada-based, Open to US). I will not promote.

Hey everyone, I’m exploring product and strategy roles in healthcare tech startups and looking to connect with early-stage founders working on AI-driven healthcare solutions. I’m currently based in Canada but looking for opportunities to work with U.S.-based startups in healthcare AI, digital health, and automation. My background is in tech, compliance, and cybersecurity, and I’m transitioning into product management for AI healthcare solutions. I’ve been working on a portfolio of AI-powered healthcare projects, including: A senior care digital assistant (health tracking, reminders) An AI companion for men's health (preventative care & chronic disease management) More projects coming in preventative health and healthcare automation I’m interested in learning from and working with fast-moving startups, particularly those at the intersection of AI and healthcare. If you’re working on something exciting, I’d love to chat. Drop a comment or DM me if you’re interested in connecting!

From "There's an App for that" to "There's YOUR App for that" - AI workflows will transform generic apps into deeply personalized experiences

I will not promote. For the past decade mobile apps were a core element of daily life for entertainment, productivity and connectivity. However, as the ecosystem saturated the general desire to download "just one more app" became apprehensive. There were clear monopolistic winners in different categories, such as Instagram and TikTok, which completely captured the majority of people's screentime. The golden age of creating indie apps and becoming a millionaire from them was dead. Conceptual models of these popular apps became ingrained in the general consciousness, and downloading new apps where re-learning new UI layouts was required, became a major friction point. There is high reluctance to download a new app rather than just utilizing the tooling of the growing market share of the existing winners. Content marketing and white labeled apps saw a resurgence of new app downloads, as users with parasympathetic relationships with influencers could be more easily persuaded to download them. However, this has led to a series of genericized tooling that lacks the soul of the early indie developer apps from the 2010s (Flappy bird comes to mind). A seemingly grim spot to be in, until everything changed on November 30th 2022. Sam Altman, Ilya Sutskever and team announced chatGPT, a Large Language Model that was the first publicly available generative AI tool. The first non-deterministic tool that could reason probablisitically in a similar (if flawed) way, to the human mind. At first, it was a clear paradigm shift in the world of computing, this was obvious from the fact that it climbed to 1 Million users within the first 5 days of its launch. However, despite the insane hype around the AI, its utility was constrained to chatbot interfaces for another year or more. As the models reasoning abilities got better and better, engineers began to look for other ways of utilizing this new paradigm shift, beyond chatbots. It became clear that, despite the powerful abilities to generate responses to prompts, the LLMs suffered from false hallucinations with extreme confidence, significantly impacting the reliability of their use, in search, coding and general utility. Retrieval Augmented Generation (RAG) was coined to provide a solution to this. Now, the LLM would apply a traditional search for data, via a database, a browser or other source of truth, and then feed that information into the prompt as it generates, allowing for more accurate results. Furthermore, it became clear that you could enhance an LLM by providing them metadata to interact with tools such as APIs for other services, allowing LLMs to perform actions typically reserved for humans, like fetching data, manipulating it and acting as an independent Agent. This prompted engineers to start treating LLMs, not as a database and a search engine, but rather a reasoning system, that could be part of a larger system of inputs and feedback to handle workflows independently. These "AI Agents" are poised to become the core technology in the next few years for hyper-personalizing and automating processes for specific users. Rather than having a generic B2B SaaS product that is somewhat useful for a team, one could standup a modular system of Agents that can handle the exactly specified workflow for that team. Frameworks such as LlangChain and LLamaIndex will help enable this for companies worldwide. The power is back in the hands of the people. However, it's not just big tech that is going to benefit from this revolution. AI Agentic workflows will allow for a resurgence in personalized applications that work like personal digital employee's. One could have a Personal Finance agent keeping track of their budgets, a Personal Trainer accountability coaching you making sure you meet your goals, or even a silly companion that roasts you when you're procrastinating. The options are endless ! At the core of this technology is the fact that these agents will be able to recall all of your previous data and actions, so they will get better at understanding you and your needs as a function of time. We are at the beginning of an exciting period in history, and I'm looking forward to this new period of deeply personalized experiences. What are your thoughts ? Let me know in the comments !

The Cold-Calling AI Project I'm Working On Just Got Some Angel Investment!

Hey y'all. The AI cold calling startup I've been working on for 3-4 months now just got a $2,500 angel investment, and we have 2 current customers, a credit card processing broker and a hospital equipment rental company based out of Texas. We have around $1,500 revenue so far, but we're having lots of trouble fulfilling the contracts because our tech just isn't "there" yet. I'm the Chief Tech Officer, and I'm also running some operations. The other main person in this is the CEO who has a strong sales background and came up with the idea. I've been working purely remotely, and it's great having some income because I'm stuck at home because I'm disabled, basically... &#x200B; We're using 11labs, openai, google speech to text, and a sh\*tty online dialer right now to run the first MVP which runs locally on our "botrunners" computers, and we're developing a web app with django python + javascript react. Our plan is, after we get the webapp working better, to hire more botrunners for $3 per hour from countries like Phillipines and India, and we're going to try to track all the actions the botrunners take to be able to train the AI to run it fully automated. The biggest problem we're facing right now with the tech is reducing latency, it started at 27 seconds to get a response and I've been able to get it down to 6 seconds, but people are still hanging up. We're trying several ways to mitigate this, including having pre-rendered speech playing something like "Okay" or "As an artificial representative, I'm still learning to be quicker on the pickup. We appreciate your patience." One of the industries we want to target is international web development and digital marketing companies, and we want to use the bot to cold-call businesses to pitch them our services. The goal is to replace $30 an hour cold-callers from the USA with $3 per hour total-cost automation. Apparently the CEO was given a $5 million valuation from the strength of the MVP from a VC. Our investment so far was at a $300k valuation tho. It's exciting. Trying to get Twilio working to be able to make calls programmatically instead of using our hacky workaround. Let me know if you have any questions. I just wanted to share this awesome news!

How a founder built a B2B AI startup to serve with 65+ global brands (including Fortune500 companies) (I will not promote)

AI Palette is an AI-driven platform that helps food and beverage companies predict emerging product trends. I had the opportunity recently to sit down with the founder to get his advice on building an AI-first startup, which he'll be going through in this post. (I will not promote) About AI Palette: Co-founders: >!2 (Somsubhra GanChoudhuri, Himanshu Upreti)!!100+!!$12.7M USD!!AI-powered predictive analytics for the CPG (Consumer Packaged Goods) industry!!Signed first paying customer in the first year!!65+ global brands, including Cargill, Diageo, Ajinomoto, Symrise, Mondelez, and L’Oréal, use AI Palette!!Every new product launched has secured a paying client within months!!Expanded into Beauty & Personal Care (BPC), onboarding one of India’s largest BPC companies within weeks!!Launched multiple new product lines in the last two years, creating a unified suite for brand innovation!Identify the pain points in your industry for ideas* When I was working in the flavour and fragrance industry, I noticed a major issue CPG companies faced: launching a product took at least one to two years. For instance, if a company decided today to launch a new juice, it wouldn’t hit the market until 2027. This long timeline made it difficult to stay relevant and on top of trends. Another big problem I noticed was that companies relied heavily on market research to determine what products to launch. While this might work for current consumer preferences, it was highly inefficient since the product wouldn’t actually reach the market for several years. By the time the product launched, the consumer trends had already shifted, making that research outdated. That’s where AI can play a crucial role. Instead of looking at what consumers like today, we realised that companies should use AI to predict what they will want next. This allows businesses to create products that are ahead of the curve. Right now, the failure rate for new product launches is alarmingly high, with 8 out of 10 products failing. By leveraging AI, companies can avoid wasting resources on products that won’t succeed, leading to better, more successful launches. Start by talking to as many industry experts as possible to identify the real problems When we first had the idea for AI Palette, it was just a hunch, a gut feeling—we had no idea whether people would actually pay for it. To validate the idea, we reached out to as many people as we could within the industry. Since our focus area was all about consumer insights, we spoke to professionals in the CPG sector, particularly those in the insights departments of CPG companies. Through these early conversations, we began to see a common pattern emerge and identified the exact problem we wanted to solve. Don’t tell people what you’re building—listen to their frustrations and challenges first. Going into these early customer conversations, our goal was to listen and understand their challenges without telling them what we were trying to build. This is crucial as it ensures that you can gather as much data about the problem to truly understand it and that you aren't biasing their answers by showing your solution. This process helped us in two key ways: First, it validated that there was a real problem in the industry through the number of people who spoke about experiencing the same problem. Second, it allowed us to understand the exact scale and depth of the problem—e.g., how much money companies were spending on consumer research, what kind of tools they were currently using, etc. Narrow down your focus to a small, actionable area to solve initially. Once we were certain that there was a clear problem worth solving, we didn’t try to tackle everything at once. As a small team of two people, we started by focusing on a specific area of the problem—something big enough to matter but small enough for us to handle. Then, we approached customers with a potential solution and asked them for feedback. We learnt that our solution seemed promising, but we wanted to validate it further. If customers are willing to pay you for the solution, it’s a strong validation signal for market demand. One of our early customer interviewees even asked us to deliver the solution, which we did manually at first. We used machine learning models to analyse the data and presented the results in a slide deck. They paid us for the work, which was a critical moment. It meant we had something with real potential, and we had customers willing to pay us before we had even built the full product. This was the key validation that we needed. By the time we were ready to build the product, we had already gathered crucial insights from our early customers. We understood the specific information they wanted and how they wanted the results to be presented. This input was invaluable in shaping the development of our final product. Building & Product Development Start with a simple concept/design to validate with customers before building When we realised the problem and solution, we began by designing the product, but not by jumping straight into coding. Instead, we created wireframes and user interfaces using tools like InVision and Figma. This allowed us to visually represent the product without the need for backend or frontend development at first. The goal was to showcase how the product would look and feel, helping potential customers understand its value before we even started building. We showed these designs to potential customers and asked for feedback. Would they want to buy this product? Would they pay for it? We didn’t dive into actual development until we found a customer willing to pay a significant amount for the solution. This approach helped us ensure we were on the right track and didn’t waste time or resources building something customers didn’t actually want. Deliver your solution using a manual consulting approach before developing an automated product Initially, we solved problems for customers in a more "consulting" manner, delivering insights manually. Recall how I mentioned that when one of our early customer interviewees asked us to deliver the solution, we initially did it manually by using machine learning models to analyse the data and presenting the results to them in a slide deck. This works for the initial stages of validating your solution, as you don't want to invest too much time into building a full-blown MVP before understanding the exact features and functionalities that your users want. However, after confirming that customers were willing to pay for what we provided, we moved forward with actual product development. This shift from a manual service to product development was key to scaling in a sustainable manner, as our building was guided by real-world feedback and insights rather than intuition. Let ongoing customer feedback drive iteration and the product roadmap Once we built the first version of the product, it was basic, solving only one problem. But as we worked closely with customers, they requested additional features and functionalities to make it more useful. As a result, we continued to evolve the product to handle more complex use cases, gradually developing new modules based on customer feedback. Product development is a continuous process. Our early customers pushed us to expand features and modules, from solving just 20% of their problems to tackling 50–60% of their needs. These demands shaped our product roadmap and guided the development of new features, ultimately resulting in a more complete solution. Revenue and user numbers are key metrics for assessing product-market fit. However, critical mass varies across industries Product-market fit (PMF) can often be gauged by looking at the size of your revenue and the number of customers you're serving. Once you've reached a certain critical mass of customers, you can usually tell that you're starting to hit product-market fit. However, this critical mass varies by industry and the type of customers you're targeting. For example, if you're building an app for a broad consumer market, you may need thousands of users. But for enterprise software, product-market fit may be reached with just a few dozen key customers. Compare customer engagement and retention with other available solutions on the market for product-market fit Revenue and the number of customers alone isn't always enough to determine if you're reaching product-market fit. The type of customer and the use case for your product also matter. The level of engagement with your product—how much time users are spending on the platform—is also an important metric to track. The more time they spend, the more likely it is that your product is meeting a crucial need. Another way to evaluate product-market fit is by assessing retention, i.e whether users are returning to your platform and relying on it consistently, as compared to other solutions available. That's another key indication that your solution is gaining traction in the market. Business Model & Monetisation Prioritise scalability Initially, we started with a consulting-type model where we tailor-made specific solutions for each customer use-case we encountered and delivered the CPG insights manually, but we soon realized that this wasn't scalable. The problem with consulting is that you need to do the same work repeatedly for every new project, which requires a large team to handle the workload. That is not how you sustain a high-growth startup. To solve this, we focused on building a product that would address the most common problems faced by our customers. Once built, this product could be sold to thousands of customers without significant overheads, making the business scalable. With this in mind, we decided on a SaaS (Software as a Service) business model. The benefit of SaaS is that once you create the software, you can sell it to many customers without adding extra overhead. This results in a business with higher margins, where the same product can serve many customers simultaneously, making it much more efficient than the consulting model. Adopt a predictable, simplistic business model for efficiency. Look to industry practices for guidance When it came to monetisation, we considered the needs of our CPG customers, who I knew from experience were already accustomed to paying annual subscriptions for sales databases and other software services. We decided to adopt the same model and charge our customers an annual upfront fee. This model worked well for our target market, aligning with industry standards and ensuring stable, recurring revenue. Moreover, our target CPG customers were already used to this business model and didn't have to choose from a huge variety of payment options, making closing sales a straightforward and efficient process. Marketing & Sales Educate the market to position yourself as a thought leader When we started, AI was not widely understood, especially in the CPG industry. We had to create awareness around both AI and its potential value. Our strategy focused on educating potential users and customers about AI, its relevance, and why they should invest in it. This education was crucial to the success of our marketing efforts. To establish credibility, we adopted a thought leadership approach. We wrote blogs on the importance of AI and how it could solve problems for CPG companies. We also participated in events and conferences to demonstrate our expertise in applying AI to the industry. This helped us build our brand and reputation as leaders in the AI space for CPG, and word-of-mouth spread as customers recognized us as the go-to company for AI solutions. It’s tempting for startups to offer products for free in the hopes of gaining early traction with customers, but this approach doesn't work in the long run. Free offerings don’t establish the value of your product, and customers may not take them seriously. You should always charge for pilots, even if the fee is minimal, to ensure that the customer is serious about potentially working with you, and that they are committed and engaged with the product. Pilots/POCs/Demos should aim to give a "flavour" of what you can deliver A paid pilot/POC trial also gives you the opportunity to provide a “flavour” of what your product can deliver, helping to build confidence and trust with the client. It allows customers to experience a detailed preview of what your product can do, which builds anticipation and desire for the full functionality. During this phase, ensure your product is built to give them a taste of the value you can provide, which sets the stage for a broader, more impactful adoption down the line. Fundraising & Financial Management Leverage PR to generate inbound interest from VCs When it comes to fundraising, our approach was fairly traditional—we reached out to VCs and used connections from existing investors to make introductions. However, looking back, one thing that really helped us build momentum during our fundraising process was getting featured in Tech in Asia. This wasn’t planned; it just so happened that Tech in Asia was doing a series on AI startups in Southeast Asia and they reached out to us for an article. During the interview, they asked if we were fundraising, and we mentioned that we were. As a result, several VCs we hadn’t yet contacted reached out to us. This inbound interest was incredibly valuable, and we found it far more effective than our outbound efforts. So, if you can, try to generate some PR attention—it can help create inbound interest from VCs, and that interest is typically much stronger and more promising than any outbound strategies because they've gone out of their way to reach out to you. Be well-prepared and deliberate about fundraising. Keep trying and don't lose heart When pitching to VCs, it’s crucial to be thoroughly prepared, as you typically only get one shot at making an impression. If you mess up, it’s unlikely they’ll give you a second chance. You need to have key metrics at your fingertips, especially if you're running a SaaS company. Be ready to answer questions like: What’s your retention rate? What are your projections for the year? How much will you close? What’s your average contract value? These numbers should be at the top of your mind. Additionally, fundraising should be treated as a structured process, not something you do on the side while juggling other tasks. When you start, create a clear plan: identify 20 VCs to reach out to each week. By planning ahead, you’ll maintain momentum and speed up the process. Fundraising can be exhausting and disheartening, especially when you face multiple rejections. Remember, you just need one investor to say yes to make it all worthwhile. When using funds, prioritise profitability and grow only when necessary. Don't rely on funding to survive. In the past, the common advice for startups was to raise money, burn through it quickly, and use it to boost revenue numbers, even if that meant operating at a loss. The idea was that profitability wasn’t the main focus, and the goal was to show rapid growth for the next funding round. However, times have changed, especially with the shift from “funding summer” to “funding winter.” My advice now is to aim for profitability as soon as possible and grow only when it's truly needed. For example, it’s tempting to hire a large team when you have substantial funds in the bank, but ask yourself: Do you really need 10 new hires, or could you get by with just four? Growing too quickly can lead to unnecessary expenses, so focus on reaching profitability as soon as possible, rather than just inflating your team or burn rate. The key takeaway is to spend your funds wisely and only when absolutely necessary to reach profitability. You want to avoid becoming dependent on future VC investments to keep your company afloat. Instead, prioritize reaching break-even as quickly as you can, so you're not reliant on external funding to survive in the long run. Team-Building & Leadership Look for complementary skill sets in co-founders When choosing a co-founder, it’s important to find someone with a complementary skill set, not just someone you’re close to. For example, I come from a business and commercial background, so I needed someone with technical expertise. That’s when I found my co-founder, Himanshu, who had experience in machine learning and AI. He was a great match because his technical knowledge complemented my business skills, and together we formed a strong team. It might seem natural to choose your best friend as your co-founder, but this can often lead to conflict. Chances are, you and your best friend share similar interests, skills, and backgrounds, which doesn’t bring diversity to the table. If both of you come from the same industry or have the same strengths, you may end up butting heads on how things should be done. Having diverse skill sets helps avoid this and fosters a more collaborative working relationship. Himanshu (left) and Somsubhra (right) co-founded AI Palette in 2018 Define roles clearly to prevent co-founder conflict To avoid conflict, it’s essential that your roles as co-founders are clearly defined from the beginning. If your co-founder and you have distinct responsibilities, there is no room for overlap or disagreement. This ensures that both of you can work without stepping on each other's toes, and there’s mutual respect for each other’s expertise. This is another reason as to why it helps to have a co-founder with a complementary skillset to yours. Not only is having similar industry backgrounds and skillsets not particularly useful when building out your startup, it's also more likely to lead to conflicts since you both have similar subject expertise. On the other hand, if your co-founder is an expert in something that you're not, you're less likely to argue with them about their decisions regarding that aspect of the business and vice versa when it comes to your decisions. Look for employees who are driven by your mission, not salary For early-stage startups, the first hires are crucial. These employees need to be highly motivated and excited about the mission. Since the salary will likely be low and the work demanding, they must be driven by something beyond just the paycheck. The right employees are the swash-buckling pirates and romantics, i.e those who are genuinely passionate about the startup’s vision and want to be part of something impactful beyond material gains. When employees are motivated by the mission, they are more likely to stick around and help take the startup to greater heights. A litmus test for hiring: Would you be excited to work with them on a Sunday? One of the most important rounds in the hiring process is the culture fit round. This is where you assess whether a candidate shares the same values as you and your team. A key question to ask yourself is: "Would I be excited to work with this person on a Sunday?" If there’s any doubt about your answer, it’s likely not a good fit. The idea is that you want employees who align with the company's culture and values and who you would enjoy collaborating with even outside of regular work hours. How we structure the team at AI Palette We have three broad functions in our organization. The first two are the big ones: Technical Team – This is the core of our product and technology. This team is responsible for product development and incorporating customer feedback into improving the technology Commercial Team – This includes sales, marketing, customer service, account managers, and so on, handling everything related to business growth and customer relations. General and Administrative Team – This smaller team supports functions like finance, HR, and administration. As with almost all businesses, we have teams that address the two core tasks of building (technical team) and selling (commercial team), but given the size we're at now, having the administrative team helps smoothen operations. Set broad goals but let your teams decide on execution What I've done is recruit highly skilled people who don't need me to micromanage them on a day-to-day basis. They're experts in their roles, and as Steve Jobs said, when you hire the right person, you don't have to tell them what to do—they understand the purpose and tell you what to do. So, my job as the CEO is to set the broader goals for them, review the plans they have to achieve those goals, and periodically check in on progress. For example, if our broad goal is to meet a certain revenue target, I break it down across teams: For the sales team, I’ll look at how they plan to hit that target—how many customers they need to sell to, how many salespeople they need, and what tactics and strategies they plan to use. For the technical team, I’ll evaluate our product offerings—whether they think we need to build new products to attract more customers, and whether they think it's scalable for the number of customers we plan to serve. This way, the entire organization's tasks are cascaded in alignment with our overarching goals, with me setting the direction and leaving the details of execution to the skilled team members that I hire.

The Cold-Calling AI Project I'm Working On Just Got Some Angel Investment!

Hey y'all. The AI cold calling startup I've been working on for 3-4 months now just got a $2,500 angel investment, and we have 2 current customers, a credit card processing broker and a hospital equipment rental company based out of Texas. We have around $1,500 revenue so far, but we're having lots of trouble fulfilling the contracts because our tech just isn't "there" yet. I'm the Chief Tech Officer, and I'm also running some operations. The other main person in this is the CEO who has a strong sales background and came up with the idea. I've been working purely remotely, and it's great having some income because I'm stuck at home because I'm disabled, basically... &#x200B; We're using 11labs, openai, google speech to text, and a sh\*tty online dialer right now to run the first MVP which runs locally on our "botrunners" computers, and we're developing a web app with django python + javascript react. Our plan is, after we get the webapp working better, to hire more botrunners for $3 per hour from countries like Phillipines and India, and we're going to try to track all the actions the botrunners take to be able to train the AI to run it fully automated. The biggest problem we're facing right now with the tech is reducing latency, it started at 27 seconds to get a response and I've been able to get it down to 6 seconds, but people are still hanging up. We're trying several ways to mitigate this, including having pre-rendered speech playing something like "Okay" or "As an artificial representative, I'm still learning to be quicker on the pickup. We appreciate your patience." One of the industries we want to target is international web development and digital marketing companies, and we want to use the bot to cold-call businesses to pitch them our services. The goal is to replace $30 an hour cold-callers from the USA with $3 per hour total-cost automation. Apparently the CEO was given a $5 million valuation from the strength of the MVP from a VC. Our investment so far was at a $300k valuation tho. It's exciting. Trying to get Twilio working to be able to make calls programmatically instead of using our hacky workaround. Let me know if you have any questions. I just wanted to share this awesome news!

Solo technical founders, has not having a business cofounder even screwed you up? "I will not promote"

I’m creating an AI startup; a reinforcement learning model designed to do a certain thing in a big field. I’ve basically developed code for a prototype (I hope to start training in two weeks) I do believe YC advice for taking a cofounder, but risk of getting a bad one is too high. In my life I also haven't met people with my grit, at least from my countries, so I'll have to "date down", I guess. At least in technical sense. So, has not having a business cofounder actually screwed anyone up badly?  (Looking at people who are doing ventures with $20m+ potential/real ARR,)

I spent 6 months on building a tool, and got 0 zero users. Here is my story.

Edit Thank you all so much for your time reading my story. Your support, feedback, criticism, and skepticism; all helped me a lot, and I couldn't appreciate it enough \^\_\^ TL;DR I spent 6 months on a tool that currently has 0 users. Below is what I learned during my journey, sharing because I believe most mistakes are easily avoidable. Do not overestimate your product and assume it will be an exception to fundamental principles. Principles are there for a reason. Always look for validation before you start. Avoid building products with a low money-to-effort ratio/in very competitive fields. Unless you have the means, you probably won't make it. Pick a problem space, pick your target audience, and talk to them before thinking about a solution. Identify and match their pain points. Only then should you think of a solution. If people are not overly excited or willing to pay in advance for a discounted price, it might be a sign to rethink. Sell one and only one feature at a time. Avoid everything else. If people don't pay for that one core feature, no secondary feature will change their mind. Always spend twice as much time marketing as you do building. You will not get users if they don't know it exists. Define success metrics ("1000 users in 3 months" or "$6000 in the account at the end of 6 months") before you start. If you don't meet them, strongly consider quitting the project. If you can't get enough users to keep going, nothing else matters. VALIDATION, VALIDATION, VALIDATION. Success is not random, but most of our first products will not make a success story. Know when to admit failure, and move on. Even if a product of yours doesn't succeed, what you learned during its journey will turn out to be invaluable for your future. My story So, this is the story of a product, Summ, that I’ve been working on for the last 6 months. As it's the first product I’ve ever built, after watching you all from the sidelines, I have learned a lot, made many mistakes, and did only a few things right. Just sharing what I’ve learned and some insights from my journey so far. I hope that this post will help you avoid the mistakes I made — most of which I consider easily avoidable — while you enjoy reading it, and get to know me a little bit more 🤓. A slow start after many years Summ isn’t the first product I really wanted to build. Lacking enough dev skills to even get started was a huge blocker for so many years. In fact, the first product I would’ve LOVED to build was a smart personal shopping assistant. I had this idea 4 years ago; but with no GPT, no coding skills, no technical co-founder, I didn’t have the means to make it happen. I still do not know if such a tool exists and is good enough. All I wanted was a tool that could make data-based predictions about when to buy stuff (“buy a new toothpaste every three months”) and suggest physical products that I might need or be strongly interested in. AFAIK, Amazon famously still struggles with the second one. Fast-forward a few years, I learned the very basics of HTML, CSS, and Vanilla JS. Still was not there to build a product; but good enough to code my design portfolio from scratch. Yet, I couldn’t imagine myself building a product using Vanilla JS. I really hated it, I really sucked at it. So, back to tutorial hell, and to learn about this framework I just heard about: React.React introduced so many new concepts to me. “Thinking in React” is a phrase we heard a lot, and with quite good reasons. After some time, I was able to build very basic tutorial apps, both in React, and React Native; but I have to say that I really hated coding for mobile. At this point, I was already a fan of productivity apps, and had a concept for a time management assistant app in my design portfolio. So, why not build one? Surely, it must be easy, since every coding tutorial starts with a todo app. ❌ WRONG! Building a basic todo app is easy enough, but building one good enough for a place in the market was a challenge I took and failed. I wasted one month on that until I abandoned the project for good. Even if I continued working on it, as the productivity landscape is overly competitive, I wouldn’t be able to make enough money to cover costs, assuming I make any. Since I was (and still am) in between jobs, I decided to abandon the project. 👉 What I learned: Do not start projects with a low ratio of money to effort and time. Example: Even if I get 500 monthly users, 200 of which are paid users (unrealistically high number), assuming an average subscription fee of $5/m (such apps are quite cheap, mostly due to the high competition), it would make me around $1000 minus any occurring costs. Any founder with a product that has 500 active users should make more. Even if it was relatively successful, due to the high competition, I wouldn’t make any meaningful money. PS: I use Todoist today. Due to local pricing, I pay less than $2/m. There is no way I could beat this competitive pricing, let alone the app itself. But, somehow, with a project that wasn’t even functional — let alone being an MVP — I made my first Wi-Fi money: Someone decided that the domain I preemptively purchased is worth something. By this point, I had already abandoned the project, certainly wasn’t going to renew the domain, was looking for a FT job, and a new project that I could work on. And out of nowhere, someone hands me some free money — who am I not to take it? Of course, I took it. The domain is still unused, no idea why 🤔. Ngl, I still hate the fact that my first Wi-Fi money came from this. A new idea worth pursuing? Fast-forward some weeks now. Around March, I got this crazy idea of building an email productivity tool. We all use emails, yet we all hate them. So, this must be fixed. Everyone uses emails, in fact everyone HAS TO use emails. So, I just needed to build a tool and wait for people to come. This was all, really. After all, the problem space is huge, there is enough room for another product, everyone uses emails, no need for any further validation, right? ❌ WRONG ONCE AGAIN! We all hear from the greatest in the startup landscape that we must validate our ideas with real people, yet at least some of us (guilty here 🥸) think that our product will be hugely successful and prove them to be an exception. Few might, but most are not. I certainly wasn't. 👉 Lesson learned: Always validate your ideas with real people. Ask them how much they’d pay for such a tool (not if they would). Much better if they are willing to pay upfront for a discount, etc. But even this comes later, keep reading. I think the difference between “How much” and “If” is huge for two reasons: (1) By asking them for “How much”, you force them to think in a more realistic setting. (2) You will have a more realistic idea on your profit margins. Based on my competitive analysis, I already had a solution in my mind to improve our email usage standards and email productivity (huge mistake), but I did my best to learn about their problems regarding those without pushing the idea too hard. The idea is this: Generate concise email summaries with suggested actions, combine them into one email, and send it at their preferred times. Save as much as time the AI you end up with allows. After all, everyone loves to save time. So, what kind of validation did I seek for? Talked with only a few people around me about this crazy, internet-breaking idea. The responses I got were, now I see, mediocre; no one got excited about it, just said things along the lines of “Cool idea, OK”. So, any reasonable person in this situation would think “Okay, not might not be working”, right? Well, I did not. I assumed that they were the wrong audience for this product, and there was this magical land of user segments waiting eagerly for my product, yet unknowingly. To this day, I still have not reached this magical place. Perhaps, it didn’t exist in the first place. If I cannot find it, whether it exists or not doesn’t matter. I am certainly searching for it. 👉 What I should have done: Once I decide on a problem space (time management, email productivity, etc.), I should decide on my potential user segments, people who I plan to sell my product to. Then I should go talk to those people, ask them about their pains, then get to the problem-solving/ideation phase only later. ❗️ VALIDATION COMES FROM THE REALITY OUTSIDE. What validation looks like might change from product to product; but what invalidation looks like is more or less the same for every product. Nico Jeannen told me yesterday “validation = money in the account” on Twitter. This is the ultimate form of validation your product could get. If your product doesn’t make any money, then something is invalidated by reality: Your product, you, your idea, who knows? So, at this point, I knew a little bit of Python from spending some time in tutorial hell a few years ago, some HTML/CSS/JS, barely enough React to build a working app. React could work for this project, but I needed easy-to-implement server interactivity. Luckily, around this time, I got to know about this new gen of indie hackers, and learned (but didn’t truly understand) about their approach to indie hacking, and this library called Nextjs. How good Next.js still blows my mind. So, I was back to tutorial hell once again. But, this time, with a promise to myself: This is the last time I would visit tutorial hell. Time to start building this "ground-breaking idea" Learning the fundamentals of Next.js was easier than learning of React unsurprisingly. Yet, the first time I managed to run server actions on Next.js was one of the rarest moments that completely blew my mind. To this day, I reject the idea that it is something else than pure magic under its hood. Did I absolutely need Nextjs for this project though? I do not think so. Did it save me lots of time? Absolutely. Furthermore, learning Nextjs will certainly be quite helpful for other projects that I will be tackling in the future. Already got a few ideas that might be worth pursuing in the head in case I decide to abandon Summ in the future. Fast-forward few weeks again: So, at this stage, I had a barely working MVP-like product. Since the very beginning, I spent every free hour (and more) on this project as speed is essential. But, I am not so sure it was worth it to overwork in retrospect. Yet, I know I couldn’t help myself. Everything is going kinda smooth, so what’s the worst thing that could ever happen? Well, both Apple and Google announced their AIs (Apple Intelligence and Google Gemini, respectively) will have email summarization features for their products. Summarizing singular emails is no big deal, after all there were already so many similar products in the market. I still think that what truly matters is a frictionless user experience, and this is why I built this product in a certain way: You spend less than a few minutes setting up your account, and you get to enjoy your email summaries, without ever visiting its website again. This is still a very cool concept I really like a lot. So, at this point: I had no other idea that could be pursued, already spent too much time on this project. Do I quit or not? This was the question. Of course not. I just have to launch this product as quickly as possible. So, I did something right, a quite rare occurrence I might say: Re-planned my product, dropped everything secondary to the core feature immediately (save time on reading emails), tried launching it asap. 👉 Insight: Sell only one core feature at one time. Drop anything secondary to this core feature. Well, my primary occupation is product design. So one would expect that a product I build must have stellar design. I considered any considerable time spent on design at this stage would be simply wasted. I still think this is both true and wrong: True, because if your product’s core benefits suck, no one will care about your design. False, because if your design looks amateurish, no one will trust you and your product. So, I always targeted an average level design with it and the way this tool works made it quite easy as I had to design only 2 primary pages: Landing page and user portal (which has only settings and analytics pages). However, even though I knew spending time on design was not worth much of my time, I got a bit “greedy”: In fact, I redesigned those pages three times, and still ended up with a so-so design that I am not proud of. 👉 What I would do differently: Unless absolutely necessary, only one iteration per stage as long as it works. This, in my mind, applies to everything. If your product’s A feature works, then no need to rewrite it from scratch for any reason, or even refactor it. When your product becomes a success, and you absolutely need that part of your codebase to be written, do so, but only then. Ready to launch, now is th etime for some marketing, right? By July 26, I already had a “launchable” product that barely works (I marked this date on a Notion docs, this is how I know). Yet, I had spent almost no time on marketing, sales, whatever. After all, “You build and they will come”. Did I know that I needed marketing? Of course I did, but knowingly didn’t. Why, you might ask. Well, from my perspective, it had to be a dev-heavy product; meaning that you spend most of your time on developing it, mostly coding skills. But, this is simply wrong. As a rule of thumb, as noted by one of the greatests, Marc Louvion, you should spend at least twice of the building time on marketing. ❗️ Time spent on building \* 2 people don’t know your product > they don’t use your product > you don’t get users > you don’t make money Easy as that. Following the same reasoning, a slightly different approach to planning a project is possible. Determine an approximate time to complete the project with a high level project plan. Let’s say 6 months. By the reasoning above, 2 months should go into building, and 4 into marketing. If you need 4 months for building instead of 2, then you need 8 months of marketing, which makes the time to complete the project 12 months. If you don’t have that much time, then quit the project. When does a project count as completed? Well, in reality, never. But, I think we have to define success conditions even before we start for indie projects and startups; so we know when to quit when they are not met. A success condition could look like “Make $6000 in 12 months” or “Have 3000 users in 6 months”. It all depends on the project. But, once you set it, it should be set in stone: You don’t change it unless absolutely necessary. I suspect there are few principles that make a solopreneur successful; and knowing when to quit and when to continue is definitely one of them. Marc Louvion is famously known for his success, but he got there after failing so many projects. To my knowledge, the same applies to Nico Jeannen, Pieter Levels, or almost everyone as well. ❗️ Determining when to continue even before you start will definitely help in the long run. A half-aed launch Time-leap again. Around mid August, I “soft launched” my product. By soft launch, I mean lazy marketing. Just tweeting about it, posting it on free directories. Did I get any traffic? Surely I did. Did I get any users? Nope. Only after this time, it hit me: “Either something is wrong with me, or with this product” Marketing might be a much bigger factor for a project’s success after all. Even though I get some traffic, not convincing enough for people to sign up even for a free trial. The product was still perfect in my eyes at the time (well, still is ^(\_),) so the right people are not finding my product, I thought. Then, a question that I should have been asking at the very first place, one that could prevent all these, comes to my mind: “How do even people search for such tools?” If we are to consider this whole journey of me and my so-far-failed product to be an already destined failure, one metric suffices to show why. Search volume: 30. Even if people have such a pain point, they are not looking for email summaries. So, almost no organic traffic coming from Google. But, as a person who did zero marketing on this or any product, who has zero marketing knowledge, who doesn’t have an audience on social media, there is not much I could do. Finally, it was time to give up. Or not… In my eyes, the most important element that makes a founder (solo or not) successful (this, I am not by any means) is to solve problems. ❗️ So, the problem was this: “People are not finding my product by organic search” How do I make sure I get some organic traffic and gets more visibility? Learn digital marketing and SEO as much as I can within very limited time. Thankfully, without spending much time, I came across Neil Patel's YT channel, and as I said many times, it is an absolute gold mine. I learned a lot, especially about the fundamentals, and surely it will be fruitful; but there is no magic trick that could make people visit your website. SEO certainly helps, but only when people are looking for your keywords. However, it is truly a magical solution to get in touch with REAL people that are in your user segments: 👉 Understand your pains, understand their problems, help them to solve them via building products. I did not do this so far, have to admit. But, in case you would like to have a chat about your email usage, and email productivity, just get in touch; I’d be delighted to hear about them. Getting ready for a ProductHunt launch The date was Sept 1. And I unlocked an impossible achievement: Running out of Supabase’s free plan’s Egres limit while having zero users. I was already considering moving out of their Cloud server and managing a Supabase CLI service on my Hetzner VPS for some time; but never ever suspected that I would have to do this quickly. The cheapest plan Supabase offers is $25/month; yet, at that point, I am in between jobs for such a long time, basically broke, and could barely afford that price. One or two months could be okay, but why pay for it if I will eventually move out of their Cloud service? So, instead of paying $25, I spent two days migrating out of Supabase Cloud. Worth my time? Definitely not. But, when you are broke, you gotta do stupid things. This was the first time that I felt lucky to have zero users: I have no idea how I would manage this migration if I had any. I think this is one of the core tenets of an indie hacker: Controlling their own environment. I can’t remember whose quote this is, but I suspect it was Naval: Entrepreneurs have an almost pathological need to control their own fate. They will take any suffering if they can be in charge of their destiny, and not have it in somebody else’s hands. What’s truly scary is, at least in my case, we make people around us suffer at the expense of our attempting to control our own fates. I know this period has been quite hard on my wife as well, as I neglected her quite a bit, but sadly, I know that this will happen again. It is something that I can barely help with. Still, so sorry. After working the last two weeks on a ProductHunt Launch, I finally launched it this Tuesday. Zero ranking, zero new users, but 36 kind people upvoted my product, and many commented and provided invaluable feedback. I couldn't be more grateful for each one of them 🙏. Considering all these, what lies in the future of Summ though? I have no idea, to be honest. On one hand, I have zero users, have no job, no income. So, I need a way to make money asap. On the other hand, the whole idea of it revolves around one core premise (not an assumption) that I am not so willing to share; and I couldn’t have more trust in it. This might not be the best iteration of it, however I certainly believe that email usage is one of the best problem spaces one could work on. 👉 But, one thing is for certain: I need to get in touch with people, and talk with them about this product I built so far. In fact, this is the only item on my agenda. Nothing else will save my brainchild <3. Below are some other insights and notes that I got during my journey; as they do not 100% fit into this story, I think it is more suitable to list them here. I hope you enjoyed reading this. Give Summ a try, it comes with a generous free trial, no credit card required. Some additional notes and insights: Project planning is one of the most underestimated skills for solopreneurs. It saves you enormous time, and helps you to keep your focus up. Building B2C products beats building B2B products. Businesses are very willing to pay big bucks if your product helps them. On the other hand, spending a few hours per user who would pay $5/m probably is not worth your time. It doesn’t matter how brilliant your product is if no one uses it. If you cannot sell a product in a certain category/niche (or do not know how to sell it), it might be a good idea not to start a project in it. Going after new ideas and ventures is quite risky, especially if you don’t know how to market it. On the other hand, an already established category means that there is already demand. Whether this demand is sufficient or not is another issue. As long as there is enough demand for your product to fit in, any category/niche is good. Some might be better, some might be worse. Unless you are going hardcore B2B, you will need people to find your product by means of organic search. Always conduct thorough keyword research as soon as possible.

Honest thoughts on our startup

Hey y'all, we've recently started a marking push, overhauled the website, and our machine learning team has done drastic work to improve the reviews & auto pr descriptions. That being said, would love some candid feedback if you or your team members would consider using a tool like ours and if not, why not. Our company is Korbit AI and we do context based, AI code reviews and automated PR descriptions. While we have been getting more traction since some of the updates and larger companies are starting to sign up, I would really appreciate some honest opinions on why you \wouldn't\ try a tool like this in hopes we can use that info to alter marketing etc. This is not meant to be a promotion post, and legitimately looking to learn from other people rocking startups trying to build up a larger customer base etc. Any feedback is very much appreciated Thank you in advanced, Riley

I studied how 7 Founders found their first 100 customers for their businesses. Summarizing it here!

I am learning marketing, and so I combed through the internet to find specific advice that helped founders reach 100 users and not random Google answers. Here’s what I found: Llama Life by Marie Marie founder of Llama Life, a productivity app ($51.4K+ revenue) got her first 100 users using Snowballing effect. She shared great advice that I want to add here verbatim, “Need to think about what you have that you can leverage based on your current situation. eg..When you have no customers, think about where you can post to get the 1st customer eg Product Hunt. If you do well on PH, say you get #3 product of the day, then you post somewhere else saying ‘I got #3 product of the day’.. to get your next few customers. Maybe that post is on reddit with some learnings that you found. If the reddit post does well, then you might post it on Twitter, saying reddit did well and what learnings you got from that etc. or even if it doesn’t do well you can still post about it.” Another tip she shared is to build related products that get more viral than the product itself. These are small stand-alone sites that would appeal to the same target audience, but by nature, are more shareable. On these sites, you can mention your startup like: ‘brought to you by Llama Life’ and then provide a link to the main website if someone is interested. If one of those gets viral or ranks on Google, you’ll have a passive traffic source. Scraping bee by Pierre Pierre, founder of Scraping Bee, a web scraping tool has now reached $1.5M ARR. Pierre and his cofounder Kevin started with 10 Free Beta Users in 2019, and after 6 months asked them to take a paid subscription if they wanted to continue using the product. That’s how they got their first user within 50 minutes of that email. Then they listed it on dozens of startup directories but their core strategy was writing the best possible content for their target audience — Developers. 3 very successful pieces of content that worked were : A small tutorial on how to scrape single-page application An extensive general guide about web scraping without getting blocked A complete introduction to web scraping with Python They didn’t do content marketing for the sake of content marketing but deep-dived into the value they were providing their customer. One of these got 70K visits, and all this together got them to over 100 users. WePay by Bill Clerico Bill Clerico left his cushy corporate job to build WePay which was then acquired for $400M got his first users by using his app. He got his first users by using his app! The app was for group payments. So he hosted a Poker tournament at his house and collected payments only with his app. Then they hosted a barbecue for fraternity treasurers at San Jose State & helped them do their annual dues collection. Good old word-of-mouth marketing, that however, started with an event where they used what they made! RealWorld by Genevieve Genevieve — Founder and CEO of Realworld stands by the old-school advice of value giving. RealWorld is an app that helps GenZ navigate adulthood. So, before launching their direct-to-consumer platform, they had an educational course that they sold to college career centers and students. They already had a pipeline of adults who turned to Realworld for their adulting challenges. From there, she gained her first 100 followers. Saner dot ai by Austin Austin got 100 users from Reddit for his startup Saner.ai. Reddit hates advertising, and so his tips to market your startup on Reddit is to Write value-driven posts on your niche. Instead of writing posts, find posts where people are looking for solutions DM people facing problems that your SaaS solves. But instead of selling, ask about their problem to see if your product is a good fit Heartfelt posts about why you built it, aren’t gonna cut it To find posts and people, search Reddit with relevant keywords and join all the subreddits A Stock Portfolio Newsletter A financial investor got his first 100 paid newsletter subscribers for his stock portfolio newsletter. His tips : Don’t reinvent the wheel. Work what’s already working. He saw a company making $500M+ from stock picking newsletter, so decided to try that. Find the gaps in “already working” and leverage them. That newsletter did not have portfolios of advisors writing them. That was his USP. He added his own portfolio to his newsletter. Now to 100 users, he partnered with a guy running an investing website and getting good traffic. That guy got a cut of his revenue, in exchange. That one simple step got him to 100 users. Hypefury by Yannick and Samy Yannick and Samy from Hypefury, Twitter and Social Media Automation tool got their first beta testers and users from a paid community. They launched Hypefury there and asked if someone wanted to try it. A couple of people tried it and gave feedback. Samy conducted user interviews and product demos for them, And shared the reviews on Twitter. That alone, along with word-of-mouth marketing on Twitter got them their first 100 users. To conclude: Don’t reinvent the wheel, try what’s working. Find the gaps in what’s working, and leverage that. Instead of thinking about millions of customers, think about the first 10. Then first 100. Leverage what you have. Get the first 10 customers, then talk about this to get the next 100. Use your app. Find ways, events, and opportunities to use your app in front of people. And get them to use it. Write content not only for SEO but also to help people. It won’t work tomorrow, but it will work for years after it picks up. Leverage other sources of traffic by partnering up! Do things that don’t scale. I’m also doing SaaS marketing deep dives over 30 pieces of content. I'm posting here for the first time, so I'm not sure if it will stay or not, sorry if it doesn't. I've helped a SaaS grow from $19K to $100K MRR as a marketer in last 2 years, and now I wanna dive deep. Cheers! (1/30)

How Are You Using AI Agents to Automate Marketing/Sales Workflows?

AI agents powered by Generative AI are starting to transform how businesses handle marketing workflows and repetitive tasks, enabling automation that wasn’t possible with traditional tools. From campaign management to content personalization, the potential applications seem endless. I’m curious—what marketing processes are you currently looking to automate, and what challenges are you facing? Are there any Gen AI platforms or AI agent solutions that have impressed you or caught your attention recently? Looking forward to learning from this community and hearing about your experiences! 😊

Good at coding, bad at marketing. Summary

Hello. I posted a question on what to do if you are good at coding but bad at marketing four days ago, and I received so many responses and tips. The original post is here. I was really glad and excited to read comments. To return the favor to the community and add some more value, I’ve summarized all the comments I got on the original post. Here are they, with my personal comments on some of the advice I got. You’ll never believe it, but the most common advice was to learn. Really, the first and only thing you should start with if you’re bad at marketing is learning. Yet learning could be different. I highlighted 5 main areas. Educate yourself on general questions. Learn more about some basics. For example, start by finding out what the 4P’s of marketing are, and afterward, you’ll inevitably run into YouTube videos, seminars, Udemy courses, or any other resource that resonates with you on some ideas/avenues you could pursue. Read books and watch videos. There are tons of books on marketing and sales. People shared in the comments books by Dan Kennedy and “Cashvertising”, written by Drew Eric Whitman. (I’ve never heard of them, but already ordered on Amazon). For sales, the most common idea was to start with YouTube videos. For example, Alex Hormozi videos and Startup school delivered by Ycombinator videos. Check out Indie Hackers and scrutinize it for a piece of good advice from developers in the same situation. Also, there was advice to follow up and read some guy on Twitter. (Don't want to get unfairly banned from here, so won't post it) Educate yourself and hire a professional or find a co-founder to help you: Hire a seasoned marketer in this field to help you out. He will help you achieve cost-efficient scales. But it could be a real problem to find the right person. Marketing agencies are expensive. Try to look on LinkedIn or among your acquaintances. Look for professionals with credentials or extensive experience. Seek marketing referrals from startups of a similar size/industry. If you don't have those, try to bring a trusted/experienced marketer friend into the intro meetings to help assess whether the service provider knows what they are doing. Talented freelancers can often get the job done for less than hiring an entire agency. Look for a co-founder who is savvy in marketing, passionate, and ready to work hard towards mutual success. Educate and DIY Being the face of your business is way better than having faceless communication. The startup checklist is made based on the comments is next: At least have your product defined. Define your target audience. Set up the goals you want to achieve. Make domain expertise and understand the market and the direction of its development. The next stage is answering tricky questions: Have you created a business model? How do you plan to compete? What’s your unique selling point? How much do you plan to budget for marketing? Are you planning to work alone, or will you need other devs? Then you start thinking about clients… You need the exposure to truly understand the customer's pain points and build a product that they love. You need to think about how your clients would think, and you should tailor each step you take for them. Get feedback from your early users if you already have a product. Interview your potential customers to learn how they buy. This will help you narrow your choice of marketing channels. Get your product or service used by several startups and help them achieve their goals. Endorsements are very valuable marketing assets. You need a landing to validate your value proposition and start sending traffic, or you can run meta instant form campaigns... It would depend on the category of your startup. You need a benchmark of the competition's ads both in Meta and Google, blog posts, domain authority, their landing page, and average search volumes. Do affiliate marketing for your product since it's an effective strategy. Educate and use AI tools for dealing with marketing. Build an LLM-based product to automate marketing. (Sounds like an idea for a startup, right?) Learn following ChatGPT advice. In 1–3 months, you will be another updated person. Look at marketowl, an AI marketing department for startups and microbusinesses that have no budget or time to do marketing. It will automate the basic tasks your business needs, but it doesn't require your marketing expertise. Check out AI tools that are delivering very good marketing content (gocharlie, jasper, copyai). Educate yourself and run socials Start a blog or YouTube channel where you can share your expertise in coding or anything else you are good at and how your product simplifies life. Engage with your audience on social media platforms like Instagram and LinkedIn, where you can showcase your industry knowledge. Start a page on Twitter and an account on Reddit. Follow and read subreddits and pages where your potential customers are. Learn the pain from the inside. Do not simply promote, people will lose interest immediately. Start by taking focused time to create informational content, so people will eventually be naturally intrigued by what you do and want to support you when they start to “know” you. Educate your potential users about the value of your product. Create content based on what ideal customers are asking at the various stages of marketing. e.g., if they are at the beginning of the process, they may use basic language; if they are further down the process, maybe they’ll be specific. Try to get on podcasts and build as many social links as you can. In other words, don’t live in a shell! Post regularly, and eventually you’ll find sites or people that are willing to promote for you. I omitted here all personal help offers and newsletters, however you could find them in the original post. Hope that will be helpful!

Seeking advice from every type of business owner - if you have a moment & an opinion please chime in.

Hello everyone. I haven't started selling yet and wanted to get some insight from the community I'm trying to serve (that makes the most sense to me). So over the past couple months I've gotten into AI & Automation. I got a HighLevel account and went to town learning new things. I learned how to make automations and workflows that make running a business easier (my dad has been letting me use his concrete business as a guinea pig). I also learned how to build and train AI Chat Assistants. I want to start a service based business that uses AI & workflows to automate some of the customer service tasks & lead generation for business. What I'm seeking advice about are as follows: NICHE SELECTION: Part of me thinks I shouldn't niche down in the beginning and just take whoever comes and niche down once I find an industry I'm comfortable with. Another side thinks I should choose one. What is your opinion on niche selection in the beginning? PRICING: I know that pricing largely depends on the value I bring to the client, but I've seen people doing the same or similar things as I want to do and charging vastly different prices. From $300- $2,000. While I think these solutions could absolutely help companies get and retain new business and reduce some of the workload of their staff -- I'm not comfortable charging a high price until I've got enough experience and data to justify that. &#x200B; THESE ARE THE SERVICES I'M THINKING OF OFFERING: Customer Service Chat Assistant. This will be on the website as a "Live Chat". It also connects to Facebook Messenger & Google Business Chat. I'd train the chat assistant on everything related to the company; pertinent info (NAP, company mission, industry background), contact info, services / products / pricing, FAQs, current specials &/or discount codes (this can be changed monthly), how to handle upset clients, etc. It can also connect to a calendar like Google or Calendly so customers can make an appointment or schedule a call directly from the conversation. Missed Call Follow Up. If you're familiar with the platform HighLevel it's commonly called "Missed Call Text Back". The idea is that when a call is missed a text message is automatically fired to the prospect's phone saying something along the lines of "Hey this is \\\\\\ from \\\\\\\_. How can I help you?" and the business owner is alerted to the missed call via text notification. People have said they see a lot of success for their clients with this alone due to the instant follow up. I see a lot of people charging $300 /m. for this. My issues with this are: 1). The text fires automatically when the call is missed, but if the business owner isn't available to actually follow up and keep texting after the customer texts back, they will look inconsistent and bothersome. 2). Without context a prospect may wonder why you didn't answer when they called, but texted them instead. So my answer to these problems are #3. SMS Answering Service. It is essentially taking 2 + 1 and combining them. The missed call text goes out to the prospect, but with context on why they're being texted (because no one is available to take the call at the moment) and IF the prospect responds, a Customer Service Chat Assistant will take over the conversation with the goal of answering their questions and either getting them on the phone with the company via a call back OR helping them schedule an appointment. This offers a more consistent solution than just a text to the business owner / team & the prospect is contacted and helped (hopefully) before they have a chance to start calling a competitor. Lead Nurture / Lead Qualifying Sales Funnel. This one is more than just AI & automation. It's a full funnel. It can be for either Facebook or Google. The process is AD -> Landing Page -> AI Text Message Convo -> Booking/Schedule Call/ Appointment. Typically the ad will offer a lead magnet which they will claim on the LP by giving their information. After the form is submitted, they get a text message and begin a conversation with the AI. It can be trained to just walk them through a booking process, nurture a sale by answering questions and handling objections or to qualify leads. Lead qualification via text works well if you want to weed out who is serious versus who is curious. To be clear; I'd be making the ad, landing page & training the AI -- all parts of the funnel. For whichever service a few things are universal: \- All conversations; no matter what platform they're had on, all go to one inbox which is pretty helpful to see them all in one place. \- When scheduling / booking these can also collect payment. \- Tags can be added to keep track of how they came into the business and where they are in a sales pipeline. There are a lot of fun things I can do with these automations and I'm excited about learning more everyday. I'd really like to know what you think these services could be worth to a business. If you do reply please tell me what type of business you're in so I have an idea of what industries I should be looking towards. Thank you for any response I get as I know this was a long read! SN: I currently do digital marketing & web design as a freelancer.

I spent 6 months on building a web product, and got zero users. Here is my story.

Edit Thank you all so much for your time reading my story. Your support, feedback, criticism, and skepticism; all helped me a lot, and I couldn't appreciate it enough \^\_\^ I have stuff to post on Reddit very rarely, but I share how my project is going on, random stuff, and memes on X. Just in case few might want to keep in touch 👀 TL;DR I spent 6 months on a tool that currently has 0 users. Below is what I learned during my journey, sharing because I believe most mistakes are easily avoidable. Do not overestimate your product and assume it will be an exception to fundamental principles. Principles are there for a reason. Always look for validation before you start. Avoid building products with a low money-to-effort ratio/in very competitive fields. Unless you have the means, you probably won't make it. Pick a problem space, pick your target audience, and talk to them before thinking about a solution. Identify and match their pain points. Only then should you think of a solution. If people are not overly excited or willing to pay in advance for a discounted price, it might be a sign to rethink. Sell one and only one feature at a time. Avoid everything else. If people don't pay for that one core feature, no secondary feature will change their mind. Always spend twice as much time marketing as you do building. You will not get users if they don't know it exists. Define success metrics ("1000 users in 3 months" or "$6000 in the account at the end of 6 months") before you start. If you don't meet them, strongly consider quitting the project. If you can't get enough users to keep going, nothing else matters. VALIDATION, VALIDATION, VALIDATION. Success is not random, but most of our first products will not make a success story. Know when to admit failure, and move on. Even if a product of yours doesn't succeed, what you learned during its journey will turn out to be invaluable for your future. My story So, this is the story of a product that I’ve been working on for the last 6 months. As it's the first product I’ve ever built, after watching you all from the sidelines, I have learned a lot, made many mistakes, and did only a few things right. Just sharing what I’ve learned and some insights from my journey so far. I hope that this post will help you avoid the mistakes I made — most of which I consider easily avoidable — while you enjoy reading it, and get to know me a little bit more 🤓. A slow start after many years Summ isn’t the first product I really wanted to build. Lacking enough dev skills to even get started was a huge blocker for so many years. In fact, the first product I would’ve LOVED to build was a smart personal shopping assistant. I had this idea 4 years ago; but with no GPT, no coding skills, no technical co-founder, I didn’t have the means to make it happen. I still do not know if such a tool exists and is good enough. All I wanted was a tool that could make data-based predictions about when to buy stuff (“buy a new toothpaste every three months”) and suggest physical products that I might need or be strongly interested in. AFAIK, Amazon famously still struggles with the second one. Fast-forward a few years, I learned the very basics of HTML, CSS, and Vanilla JS. Still was not there to build a product; but good enough to code my design portfolio from scratch. Yet, I couldn’t imagine myself building a product using Vanilla JS. I really hated it, I really sucked at it. So, back to tutorial hell, and to learn about this framework I just heard about: React.React introduced so many new concepts to me. “Thinking in React” is a phrase we heard a lot, and with quite good reasons. After some time, I was able to build very basic tutorial apps, both in React, and React Native; but I have to say that I really hated coding for mobile. At this point, I was already a fan of productivity apps, and had a concept for a time management assistant app in my design portfolio. So, why not build one? Surely, it must be easy, since every coding tutorial starts with a todo app. ❌ WRONG! Building a basic todo app is easy enough, but building one good enough for a place in the market was a challenge I took and failed. I wasted one month on that until I abandoned the project for good. Even if I continued working on it, as the productivity landscape is overly competitive, I wouldn’t be able to make enough money to cover costs, assuming I make any. Since I was (and still am) in between jobs, I decided to abandon the project. 👉 What I learned: Do not start projects with a low ratio of money to effort and time. Example: Even if I get 500 monthly users, 200 of which are paid users (unrealistically high number), assuming an average subscription fee of $5/m (such apps are quite cheap, mostly due to the high competition), it would make me around $1000 minus any occurring costs. Any founder with a product that has 500 active users should make more. Even if it was relatively successful, due to the high competition, I wouldn’t make any meaningful money. PS: I use Todoist today. Due to local pricing, I pay less than $2/m. There is no way I could beat this competitive pricing, let alone the app itself. But, somehow, with a project that wasn’t even functional — let alone being an MVP — I made my first Wi-Fi money: Someone decided that the domain I preemptively purchased is worth something. By this point, I had already abandoned the project, certainly wasn’t going to renew the domain, was looking for a FT job, and a new project that I could work on. And out of nowhere, someone hands me some free money — who am I not to take it? Of course, I took it. The domain is still unused, no idea why 🤔. Ngl, I still hate the fact that my first Wi-Fi money came from this. A new idea worth pursuing? Fast-forward some weeks now. Around March, I got this crazy idea of building an email productivity tool. We all use emails, yet we all hate them. So, this must be fixed. Everyone uses emails, in fact everyone HAS TO use emails. So, I just needed to build a tool and wait for people to come. This was all, really. After all, the problem space is huge, there is enough room for another product, everyone uses emails, no need for any further validation, right? ❌ WRONG ONCE AGAIN! We all hear from the greatest in the startup landscape that we must validate our ideas with real people, yet at least some of us (guilty here 🥸) think that our product will be hugely successful and prove them to be an exception. Few might, but most are not. I certainly wasn't. 👉 Lesson learned: Always validate your ideas with real people. Ask them how much they’d pay for such a tool (not if they would). Much better if they are willing to pay upfront for a discount, etc. But even this comes later, keep reading. I think the difference between “How much” and “If” is huge for two reasons: (1) By asking them for “How much”, you force them to think in a more realistic setting. (2) You will have a more realistic idea on your profit margins. Based on my competitive analysis, I already had a solution in my mind to improve our email usage standards and email productivity (huge mistake), but I did my best to learn about their problems regarding those without pushing the idea too hard. The idea is this: Generate concise email summaries with suggested actions, combine them into one email, and send it at their preferred times. Save as much as time the AI you end up with allows. After all, everyone loves to save time. So, what kind of validation did I seek for? Talked with only a few people around me about this crazy, internet-breaking idea. The responses I got were, now I see, mediocre; no one got excited about it, just said things along the lines of “Cool idea, OK”. So, any reasonable person in this situation would think “Okay, not might not be working”, right? Well, I did not. I assumed that they were the wrong audience for this product, and there was this magical land of user segments waiting eagerly for my product, yet unknowingly. To this day, I still have not reached this magical place. Perhaps, it didn’t exist in the first place. If I cannot find it, whether it exists or not doesn’t matter. I am certainly searching for it. 👉 What I should have done: Once I decide on a problem space (time management, email productivity, etc.), I should decide on my potential user segments, people who I plan to sell my product to. Then I should go talk to those people, ask them about their pains, then get to the problem-solving/ideation phase only later. ❗️ VALIDATION COMES FROM THE REALITY OUTSIDE. What validation looks like might change from product to product; but what invalidation looks like is more or less the same for every product. Nico Jeannen told me yesterday “validation = money in the account” on Twitter. This is the ultimate form of validation your product could get. If your product doesn’t make any money, then something is invalidated by reality: Your product, you, your idea, who knows? So, at this point, I knew a little bit of Python from spending some time in tutorial hell a few years ago, some HTML/CSS/JS, barely enough React to build a working app. React could work for this project, but I needed easy-to-implement server interactivity. Luckily, around this time, I got to know about this new gen of indie hackers, and learned (but didn’t truly understand) about their approach to indie hacking, and this library called Nextjs. How good Next.js still blows my mind. So, I was back to tutorial hell once again. But, this time, with a promise to myself: This is the last time I would visit tutorial hell. Time to start building this "ground-breaking idea" Learning the fundamentals of Next.js was easier than learning of React unsurprisingly. Yet, the first time I managed to run server actions on Next.js was one of the rarest moments that completely blew my mind. To this day, I reject the idea that it is something else than pure magic under its hood. Did I absolutely need Nextjs for this project though? I do not think so. Did it save me lots of time? Absolutely. Furthermore, learning Nextjs will certainly be quite helpful for other projects that I will be tackling in the future. Already got a few ideas that might be worth pursuing in the head in case I decide to abandon Summ in the future. Fast-forward few weeks again: So, at this stage, I had a barely working MVP-like product. Since the very beginning, I spent every free hour (and more) on this project as speed is essential. But, I am not so sure it was worth it to overwork in retrospect. Yet, I know I couldn’t help myself. Everything is going kinda smooth, so what’s the worst thing that could ever happen? Well, both Apple and Google announced their AIs (Apple Intelligence and Google Gemini, respectively) will have email summarization features for their products. Summarizing singular emails is no big deal, after all there were already so many similar products in the market. I still think that what truly matters is a frictionless user experience, and this is why I built this product in a certain way: You spend less than a few minutes setting up your account, and you get to enjoy your email summaries, without ever visiting its website again. This is still a very cool concept I really like a lot. So, at this point: I had no other idea that could be pursued, already spent too much time on this project. Do I quit or not? This was the question. Of course not. I just have to launch this product as quickly as possible. So, I did something right, a quite rare occurrence I might say: Re-planned my product, dropped everything secondary to the core feature immediately (save time on reading emails), tried launching it asap. 👉 Insight: Sell only one core feature at one time. Drop anything secondary to this core feature. Well, my primary occupation is product design. So one would expect that a product I build must have stellar design. I considered any considerable time spent on design at this stage would be simply wasted. I still think this is both true and wrong: True, because if your product’s core benefits suck, no one will care about your design. False, because if your design looks amateurish, no one will trust you and your product. So, I always targeted an average level design with it and the way this tool works made it quite easy as I had to design only 2 primary pages: Landing page and user portal (which has only settings and analytics pages). However, even though I knew spending time on design was not worth much of my time, I got a bit “greedy”: In fact, I redesigned those pages three times, and still ended up with a so-so design that I am not proud of. 👉 What I would do differently: Unless absolutely necessary, only one iteration per stage as long as it works. This, in my mind, applies to everything. If your product’s A feature works, then no need to rewrite it from scratch for any reason, or even refactor it. When your product becomes a success, and you absolutely need that part of your codebase to be written, do so, but only then. Ready to launch, now is th etime for some marketing, right? By July 26, I already had a “launchable” product that barely works (I marked this date on a Notion docs, this is how I know). Yet, I had spent almost no time on marketing, sales, whatever. After all, “You build and they will come”. Did I know that I needed marketing? Of course I did, but knowingly didn’t. Why, you might ask. Well, from my perspective, it had to be a dev-heavy product; meaning that you spend most of your time on developing it, mostly coding skills. But, this is simply wrong. As a rule of thumb, as noted by one of the greatests, Marc Louvion, you should spend at least twice of the building time on marketing. ❗️ Time spent on building \* 2 people don’t know your product > they don’t use your product > you don’t get users > you don’t make money Easy as that. Following the same reasoning, a slightly different approach to planning a project is possible. Determine an approximate time to complete the project with a high level project plan. Let’s say 6 months. By the reasoning above, 2 months should go into building, and 4 into marketing. If you need 4 months for building instead of 2, then you need 8 months of marketing, which makes the time to complete the project 12 months. If you don’t have that much time, then quit the project. When does a project count as completed? Well, in reality, never. But, I think we have to define success conditions even before we start for indie projects and startups; so we know when to quit when they are not met. A success condition could look like “Make $6000 in 12 months” or “Have 3000 users in 6 months”. It all depends on the project. But, once you set it, it should be set in stone: You don’t change it unless absolutely necessary. I suspect there are few principles that make a solopreneur successful; and knowing when to quit and when to continue is definitely one of them. Marc Louvion is famously known for his success, but he got there after failing so many projects. To my knowledge, the same applies to Nico Jeannen, Pieter Levels, or almost everyone as well. ❗️ Determining when to continue even before you start will definitely help in the long run. A half-aed launch Time-leap again. Around mid August, I “soft launched” my product. By soft launch, I mean lazy marketing. Just tweeting about it, posting it on free directories. Did I get any traffic? Surely I did. Did I get any users? Nope. Only after this time, it hit me: “Either something is wrong with me, or with this product” Marketing might be a much bigger factor for a project’s success after all. Even though I get some traffic, not convincing enough for people to sign up even for a free trial. The product was still perfect in my eyes at the time (well, still is ^(\_),) so the right people are not finding my product, I thought. Then, a question that I should have been asking at the very first place, one that could prevent all these, comes to my mind: “How do even people search for such tools?” If we are to consider this whole journey of me and my so-far-failed product to be an already destined failure, one metric suffices to show why. Search volume: 30. Even if people have such a pain point, they are not looking for email summaries. So, almost no organic traffic coming from Google. But, as a person who did zero marketing on this or any product, who has zero marketing knowledge, who doesn’t have an audience on social media, there is not much I could do. Finally, it was time to give up. Or not… In my eyes, the most important element that makes a founder (solo or not) successful (this, I am not by any means) is to solve problems. ❗️ So, the problem was this: “People are not finding my product by organic search” How do I make sure I get some organic traffic and gets more visibility? Learn digital marketing and SEO as much as I can within very limited time. Thankfully, without spending much time, I came across Neil Patel's YT channel, and as I said many times, it is an absolute gold mine. I learned a lot, especially about the fundamentals, and surely it will be fruitful; but there is no magic trick that could make people visit your website. SEO certainly helps, but only when people are looking for your keywords. However, it is truly a magical solution to get in touch with REAL people that are in your user segments: 👉 Understand your pains, understand their problems, help them to solve them via building products. I did not do this so far, have to admit. But, in case you would like to have a chat about your email usage, and email productivity, just get in touch; I’d be delighted to hear about them. Getting ready for a ProductHunt launch The date was Sept 1. And I unlocked an impossible achievement: Running out of Supabase’s free plan’s Egres limit while having zero users. I was already considering moving out of their Cloud server and managing a Supabase CLI service on my Hetzner VPS for some time; but never ever suspected that I would have to do this quickly. The cheapest plan Supabase offers is $25/month; yet, at that point, I am in between jobs for such a long time, basically broke, and could barely afford that price. One or two months could be okay, but why pay for it if I will eventually move out of their Cloud service? So, instead of paying $25, I spent two days migrating out of Supabase Cloud. Worth my time? Definitely not. But, when you are broke, you gotta do stupid things. This was the first time that I felt lucky to have zero users: I have no idea how I would manage this migration if I had any. I think this is one of the core tenets of an indie hacker: Controlling their own environment. I can’t remember whose quote this is, but I suspect it was Naval: Entrepreneurs have an almost pathological need to control their own fate. They will take any suffering if they can be in charge of their destiny, and not have it in somebody else’s hands. What’s truly scary is, at least in my case, we make people around us suffer at the expense of our attempting to control our own fates. I know this period has been quite hard on my wife as well, as I neglected her quite a bit, but sadly, I know that this will happen again. It is something that I can barely help with. Still, so sorry. After working the last two weeks on a ProductHunt Launch, I finally launched it this Tuesday. Zero ranking, zero new users, but 36 kind people upvoted my product, and many commented and provided invaluable feedback. I couldn't be more grateful for each one of them 🙏. Considering all these, what lies in the future of Summ though? I have no idea, to be honest. On one hand, I have zero users, have no job, no income. So, I need a way to make money asap. On the other hand, the whole idea of it revolves around one core premise (not an assumption) that I am not so willing to share; and I couldn’t have more trust in it. This might not be the best iteration of it, however I certainly believe that email usage is one of the best problem spaces one could work on. 👉 But, one thing is for certain: I need to get in touch with people, and talk with them about this product I built so far. In fact, this is the only item on my agenda. Nothing else will save my brainchild <3. Below are some other insights and notes that I got during my journey; as they do not 100% fit into this story, I think it is more suitable to list them here. I hope you enjoyed reading this. Give Summ a try, it comes with a generous free trial, no credit card required. Some additional notes and insights: Project planning is one of the most underestimated skills for solopreneurs. It saves you enormous time, and helps you to keep your focus up. Building B2C products beats building B2B products. Businesses are very willing to pay big bucks if your product helps them. On the other hand, spending a few hours per user who would pay $5/m probably is not worth your time. It doesn’t matter how brilliant your product is if no one uses it. If you cannot sell a product in a certain category/niche (or do not know how to sell it), it might be a good idea not to start a project in it. Going after new ideas and ventures is quite risky, especially if you don’t know how to market it. On the other hand, an already established category means that there is already demand. Whether this demand is sufficient or not is another issue. As long as there is enough demand for your product to fit in, any category/niche is good. Some might be better, some might be worse. Unless you are going hardcore B2B, you will need people to find your product by means of organic search. Always conduct thorough keyword research as soon as possible.

Month 2 of building my startup after being laid off - $200 in revenue and 4 (actual) paying customers

In September 2024, I got laid off from my Silicon Valley job. It fucking sucked. I took a day to be sad, then got to work - I'm not one to wallow, I prefer action. Updated my resume, hit up my network, started interviewing. During this time, I had a realization - I'm tired of depending on a single income stream. I needed to diversify. Then it hit me: I literally work with RAG (retrieval augmented generation) in AI. Why not use this knowledge to help small businesses reduce their customer service load and boost sales? One month later, Answer HQ 0.5 (the MVP) was in the hands of our first users (shoutout to these alpha testers - their feedback shaped everything). By month 2, Answer HQ 1.0 launched with four paying customers, and growing. You're probably thinking - great, another chatbot. Yes, Answer HQ is a chatbot at its core. But here's the difference: it actually works. Our paying customers are seeing real results in reducing support load, plus it has something unique - it actively drives sales by turning customer questions into conversions. How? The AI doesn't just answer questions, it naturally recommends relevant products and content (blogs, social media, etc). Since I'm targeting small business owners (who usually aren't tech wizards) and early startups, Answer HQ had to be dead simple to set up. Here's my onboarding process - just 4 steps. I've checked out competitors like Intercom and Crisp, and I can say this: if my non-tech fiancée can set up an assistant on her blog in minutes, anyone can. Key learnings so far: Building in public is powerful. I shared my journey on Threads and X, and the support for a solo founder has been amazing. AI dev tools (Cursor, Claude Sonnet 3.5) have made MVP development incredibly accessible. You can get a working prototype frontend ready in days. I don't see how traditional no-code tools can survive in this age. But.. for a production-ready product? You still need dev skills and background. Example: I use Redis for super-fast loading of configs and themes. An AI won't suggest this optimization unless you know to ask for it. Another example: Cursor + Sonnet 3.5 struggles with code bases with many files and dependencies. It will change things you don't want it to change. Unless you can read code + understand it + know what needs to be changed and not changed, you'll easily run into upper limits of what prompting alone can do. I never mention "artificial intelligence" "AI" "machine learning" or any of these buzzwords once in my copy in my landing page, docs, product, etc. There is no point. Your customers do not care that something has AI in it. AI is not the product. Solving their pain points and problems is the product. AI is simply a tool of many tools like databases, APIs, caching, system design, etc. Early on, I personally onboarded every user through video calls. Time-consuming? Yes. But it helped me deeply understand their pain points and needs. I wasn't selling tech - I was showing them solutions to their problems. Tech stack: NextJS/React/Tailwind/shadcn frontend, Python FastAPI backend. Using Supabase Postgres, Upstash Redis, and Pinecone for different data needs. Hosted on Vercel and Render.com. Customer growth: Started with one alpha tester who saw such great results (especially in driving e-commerce sales) that he insisted on paying for a full year to keep me motivated. This led to two monthly customers, then a fourth annual customer after I raised prices. My advisor actually pushed me to raise prices again, saying I was undercharging for the value provided. I have settled on my final pricing now. I am learning so much. Traditionally, I have a software development and product management background. I am weak in sales and marketing. Building that app, designing the architecture, talking to customers, etc, these are all my strong suits. I enjoy doing it too. But now I need to improve on my ability to market the startup and really start learning things like SEO, content marketing, cold outreach, etc. I enjoying learning new skills. Happy to answer any questions about the journey so far!

My app has gone viral and I grew from 1k users (take 5months) to 100k user in 5 days

I've always dreamt of building an online side business where I can build once and sell to millions. I love that business model but have never dreamt that I can achieve that, given that I am not a programmer in my career. I have been following side hustle school and some other business podcast for the past years as a drive and motivation to create my own business.  Over the years, I've delve a little on to web development using WordPress and in the hope of earning some money from that. I learnt in the hard way but is a good learning story and journey. I realised that what you put all your efforts building and excited for doesn't mean anything for anyone else and also learnt the importance of UI UX.  Fast forward to 5 months ago (July 2024), I've came across several low code app builder. With the help of the low code tools in combination with chatgpt, I've finally launched my first mobile app - Rolly: AI Money Tracker. But the business challenges doesn't end here, but it's just the beginning. I got no experience and skills on marketing but I've got my drive and passion that keep propelling me forward. By keep listening on people sharing their journey, looking at different apps to brainstorm etc, I've managed to now grow my user base from 1k (in 5 months) to 100k (in 5days). What's happening was my app somehow got viral in Vietnam when people are getting interest funny comments from my AI during entering the transaction and it has been sharing around in the social media and even featured on the news. What a crazy journey as the inflow of users has been too sudden, my server has been down for a few times until I progressively upgrade it until it got stable these couple of days. As for my advice to people dreaming the to be entreprenuer - Don't overthinking about all the problems you will face before starting. You will encounter hundreds of problems along the way and you just need to solve them one by one. You will never start if you think about what's not working and there will never be an answer for everything - even I don't have an answer for everything now.

The Evolution of Financial Technology: How CAs Are Embracing the Digital Age

The Evolution of Financial Technology: How CAs Are Embracing the Digital Age Introduction In an era characterized by rapid technological advancements, the field of finance is undergoing a transformative journey. The emergence of financial technology, or fintech, is reshaping the way businesses manage their finances, and Chartered Accountants (CAs) are at the forefront of this evolution. In this blog post, we'll explore how CAs are embracing fintech and leveraging its potential to enhance financial management, analysis, and advisory services. Fintech's Impact on Financial Services Fintech encompasses a wide range of technologies that leverage data analytics, artificial intelligence, blockchain, and automation to improve financial services. For CAs, this means new tools to streamline processes, enhance decision-making, and offer innovative solutions to clients. Automation of Routine Tasks CAs are increasingly using automation tools to handle repetitive tasks such as data entry, reconciliations, and transaction processing. This not only reduces the risk of human error but also frees up CAs to focus on higher-value tasks like strategic planning and analysis. Advanced Data Analytics Data analytics tools enable CAs to extract meaningful insights from large volumes of financial data. These insights can help businesses identify trends, anticipate risks, and make informed decisions to drive growth. Real-Time Financial Reporting Fintech enables CAs to provide clients with real-time financial reporting, giving businesses immediate access to critical information. This enhances transparency and empowers business owners to respond quickly to changing market conditions. Enhancing Audit Efficiency Fintech tools are revolutionizing the audit process. CAs can use AI-powered algorithms to analyze vast amounts of data, detect anomalies, and identify potential instances of fraud more efficiently. Personalized Financial Planning CAs can leverage fintech to offer personalized financial planning services. With access to detailed financial data, CAs can create tailored strategies that align with a client's unique goals and circumstances. Strengthening Cybersecurity As businesses become more reliant on digital tools, cybersecurity becomes paramount. CAs are playing a critical role in advising clients on cybersecurity measures to protect sensitive financial information. Virtual CFO Services Fintech enables CAs to offer virtual CFO services to startups and small businesses. Through digital platforms, CAs can provide expert financial advice and guidance remotely, making their expertise accessible to a wider range of clients. Embracing Blockchain Technology Blockchain's potential for secure and transparent record-keeping is of interest to CAs. They can explore applications in supply chain finance, smart contracts, and even audit trail verification. Continuous Learning in Fintech CAs recognize the importance of staying updated with fintech trends. Many are investing in continuous learning to master the use of new tools and technologies that can optimize their services. Conclusion The integration of fintech into the realm of finance is reshaping the landscape in profound ways. CAs are embracing these technologies to elevate their roles from traditional number-crunchers to strategic advisors, equipped with tools that enhance efficiency, accuracy, and insight. As fintech continues to evolve, CAs will remain pivotal in guiding businesses through the ever-changing financial landscape, leveraging technology to drive growth, innovation, and success. Find the top verified CA in your City Feel free to let me know if you'd like more blogs on different topics or if you have specific requirements for the content.

Seeking Feedback: Would a No-Code AI Solution Benefit Your Business?

Hi, fellow small business owners. I'm currently working on an AI startup, with the goal of providing small businesses a seamless and intuitive way to integrate AI into operations without the need for any coding or tech expertise. We're designing an auto machine learning application that's user-friendly and tailored to the unique needs of small businesses. Before we scale, I would really appreciate any insights and feedback. Here are a few questions that would be helpful to get answers to: Pain Points: Are there specific tasks or processes in your operations that you think could be automated or enhanced using AI? This could be anything from customer service chatbots, inventory management, sales forecasting, or anything else you might think of. Features: What features would you want in a no-code AI solution? Perhaps easy integration with existing software? Drag-and-drop model training? Pre-built models for common tasks? Training & Support: How important would training and support be for you in implementing and using an AI solution? Would you prefer video tutorials, live-chat support, or hands-on workshops? Pricing: Would you be willing to invest in such a tool? If so, what would be a reasonable price point for you? We're considering a tiered model based on usage, with a potential starting point of $X/month. Does that sound feasible? Trial Period: Would a free trial period be beneficial for you? How long would you need to assess the tool's impact on your business? Data Concerns: How comfortable are you with sharing data with an AI application? What privacy and security measures would make you feel at ease? Your feedback is really useful. We're building this solution with you in mind, and your insights will guide the next steps. In appreciation for your time and input, we're offering a special discount for early adopters from this community once we launch. Just drop a comment below, and I'll make sure to get in touch when we are ready. Many Thanks, Chris Parker

Idea Validation Post: Seeking Feedback on My AI-Driven Quick Launch Application! 🚀

Hey Members! I’m excited to share an idea for a new application I’m planning to build: Quick Launch . This AI-driven platform is designed to assist solopreneurs or anyone with an idea in launching their Minimum Viable Products (MVPs) by taking on the roles of the entire team needed for the process. Goal: Assistance in quickly moving from Idea to MVP Before I dive into the details, I’d love to hear your thoughts and feedback. Key Features: Product Creation: From Idea to Product Detailing AI-Generated Q&A: Real-time questions generation one-at-a-time to define the product requirements based on their knowledge levels to convert an Idea into a Product. Market Research Reports: In-depth analysis that identifies product-market fit, competitive landscape, and potential marketing strategies. Sentiment Analysis: Evaluation of user feedback and reactions across multiple subreddits to gauge public opinion on ideas. Product Development: Product Detailing to Actual Product User Story Generation: Identification and creation of comprehensive user stories, tasks, and sub-tasks to facilitate development. AI Project Management: AI agents assume roles of project managers and UI/UX designers to streamline product detailing and development. Integration Capabilities: Seamless integration with popular project management tools like Jira, Asana, and Trello for better workflow management. Target Audience: Solopreneurs: Individuals looking to bring their business ideas to life without extensive resources. Indie Hackers: Entrepreneurs focused on building small projects or startups with minimal overhead. Idea Validators: Anyone with a concept seeking initial validation and market feedback before committing significant resources. If you’re interested in learning more, check out our teaser website: Quick Launch Discussion Question: What features would you find most valuable in an application like this? Are there specific pain points you face when launching an MVP? Your insights would be incredibly helpful as I refine this idea! Looking forward to your thoughts! 🙌

I spent 6 months on building a web product, and got zero users. Here is my story.

Edit Thank you all so much for your time reading my story. Your support, feedback, criticism, and skepticism; all helped me a lot, and I couldn't appreciate it enough \^\_\^ I have stuff to post on Reddit very rarely, but I share how my project is going on, random stuff, and memes on X. Just in case few might want to keep in touch 👀 TL;DR I spent 6 months on a tool that currently has 0 users. Below is what I learned during my journey, sharing because I believe most mistakes are easily avoidable. Do not overestimate your product and assume it will be an exception to fundamental principles. Principles are there for a reason. Always look for validation before you start. Avoid building products with a low money-to-effort ratio/in very competitive fields. Unless you have the means, you probably won't make it. Pick a problem space, pick your target audience, and talk to them before thinking about a solution. Identify and match their pain points. Only then should you think of a solution. If people are not overly excited or willing to pay in advance for a discounted price, it might be a sign to rethink. Sell one and only one feature at a time. Avoid everything else. If people don't pay for that one core feature, no secondary feature will change their mind. Always spend twice as much time marketing as you do building. You will not get users if they don't know it exists. Define success metrics ("1000 users in 3 months" or "$6000 in the account at the end of 6 months") before you start. If you don't meet them, strongly consider quitting the project. If you can't get enough users to keep going, nothing else matters. VALIDATION, VALIDATION, VALIDATION. Success is not random, but most of our first products will not make a success story. Know when to admit failure, and move on. Even if a product of yours doesn't succeed, what you learned during its journey will turn out to be invaluable for your future. My story So, this is the story of a product that I’ve been working on for the last 6 months. As it's the first product I’ve ever built, after watching you all from the sidelines, I have learned a lot, made many mistakes, and did only a few things right. Just sharing what I’ve learned and some insights from my journey so far. I hope that this post will help you avoid the mistakes I made — most of which I consider easily avoidable — while you enjoy reading it, and get to know me a little bit more 🤓. A slow start after many years Summ isn’t the first product I really wanted to build. Lacking enough dev skills to even get started was a huge blocker for so many years. In fact, the first product I would’ve LOVED to build was a smart personal shopping assistant. I had this idea 4 years ago; but with no GPT, no coding skills, no technical co-founder, I didn’t have the means to make it happen. I still do not know if such a tool exists and is good enough. All I wanted was a tool that could make data-based predictions about when to buy stuff (“buy a new toothpaste every three months”) and suggest physical products that I might need or be strongly interested in. AFAIK, Amazon famously still struggles with the second one. Fast-forward a few years, I learned the very basics of HTML, CSS, and Vanilla JS. Still was not there to build a product; but good enough to code my design portfolio from scratch. Yet, I couldn’t imagine myself building a product using Vanilla JS. I really hated it, I really sucked at it. So, back to tutorial hell, and to learn about this framework I just heard about: React.React introduced so many new concepts to me. “Thinking in React” is a phrase we heard a lot, and with quite good reasons. After some time, I was able to build very basic tutorial apps, both in React, and React Native; but I have to say that I really hated coding for mobile. At this point, I was already a fan of productivity apps, and had a concept for a time management assistant app in my design portfolio. So, why not build one? Surely, it must be easy, since every coding tutorial starts with a todo app. ❌ WRONG! Building a basic todo app is easy enough, but building one good enough for a place in the market was a challenge I took and failed. I wasted one month on that until I abandoned the project for good. Even if I continued working on it, as the productivity landscape is overly competitive, I wouldn’t be able to make enough money to cover costs, assuming I make any. Since I was (and still am) in between jobs, I decided to abandon the project. 👉 What I learned: Do not start projects with a low ratio of money to effort and time. Example: Even if I get 500 monthly users, 200 of which are paid users (unrealistically high number), assuming an average subscription fee of $5/m (such apps are quite cheap, mostly due to the high competition), it would make me around $1000 minus any occurring costs. Any founder with a product that has 500 active users should make more. Even if it was relatively successful, due to the high competition, I wouldn’t make any meaningful money. PS: I use Todoist today. Due to local pricing, I pay less than $2/m. There is no way I could beat this competitive pricing, let alone the app itself. But, somehow, with a project that wasn’t even functional — let alone being an MVP — I made my first Wi-Fi money: Someone decided that the domain I preemptively purchased is worth something. By this point, I had already abandoned the project, certainly wasn’t going to renew the domain, was looking for a FT job, and a new project that I could work on. And out of nowhere, someone hands me some free money — who am I not to take it? Of course, I took it. The domain is still unused, no idea why 🤔. Ngl, I still hate the fact that my first Wi-Fi money came from this. A new idea worth pursuing? Fast-forward some weeks now. Around March, I got this crazy idea of building an email productivity tool. We all use emails, yet we all hate them. So, this must be fixed. Everyone uses emails, in fact everyone HAS TO use emails. So, I just needed to build a tool and wait for people to come. This was all, really. After all, the problem space is huge, there is enough room for another product, everyone uses emails, no need for any further validation, right? ❌ WRONG ONCE AGAIN! We all hear from the greatest in the startup landscape that we must validate our ideas with real people, yet at least some of us (guilty here 🥸) think that our product will be hugely successful and prove them to be an exception. Few might, but most are not. I certainly wasn't. 👉 Lesson learned: Always validate your ideas with real people. Ask them how much they’d pay for such a tool (not if they would). Much better if they are willing to pay upfront for a discount, etc. But even this comes later, keep reading. I think the difference between “How much” and “If” is huge for two reasons: (1) By asking them for “How much”, you force them to think in a more realistic setting. (2) You will have a more realistic idea on your profit margins. Based on my competitive analysis, I already had a solution in my mind to improve our email usage standards and email productivity (huge mistake), but I did my best to learn about their problems regarding those without pushing the idea too hard. The idea is this: Generate concise email summaries with suggested actions, combine them into one email, and send it at their preferred times. Save as much as time the AI you end up with allows. After all, everyone loves to save time. So, what kind of validation did I seek for? Talked with only a few people around me about this crazy, internet-breaking idea. The responses I got were, now I see, mediocre; no one got excited about it, just said things along the lines of “Cool idea, OK”. So, any reasonable person in this situation would think “Okay, not might not be working”, right? Well, I did not. I assumed that they were the wrong audience for this product, and there was this magical land of user segments waiting eagerly for my product, yet unknowingly. To this day, I still have not reached this magical place. Perhaps, it didn’t exist in the first place. If I cannot find it, whether it exists or not doesn’t matter. I am certainly searching for it. 👉 What I should have done: Once I decide on a problem space (time management, email productivity, etc.), I should decide on my potential user segments, people who I plan to sell my product to. Then I should go talk to those people, ask them about their pains, then get to the problem-solving/ideation phase only later. ❗️ VALIDATION COMES FROM THE REALITY OUTSIDE. What validation looks like might change from product to product; but what invalidation looks like is more or less the same for every product. Nico Jeannen told me yesterday “validation = money in the account” on Twitter. This is the ultimate form of validation your product could get. If your product doesn’t make any money, then something is invalidated by reality: Your product, you, your idea, who knows? So, at this point, I knew a little bit of Python from spending some time in tutorial hell a few years ago, some HTML/CSS/JS, barely enough React to build a working app. React could work for this project, but I needed easy-to-implement server interactivity. Luckily, around this time, I got to know about this new gen of indie hackers, and learned (but didn’t truly understand) about their approach to indie hacking, and this library called Nextjs. How good Next.js still blows my mind. So, I was back to tutorial hell once again. But, this time, with a promise to myself: This is the last time I would visit tutorial hell. Time to start building this "ground-breaking idea" Learning the fundamentals of Next.js was easier than learning of React unsurprisingly. Yet, the first time I managed to run server actions on Next.js was one of the rarest moments that completely blew my mind. To this day, I reject the idea that it is something else than pure magic under its hood. Did I absolutely need Nextjs for this project though? I do not think so. Did it save me lots of time? Absolutely. Furthermore, learning Nextjs will certainly be quite helpful for other projects that I will be tackling in the future. Already got a few ideas that might be worth pursuing in the head in case I decide to abandon Summ in the future. Fast-forward few weeks again: So, at this stage, I had a barely working MVP-like product. Since the very beginning, I spent every free hour (and more) on this project as speed is essential. But, I am not so sure it was worth it to overwork in retrospect. Yet, I know I couldn’t help myself. Everything is going kinda smooth, so what’s the worst thing that could ever happen? Well, both Apple and Google announced their AIs (Apple Intelligence and Google Gemini, respectively) will have email summarization features for their products. Summarizing singular emails is no big deal, after all there were already so many similar products in the market. I still think that what truly matters is a frictionless user experience, and this is why I built this product in a certain way: You spend less than a few minutes setting up your account, and you get to enjoy your email summaries, without ever visiting its website again. This is still a very cool concept I really like a lot. So, at this point: I had no other idea that could be pursued, already spent too much time on this project. Do I quit or not? This was the question. Of course not. I just have to launch this product as quickly as possible. So, I did something right, a quite rare occurrence I might say: Re-planned my product, dropped everything secondary to the core feature immediately (save time on reading emails), tried launching it asap. 👉 Insight: Sell only one core feature at one time. Drop anything secondary to this core feature. Well, my primary occupation is product design. So one would expect that a product I build must have stellar design. I considered any considerable time spent on design at this stage would be simply wasted. I still think this is both true and wrong: True, because if your product’s core benefits suck, no one will care about your design. False, because if your design looks amateurish, no one will trust you and your product. So, I always targeted an average level design with it and the way this tool works made it quite easy as I had to design only 2 primary pages: Landing page and user portal (which has only settings and analytics pages). However, even though I knew spending time on design was not worth much of my time, I got a bit “greedy”: In fact, I redesigned those pages three times, and still ended up with a so-so design that I am not proud of. 👉 What I would do differently: Unless absolutely necessary, only one iteration per stage as long as it works. This, in my mind, applies to everything. If your product’s A feature works, then no need to rewrite it from scratch for any reason, or even refactor it. When your product becomes a success, and you absolutely need that part of your codebase to be written, do so, but only then. Ready to launch, now is th etime for some marketing, right? By July 26, I already had a “launchable” product that barely works (I marked this date on a Notion docs, this is how I know). Yet, I had spent almost no time on marketing, sales, whatever. After all, “You build and they will come”. Did I know that I needed marketing? Of course I did, but knowingly didn’t. Why, you might ask. Well, from my perspective, it had to be a dev-heavy product; meaning that you spend most of your time on developing it, mostly coding skills. But, this is simply wrong. As a rule of thumb, as noted by one of the greatests, Marc Louvion, you should spend at least twice of the building time on marketing. ❗️ Time spent on building \* 2 people don’t know your product > they don’t use your product > you don’t get users > you don’t make money Easy as that. Following the same reasoning, a slightly different approach to planning a project is possible. Determine an approximate time to complete the project with a high level project plan. Let’s say 6 months. By the reasoning above, 2 months should go into building, and 4 into marketing. If you need 4 months for building instead of 2, then you need 8 months of marketing, which makes the time to complete the project 12 months. If you don’t have that much time, then quit the project. When does a project count as completed? Well, in reality, never. But, I think we have to define success conditions even before we start for indie projects and startups; so we know when to quit when they are not met. A success condition could look like “Make $6000 in 12 months” or “Have 3000 users in 6 months”. It all depends on the project. But, once you set it, it should be set in stone: You don’t change it unless absolutely necessary. I suspect there are few principles that make a solopreneur successful; and knowing when to quit and when to continue is definitely one of them. Marc Louvion is famously known for his success, but he got there after failing so many projects. To my knowledge, the same applies to Nico Jeannen, Pieter Levels, or almost everyone as well. ❗️ Determining when to continue even before you start will definitely help in the long run. A half-aed launch Time-leap again. Around mid August, I “soft launched” my product. By soft launch, I mean lazy marketing. Just tweeting about it, posting it on free directories. Did I get any traffic? Surely I did. Did I get any users? Nope. Only after this time, it hit me: “Either something is wrong with me, or with this product” Marketing might be a much bigger factor for a project’s success after all. Even though I get some traffic, not convincing enough for people to sign up even for a free trial. The product was still perfect in my eyes at the time (well, still is ^(\_),) so the right people are not finding my product, I thought. Then, a question that I should have been asking at the very first place, one that could prevent all these, comes to my mind: “How do even people search for such tools?” If we are to consider this whole journey of me and my so-far-failed product to be an already destined failure, one metric suffices to show why. Search volume: 30. Even if people have such a pain point, they are not looking for email summaries. So, almost no organic traffic coming from Google. But, as a person who did zero marketing on this or any product, who has zero marketing knowledge, who doesn’t have an audience on social media, there is not much I could do. Finally, it was time to give up. Or not… In my eyes, the most important element that makes a founder (solo or not) successful (this, I am not by any means) is to solve problems. ❗️ So, the problem was this: “People are not finding my product by organic search” How do I make sure I get some organic traffic and gets more visibility? Learn digital marketing and SEO as much as I can within very limited time. Thankfully, without spending much time, I came across Neil Patel's YT channel, and as I said many times, it is an absolute gold mine. I learned a lot, especially about the fundamentals, and surely it will be fruitful; but there is no magic trick that could make people visit your website. SEO certainly helps, but only when people are looking for your keywords. However, it is truly a magical solution to get in touch with REAL people that are in your user segments: 👉 Understand your pains, understand their problems, help them to solve them via building products. I did not do this so far, have to admit. But, in case you would like to have a chat about your email usage, and email productivity, just get in touch; I’d be delighted to hear about them. Getting ready for a ProductHunt launch The date was Sept 1. And I unlocked an impossible achievement: Running out of Supabase’s free plan’s Egres limit while having zero users. I was already considering moving out of their Cloud server and managing a Supabase CLI service on my Hetzner VPS for some time; but never ever suspected that I would have to do this quickly. The cheapest plan Supabase offers is $25/month; yet, at that point, I am in between jobs for such a long time, basically broke, and could barely afford that price. One or two months could be okay, but why pay for it if I will eventually move out of their Cloud service? So, instead of paying $25, I spent two days migrating out of Supabase Cloud. Worth my time? Definitely not. But, when you are broke, you gotta do stupid things. This was the first time that I felt lucky to have zero users: I have no idea how I would manage this migration if I had any. I think this is one of the core tenets of an indie hacker: Controlling their own environment. I can’t remember whose quote this is, but I suspect it was Naval: Entrepreneurs have an almost pathological need to control their own fate. They will take any suffering if they can be in charge of their destiny, and not have it in somebody else’s hands. What’s truly scary is, at least in my case, we make people around us suffer at the expense of our attempting to control our own fates. I know this period has been quite hard on my wife as well, as I neglected her quite a bit, but sadly, I know that this will happen again. It is something that I can barely help with. Still, so sorry. After working the last two weeks on a ProductHunt Launch, I finally launched it this Tuesday. Zero ranking, zero new users, but 36 kind people upvoted my product, and many commented and provided invaluable feedback. I couldn't be more grateful for each one of them 🙏. Considering all these, what lies in the future of Summ though? I have no idea, to be honest. On one hand, I have zero users, have no job, no income. So, I need a way to make money asap. On the other hand, the whole idea of it revolves around one core premise (not an assumption) that I am not so willing to share; and I couldn’t have more trust in it. This might not be the best iteration of it, however I certainly believe that email usage is one of the best problem spaces one could work on. 👉 But, one thing is for certain: I need to get in touch with people, and talk with them about this product I built so far. In fact, this is the only item on my agenda. Nothing else will save my brainchild <3. Below are some other insights and notes that I got during my journey; as they do not 100% fit into this story, I think it is more suitable to list them here. I hope you enjoyed reading this. Give Summ a try, it comes with a generous free trial, no credit card required. Some additional notes and insights: Project planning is one of the most underestimated skills for solopreneurs. It saves you enormous time, and helps you to keep your focus up. Building B2C products beats building B2B products. Businesses are very willing to pay big bucks if your product helps them. On the other hand, spending a few hours per user who would pay $5/m probably is not worth your time. It doesn’t matter how brilliant your product is if no one uses it. If you cannot sell a product in a certain category/niche (or do not know how to sell it), it might be a good idea not to start a project in it. Going after new ideas and ventures is quite risky, especially if you don’t know how to market it. On the other hand, an already established category means that there is already demand. Whether this demand is sufficient or not is another issue. As long as there is enough demand for your product to fit in, any category/niche is good. Some might be better, some might be worse. Unless you are going hardcore B2B, you will need people to find your product by means of organic search. Always conduct thorough keyword research as soon as possible.

Seeking co-founder to build LinkedIn’s biggest rival(curated version)

How do you connect with likeminded people? You see the polished wins everywhere, but what about the messy drafts , the awkward pitches and the moments you’re not sure you’ve got it right? Problem: The whole idea of founding and starting a business can be super intimidating for some people, specially those who don’t know any founders personally, those who don’t have a large network, those who don’t have rich parents with large networks, those not inserted in an entrepreneurial culture like in the US for example (which is my case). Sometimes all you need is the right support network, and too see others do what you want, to know that it’s possible! Everyone has an “ultimate guide” to make 7 figures or build a business on YouTube but NO ONE shoes you the HOW, just the results… I’ve tried joining founder communities, LinkedIn ,Reddit … you name it. Most of these founder communities are inaccessible for regular people and often ask for you to have an already existing business with a min ARR… or their simply geography based and if you’re not in a certain area you can’t really participate… As of LinkedIn… full of empty AI generated posts about how some random dude raised $10m in 7 days. Okay Jonathan, but what about the HOW?? How did you write your first pitch? How many rejection calls did you get? What is an MVP? There simply isn’t a platform out there to document your founding journey and find inspiration within a community of people who are doing the same as you. What better way to feel motivated then to see someone actually document their process? Solution: I’m working on building a social media platform for aspiring/founders to connect through the RAW, UNFILTERED process of turning ideas into reality in REAL time. It’s all gonna be around the “building in public “ concept and content creation. Picture an instagram/tiktok profile where instead of seeing someone’s dog you see them documenting their founding process—from the moment they had the idea, to the moment they launched, you’re going to see the successes, the fails, the rejected calls, all documented through actual content and not some AI generated LinkedIn post. Imagine if you wanted to learn about how Steve Jobs started Apple , you could simply go through his profile on this app—exactly. To make sure all interactions are meaningful people would have to apply. It’s a truly curated community, with REAL people, building REAL things in REAL time, and not just tell us the story of how they did it… Audience: I’m targeting people who have a burning desire of building a business and early stage founders starting their founder journeys, that don’t have a support network and simply don’t know where to start. People who are tired of watching 30 min “ultimate guides “ on how to make it on YouTube from “business gurus” selling courses. People who haven’t reached the min ARR required to join an “exclusive “ founder a community. People who can’t simply just move to the US to get into the “exclusive” YC combinator. People who want to connect with real people building real things and not anonymous people on Reddit, or LinkedIn influencers again trying to promote their services. I believe in the idea because I’m also part of my audience. Have always wanted to start my own thing just never knew how to and where to find a community of likeminded people . I don’t know any founders myself, I come from a non-entrepreneurial society and I’d pay good money to access a community of REAL passionate founders building REAL things, in REAL time. This would be my first ever business, and I want to share my journey building it and hopefully inspire others to just start so I’ve created a mailing list to keep anyone interested in the project updated on my fails , learnings and successes. I’m not worried about “making it” but just “starting” and hopefully reach the right audience and inspire anyone to start whatever they have marinating in their thoughts. If you’re a founder struggling with staying consistent or an aspiring founder with an insane desire of starting and don’t know how to start, I’d love to get your feedback on what’s stopping you, your challenges starting out and what you’d find useful in such platform. And finally would this be something that interests you?? PS: casually looking for a technical co-founder

Idea Validation Post: Seeking Feedback on My AI-Driven Quick Launch Application! 🚀

Hey Members! I’m excited to share an idea for a new application I’m planning to build: Quick Launch . This AI-driven platform is designed to assist solopreneurs or anyone with an idea in launching their Minimum Viable Products (MVPs) by taking on the roles of the entire team needed for the process. Goal: Assistance in quickly moving from Idea to MVP Before I dive into the details, I’d love to hear your thoughts and feedback. Key Features: Product Creation: From Idea to Product Detailing AI-Generated Q&A: Real-time questions generation one-at-a-time to define the product requirements based on their knowledge levels to convert an Idea into a Product. Market Research Reports: In-depth analysis that identifies product-market fit, competitive landscape, and potential marketing strategies. Sentiment Analysis: Evaluation of user feedback and reactions across multiple subreddits to gauge public opinion on ideas. Product Development: Product Detailing to Actual Product User Story Generation: Identification and creation of comprehensive user stories, tasks, and sub-tasks to facilitate development. AI Project Management: AI agents assume roles of project managers and UI/UX designers to streamline product detailing and development. Integration Capabilities: Seamless integration with popular project management tools like Jira, Asana, and Trello for better workflow management. Target Audience: Solopreneurs: Individuals looking to bring their business ideas to life without extensive resources. Indie Hackers: Entrepreneurs focused on building small projects or startups with minimal overhead. Idea Validators: Anyone with a concept seeking initial validation and market feedback before committing significant resources. If you’re interested in learning more, check out our teaser website: Quick Launch Discussion Question: What features would you find most valuable in an application like this? Are there specific pain points you face when launching an MVP? Your insights would be incredibly helpful as I refine this idea! Looking forward to your thoughts! 🙌

I spent 6 months on building a web product, and got zero users. Here is my story.

Edit Thank you all so much for your time reading my story. Your support, feedback, criticism, and skepticism; all helped me a lot, and I couldn't appreciate it enough \^\_\^ I have stuff to post on Reddit very rarely, but I share how my project is going on, random stuff, and memes on X. Just in case few might want to keep in touch 👀 TL;DR I spent 6 months on a tool that currently has 0 users. Below is what I learned during my journey, sharing because I believe most mistakes are easily avoidable. Do not overestimate your product and assume it will be an exception to fundamental principles. Principles are there for a reason. Always look for validation before you start. Avoid building products with a low money-to-effort ratio/in very competitive fields. Unless you have the means, you probably won't make it. Pick a problem space, pick your target audience, and talk to them before thinking about a solution. Identify and match their pain points. Only then should you think of a solution. If people are not overly excited or willing to pay in advance for a discounted price, it might be a sign to rethink. Sell one and only one feature at a time. Avoid everything else. If people don't pay for that one core feature, no secondary feature will change their mind. Always spend twice as much time marketing as you do building. You will not get users if they don't know it exists. Define success metrics ("1000 users in 3 months" or "$6000 in the account at the end of 6 months") before you start. If you don't meet them, strongly consider quitting the project. If you can't get enough users to keep going, nothing else matters. VALIDATION, VALIDATION, VALIDATION. Success is not random, but most of our first products will not make a success story. Know when to admit failure, and move on. Even if a product of yours doesn't succeed, what you learned during its journey will turn out to be invaluable for your future. My story So, this is the story of a product that I’ve been working on for the last 6 months. As it's the first product I’ve ever built, after watching you all from the sidelines, I have learned a lot, made many mistakes, and did only a few things right. Just sharing what I’ve learned and some insights from my journey so far. I hope that this post will help you avoid the mistakes I made — most of which I consider easily avoidable — while you enjoy reading it, and get to know me a little bit more 🤓. A slow start after many years Summ isn’t the first product I really wanted to build. Lacking enough dev skills to even get started was a huge blocker for so many years. In fact, the first product I would’ve LOVED to build was a smart personal shopping assistant. I had this idea 4 years ago; but with no GPT, no coding skills, no technical co-founder, I didn’t have the means to make it happen. I still do not know if such a tool exists and is good enough. All I wanted was a tool that could make data-based predictions about when to buy stuff (“buy a new toothpaste every three months”) and suggest physical products that I might need or be strongly interested in. AFAIK, Amazon famously still struggles with the second one. Fast-forward a few years, I learned the very basics of HTML, CSS, and Vanilla JS. Still was not there to build a product; but good enough to code my design portfolio from scratch. Yet, I couldn’t imagine myself building a product using Vanilla JS. I really hated it, I really sucked at it. So, back to tutorial hell, and to learn about this framework I just heard about: React.React introduced so many new concepts to me. “Thinking in React” is a phrase we heard a lot, and with quite good reasons. After some time, I was able to build very basic tutorial apps, both in React, and React Native; but I have to say that I really hated coding for mobile. At this point, I was already a fan of productivity apps, and had a concept for a time management assistant app in my design portfolio. So, why not build one? Surely, it must be easy, since every coding tutorial starts with a todo app. ❌ WRONG! Building a basic todo app is easy enough, but building one good enough for a place in the market was a challenge I took and failed. I wasted one month on that until I abandoned the project for good. Even if I continued working on it, as the productivity landscape is overly competitive, I wouldn’t be able to make enough money to cover costs, assuming I make any. Since I was (and still am) in between jobs, I decided to abandon the project. 👉 What I learned: Do not start projects with a low ratio of money to effort and time. Example: Even if I get 500 monthly users, 200 of which are paid users (unrealistically high number), assuming an average subscription fee of $5/m (such apps are quite cheap, mostly due to the high competition), it would make me around $1000 minus any occurring costs. Any founder with a product that has 500 active users should make more. Even if it was relatively successful, due to the high competition, I wouldn’t make any meaningful money. PS: I use Todoist today. Due to local pricing, I pay less than $2/m. There is no way I could beat this competitive pricing, let alone the app itself. But, somehow, with a project that wasn’t even functional — let alone being an MVP — I made my first Wi-Fi money: Someone decided that the domain I preemptively purchased is worth something. By this point, I had already abandoned the project, certainly wasn’t going to renew the domain, was looking for a FT job, and a new project that I could work on. And out of nowhere, someone hands me some free money — who am I not to take it? Of course, I took it. The domain is still unused, no idea why 🤔. Ngl, I still hate the fact that my first Wi-Fi money came from this. A new idea worth pursuing? Fast-forward some weeks now. Around March, I got this crazy idea of building an email productivity tool. We all use emails, yet we all hate them. So, this must be fixed. Everyone uses emails, in fact everyone HAS TO use emails. So, I just needed to build a tool and wait for people to come. This was all, really. After all, the problem space is huge, there is enough room for another product, everyone uses emails, no need for any further validation, right? ❌ WRONG ONCE AGAIN! We all hear from the greatest in the startup landscape that we must validate our ideas with real people, yet at least some of us (guilty here 🥸) think that our product will be hugely successful and prove them to be an exception. Few might, but most are not. I certainly wasn't. 👉 Lesson learned: Always validate your ideas with real people. Ask them how much they’d pay for such a tool (not if they would). Much better if they are willing to pay upfront for a discount, etc. But even this comes later, keep reading. I think the difference between “How much” and “If” is huge for two reasons: (1) By asking them for “How much”, you force them to think in a more realistic setting. (2) You will have a more realistic idea on your profit margins. Based on my competitive analysis, I already had a solution in my mind to improve our email usage standards and email productivity (huge mistake), but I did my best to learn about their problems regarding those without pushing the idea too hard. The idea is this: Generate concise email summaries with suggested actions, combine them into one email, and send it at their preferred times. Save as much as time the AI you end up with allows. After all, everyone loves to save time. So, what kind of validation did I seek for? Talked with only a few people around me about this crazy, internet-breaking idea. The responses I got were, now I see, mediocre; no one got excited about it, just said things along the lines of “Cool idea, OK”. So, any reasonable person in this situation would think “Okay, not might not be working”, right? Well, I did not. I assumed that they were the wrong audience for this product, and there was this magical land of user segments waiting eagerly for my product, yet unknowingly. To this day, I still have not reached this magical place. Perhaps, it didn’t exist in the first place. If I cannot find it, whether it exists or not doesn’t matter. I am certainly searching for it. 👉 What I should have done: Once I decide on a problem space (time management, email productivity, etc.), I should decide on my potential user segments, people who I plan to sell my product to. Then I should go talk to those people, ask them about their pains, then get to the problem-solving/ideation phase only later. ❗️ VALIDATION COMES FROM THE REALITY OUTSIDE. What validation looks like might change from product to product; but what invalidation looks like is more or less the same for every product. Nico Jeannen told me yesterday “validation = money in the account” on Twitter. This is the ultimate form of validation your product could get. If your product doesn’t make any money, then something is invalidated by reality: Your product, you, your idea, who knows? So, at this point, I knew a little bit of Python from spending some time in tutorial hell a few years ago, some HTML/CSS/JS, barely enough React to build a working app. React could work for this project, but I needed easy-to-implement server interactivity. Luckily, around this time, I got to know about this new gen of indie hackers, and learned (but didn’t truly understand) about their approach to indie hacking, and this library called Nextjs. How good Next.js still blows my mind. So, I was back to tutorial hell once again. But, this time, with a promise to myself: This is the last time I would visit tutorial hell. Time to start building this "ground-breaking idea" Learning the fundamentals of Next.js was easier than learning of React unsurprisingly. Yet, the first time I managed to run server actions on Next.js was one of the rarest moments that completely blew my mind. To this day, I reject the idea that it is something else than pure magic under its hood. Did I absolutely need Nextjs for this project though? I do not think so. Did it save me lots of time? Absolutely. Furthermore, learning Nextjs will certainly be quite helpful for other projects that I will be tackling in the future. Already got a few ideas that might be worth pursuing in the head in case I decide to abandon Summ in the future. Fast-forward few weeks again: So, at this stage, I had a barely working MVP-like product. Since the very beginning, I spent every free hour (and more) on this project as speed is essential. But, I am not so sure it was worth it to overwork in retrospect. Yet, I know I couldn’t help myself. Everything is going kinda smooth, so what’s the worst thing that could ever happen? Well, both Apple and Google announced their AIs (Apple Intelligence and Google Gemini, respectively) will have email summarization features for their products. Summarizing singular emails is no big deal, after all there were already so many similar products in the market. I still think that what truly matters is a frictionless user experience, and this is why I built this product in a certain way: You spend less than a few minutes setting up your account, and you get to enjoy your email summaries, without ever visiting its website again. This is still a very cool concept I really like a lot. So, at this point: I had no other idea that could be pursued, already spent too much time on this project. Do I quit or not? This was the question. Of course not. I just have to launch this product as quickly as possible. So, I did something right, a quite rare occurrence I might say: Re-planned my product, dropped everything secondary to the core feature immediately (save time on reading emails), tried launching it asap. 👉 Insight: Sell only one core feature at one time. Drop anything secondary to this core feature. Well, my primary occupation is product design. So one would expect that a product I build must have stellar design. I considered any considerable time spent on design at this stage would be simply wasted. I still think this is both true and wrong: True, because if your product’s core benefits suck, no one will care about your design. False, because if your design looks amateurish, no one will trust you and your product. So, I always targeted an average level design with it and the way this tool works made it quite easy as I had to design only 2 primary pages: Landing page and user portal (which has only settings and analytics pages). However, even though I knew spending time on design was not worth much of my time, I got a bit “greedy”: In fact, I redesigned those pages three times, and still ended up with a so-so design that I am not proud of. 👉 What I would do differently: Unless absolutely necessary, only one iteration per stage as long as it works. This, in my mind, applies to everything. If your product’s A feature works, then no need to rewrite it from scratch for any reason, or even refactor it. When your product becomes a success, and you absolutely need that part of your codebase to be written, do so, but only then. Ready to launch, now is th etime for some marketing, right? By July 26, I already had a “launchable” product that barely works (I marked this date on a Notion docs, this is how I know). Yet, I had spent almost no time on marketing, sales, whatever. After all, “You build and they will come”. Did I know that I needed marketing? Of course I did, but knowingly didn’t. Why, you might ask. Well, from my perspective, it had to be a dev-heavy product; meaning that you spend most of your time on developing it, mostly coding skills. But, this is simply wrong. As a rule of thumb, as noted by one of the greatests, Marc Louvion, you should spend at least twice of the building time on marketing. ❗️ Time spent on building \* 2 people don’t know your product > they don’t use your product > you don’t get users > you don’t make money Easy as that. Following the same reasoning, a slightly different approach to planning a project is possible. Determine an approximate time to complete the project with a high level project plan. Let’s say 6 months. By the reasoning above, 2 months should go into building, and 4 into marketing. If you need 4 months for building instead of 2, then you need 8 months of marketing, which makes the time to complete the project 12 months. If you don’t have that much time, then quit the project. When does a project count as completed? Well, in reality, never. But, I think we have to define success conditions even before we start for indie projects and startups; so we know when to quit when they are not met. A success condition could look like “Make $6000 in 12 months” or “Have 3000 users in 6 months”. It all depends on the project. But, once you set it, it should be set in stone: You don’t change it unless absolutely necessary. I suspect there are few principles that make a solopreneur successful; and knowing when to quit and when to continue is definitely one of them. Marc Louvion is famously known for his success, but he got there after failing so many projects. To my knowledge, the same applies to Nico Jeannen, Pieter Levels, or almost everyone as well. ❗️ Determining when to continue even before you start will definitely help in the long run. A half-aed launch Time-leap again. Around mid August, I “soft launched” my product. By soft launch, I mean lazy marketing. Just tweeting about it, posting it on free directories. Did I get any traffic? Surely I did. Did I get any users? Nope. Only after this time, it hit me: “Either something is wrong with me, or with this product” Marketing might be a much bigger factor for a project’s success after all. Even though I get some traffic, not convincing enough for people to sign up even for a free trial. The product was still perfect in my eyes at the time (well, still is ^(\_),) so the right people are not finding my product, I thought. Then, a question that I should have been asking at the very first place, one that could prevent all these, comes to my mind: “How do even people search for such tools?” If we are to consider this whole journey of me and my so-far-failed product to be an already destined failure, one metric suffices to show why. Search volume: 30. Even if people have such a pain point, they are not looking for email summaries. So, almost no organic traffic coming from Google. But, as a person who did zero marketing on this or any product, who has zero marketing knowledge, who doesn’t have an audience on social media, there is not much I could do. Finally, it was time to give up. Or not… In my eyes, the most important element that makes a founder (solo or not) successful (this, I am not by any means) is to solve problems. ❗️ So, the problem was this: “People are not finding my product by organic search” How do I make sure I get some organic traffic and gets more visibility? Learn digital marketing and SEO as much as I can within very limited time. Thankfully, without spending much time, I came across Neil Patel's YT channel, and as I said many times, it is an absolute gold mine. I learned a lot, especially about the fundamentals, and surely it will be fruitful; but there is no magic trick that could make people visit your website. SEO certainly helps, but only when people are looking for your keywords. However, it is truly a magical solution to get in touch with REAL people that are in your user segments: 👉 Understand your pains, understand their problems, help them to solve them via building products. I did not do this so far, have to admit. But, in case you would like to have a chat about your email usage, and email productivity, just get in touch; I’d be delighted to hear about them. Getting ready for a ProductHunt launch The date was Sept 1. And I unlocked an impossible achievement: Running out of Supabase’s free plan’s Egres limit while having zero users. I was already considering moving out of their Cloud server and managing a Supabase CLI service on my Hetzner VPS for some time; but never ever suspected that I would have to do this quickly. The cheapest plan Supabase offers is $25/month; yet, at that point, I am in between jobs for such a long time, basically broke, and could barely afford that price. One or two months could be okay, but why pay for it if I will eventually move out of their Cloud service? So, instead of paying $25, I spent two days migrating out of Supabase Cloud. Worth my time? Definitely not. But, when you are broke, you gotta do stupid things. This was the first time that I felt lucky to have zero users: I have no idea how I would manage this migration if I had any. I think this is one of the core tenets of an indie hacker: Controlling their own environment. I can’t remember whose quote this is, but I suspect it was Naval: Entrepreneurs have an almost pathological need to control their own fate. They will take any suffering if they can be in charge of their destiny, and not have it in somebody else’s hands. What’s truly scary is, at least in my case, we make people around us suffer at the expense of our attempting to control our own fates. I know this period has been quite hard on my wife as well, as I neglected her quite a bit, but sadly, I know that this will happen again. It is something that I can barely help with. Still, so sorry. After working the last two weeks on a ProductHunt Launch, I finally launched it this Tuesday. Zero ranking, zero new users, but 36 kind people upvoted my product, and many commented and provided invaluable feedback. I couldn't be more grateful for each one of them 🙏. Considering all these, what lies in the future of Summ though? I have no idea, to be honest. On one hand, I have zero users, have no job, no income. So, I need a way to make money asap. On the other hand, the whole idea of it revolves around one core premise (not an assumption) that I am not so willing to share; and I couldn’t have more trust in it. This might not be the best iteration of it, however I certainly believe that email usage is one of the best problem spaces one could work on. 👉 But, one thing is for certain: I need to get in touch with people, and talk with them about this product I built so far. In fact, this is the only item on my agenda. Nothing else will save my brainchild <3. Below are some other insights and notes that I got during my journey; as they do not 100% fit into this story, I think it is more suitable to list them here. I hope you enjoyed reading this. Give Summ a try, it comes with a generous free trial, no credit card required. Some additional notes and insights: Project planning is one of the most underestimated skills for solopreneurs. It saves you enormous time, and helps you to keep your focus up. Building B2C products beats building B2B products. Businesses are very willing to pay big bucks if your product helps them. On the other hand, spending a few hours per user who would pay $5/m probably is not worth your time. It doesn’t matter how brilliant your product is if no one uses it. If you cannot sell a product in a certain category/niche (or do not know how to sell it), it might be a good idea not to start a project in it. Going after new ideas and ventures is quite risky, especially if you don’t know how to market it. On the other hand, an already established category means that there is already demand. Whether this demand is sufficient or not is another issue. As long as there is enough demand for your product to fit in, any category/niche is good. Some might be better, some might be worse. Unless you are going hardcore B2B, you will need people to find your product by means of organic search. Always conduct thorough keyword research as soon as possible.

What to look for in the Best PDF Invoice Parser?

I've been thinking about starting using PDF Invoice Parser, so these are some key features to look out for in a PDF invoice parser I've learned about these days on Affinda. Machine Learning - There are invoice parsers available that use machine learning algorithms to learn from their mistakes, resulting in them being able to parse many data sources and become more accurate over time. Optical Character Recognition - An OCR invoice parser is one that uses optical character recognition to take images lacking text data and turn them into digital files. Natural Language Processing - This results in more efficient and effective invoice processing that seeks to understand the text and sort invoice fields correctly. Artificial Intelligence - Many parsers struggle to adapt and fail to complete information extraction from nonstandard invoice formats. That’s why you need a parser that leverages document AI to analyze the template and extract structured data no matter what invoice layout is used. Different Types Analysed - For example, you might receive a mailed invoice or Word document. You need a parser that can analyze and get extracted data from any format of the supplier invoice. So, is this enough information and benefits for me to choose this product? I guess so, I've even heard great stuff about it, but I would love to share all of this with you and maybe some of you already had any experience to share with all of us. Have a nice day, guys!

The Evolution of Financial Technology: How CAs Are Embracing the Digital Age

The Evolution of Financial Technology: How CAs Are Embracing the Digital Age Introduction In an era characterized by rapid technological advancements, the field of finance is undergoing a transformative journey. The emergence of financial technology, or fintech, is reshaping the way businesses manage their finances, and Chartered Accountants (CAs) are at the forefront of this evolution. In this blog post, we'll explore how CAs are embracing fintech and leveraging its potential to enhance financial management, analysis, and advisory services. Fintech's Impact on Financial Services Fintech encompasses a wide range of technologies that leverage data analytics, artificial intelligence, blockchain, and automation to improve financial services. For CAs, this means new tools to streamline processes, enhance decision-making, and offer innovative solutions to clients. Automation of Routine Tasks CAs are increasingly using automation tools to handle repetitive tasks such as data entry, reconciliations, and transaction processing. This not only reduces the risk of human error but also frees up CAs to focus on higher-value tasks like strategic planning and analysis. Advanced Data Analytics Data analytics tools enable CAs to extract meaningful insights from large volumes of financial data. These insights can help businesses identify trends, anticipate risks, and make informed decisions to drive growth. Real-Time Financial Reporting Fintech enables CAs to provide clients with real-time financial reporting, giving businesses immediate access to critical information. This enhances transparency and empowers business owners to respond quickly to changing market conditions. Enhancing Audit Efficiency Fintech tools are revolutionizing the audit process. CAs can use AI-powered algorithms to analyze vast amounts of data, detect anomalies, and identify potential instances of fraud more efficiently. Personalized Financial Planning CAs can leverage fintech to offer personalized financial planning services. With access to detailed financial data, CAs can create tailored strategies that align with a client's unique goals and circumstances. Strengthening Cybersecurity As businesses become more reliant on digital tools, cybersecurity becomes paramount. CAs are playing a critical role in advising clients on cybersecurity measures to protect sensitive financial information. Virtual CFO Services Fintech enables CAs to offer virtual CFO services to startups and small businesses. Through digital platforms, CAs can provide expert financial advice and guidance remotely, making their expertise accessible to a wider range of clients. Embracing Blockchain Technology Blockchain's potential for secure and transparent record-keeping is of interest to CAs. They can explore applications in supply chain finance, smart contracts, and even audit trail verification. Continuous Learning in Fintech CAs recognize the importance of staying updated with fintech trends. Many are investing in continuous learning to master the use of new tools and technologies that can optimize their services. Conclusion The integration of fintech into the realm of finance is reshaping the landscape in profound ways. CAs are embracing these technologies to elevate their roles from traditional number-crunchers to strategic advisors, equipped with tools that enhance efficiency, accuracy, and insight. As fintech continues to evolve, CAs will remain pivotal in guiding businesses through the ever-changing financial landscape, leveraging technology to drive growth, innovation, and success. Find the top verified CA in your City Feel free to let me know if you'd like more blogs on different topics or if you have specific requirements for the content.

Seeking advice from every type of business owner - if you have a moment & an opinion please chime in.

Hello everyone. I haven't started selling yet and wanted to get some insight from the community I'm trying to serve (that makes the most sense to me). So over the past couple months I've gotten into AI & Automation. I got a HighLevel account and went to town learning new things. I learned how to make automations and workflows that make running a business easier (my dad has been letting me use his concrete business as a guinea pig). I also learned how to build and train AI Chat Assistants. I want to start a service based business that uses AI & workflows to automate some of the customer service tasks & lead generation for business. What I'm seeking advice about are as follows: NICHE SELECTION: Part of me thinks I shouldn't niche down in the beginning and just take whoever comes and niche down once I find an industry I'm comfortable with. Another side thinks I should choose one. What is your opinion on niche selection in the beginning? PRICING: I know that pricing largely depends on the value I bring to the client, but I've seen people doing the same or similar things as I want to do and charging vastly different prices. From $300- $2,000. While I think these solutions could absolutely help companies get and retain new business and reduce some of the workload of their staff -- I'm not comfortable charging a high price until I've got enough experience and data to justify that. &#x200B; THESE ARE THE SERVICES I'M THINKING OF OFFERING: Customer Service Chat Assistant. This will be on the website as a "Live Chat". It also connects to Facebook Messenger & Google Business Chat. I'd train the chat assistant on everything related to the company; pertinent info (NAP, company mission, industry background), contact info, services / products / pricing, FAQs, current specials &/or discount codes (this can be changed monthly), how to handle upset clients, etc. It can also connect to a calendar like Google or Calendly so customers can make an appointment or schedule a call directly from the conversation. Missed Call Follow Up. If you're familiar with the platform HighLevel it's commonly called "Missed Call Text Back". The idea is that when a call is missed a text message is automatically fired to the prospect's phone saying something along the lines of "Hey this is \\\\\\ from \\\\\\\_. How can I help you?" and the business owner is alerted to the missed call via text notification. People have said they see a lot of success for their clients with this alone due to the instant follow up. I see a lot of people charging $300 /m. for this. My issues with this are: 1). The text fires automatically when the call is missed, but if the business owner isn't available to actually follow up and keep texting after the customer texts back, they will look inconsistent and bothersome. 2). Without context a prospect may wonder why you didn't answer when they called, but texted them instead. So my answer to these problems are #3. SMS Answering Service. It is essentially taking 2 + 1 and combining them. The missed call text goes out to the prospect, but with context on why they're being texted (because no one is available to take the call at the moment) and IF the prospect responds, a Customer Service Chat Assistant will take over the conversation with the goal of answering their questions and either getting them on the phone with the company via a call back OR helping them schedule an appointment. This offers a more consistent solution than just a text to the business owner / team & the prospect is contacted and helped (hopefully) before they have a chance to start calling a competitor. Lead Nurture / Lead Qualifying Sales Funnel. This one is more than just AI & automation. It's a full funnel. It can be for either Facebook or Google. The process is AD -> Landing Page -> AI Text Message Convo -> Booking/Schedule Call/ Appointment. Typically the ad will offer a lead magnet which they will claim on the LP by giving their information. After the form is submitted, they get a text message and begin a conversation with the AI. It can be trained to just walk them through a booking process, nurture a sale by answering questions and handling objections or to qualify leads. Lead qualification via text works well if you want to weed out who is serious versus who is curious. To be clear; I'd be making the ad, landing page & training the AI -- all parts of the funnel. For whichever service a few things are universal: \- All conversations; no matter what platform they're had on, all go to one inbox which is pretty helpful to see them all in one place. \- When scheduling / booking these can also collect payment. \- Tags can be added to keep track of how they came into the business and where they are in a sales pipeline. There are a lot of fun things I can do with these automations and I'm excited about learning more everyday. I'd really like to know what you think these services could be worth to a business. If you do reply please tell me what type of business you're in so I have an idea of what industries I should be looking towards. Thank you for any response I get as I know this was a long read! SN: I currently do digital marketing & web design as a freelancer.

(Academic) AI Readiness Survey for Small and Medium Businesses (SMB's) in Food and Beverage Industry. (Everyone 18+, Growing & Managing Small Business in Food and Beverage Industry, Canadian market)

Hi everyone! 👋 I'm conducting a research study on how AI-driven automation and hyper-personalization can enhance customer-centric innovation for small bakeries and food businesses. This survey will help understand and assess the awareness, key challenges, opportunities, and ethical concerns surrounding AI adoption among SMBs in the food and beverage industry. The results will help tailor AI adoption strategies, resources, and training programs. This survey will take about 10-15 minutes, and your responses will remain confidential. This study is also approved by Research Ethics Board (REB) #2024-70. Link: AI Readiness Survey for Small Businesses across Food and Beverage Industry Your insights will contribute to real-world AI adoption strategies, AI toolkits, and experiential learning programs for small businesses. I'd love to hear your thoughts! Feel free to drop any comments or questions. We will share the results of the study on this subreddit once we analyze the result. Thank you very much in advance for your time and help!

How are small businesses leveraging AI for growth?

AI in Business: Share Your Experiences! How are small businesses leveraging AI for growth? Share your stories, challenges, or successes! Let's discuss: AI-powered automation Machine learning strategies Chatbots for customer support Help us learn from each other!

How are small businesses leveraging AI for growth?

AI in Business: Share Your Experiences! How are small businesses leveraging AI for growth? Share your stories, challenges, or successes! Let's discuss: AI-powered automation Machine learning strategies Chatbots for customer support Help us learn from each other!

(Academic) AI Readiness Survey for Small and Medium Businesses (SMB's) in Food and Beverage Industry. (Everyone 18+, Growing & Managing Small Business in Food and Beverage Industry, Canadian market)

Hi everyone! 👋 I'm conducting a research study on how AI-driven automation and hyper-personalization can enhance customer-centric innovation for small bakeries and food businesses. This survey will help understand and assess the awareness, key challenges, opportunities, and ethical concerns surrounding AI adoption among SMBs in the food and beverage industry. The results will help tailor AI adoption strategies, resources, and training programs. This survey will take about 10-15 minutes, and your responses will remain confidential. This study is also approved by Research Ethics Board (REB) #2024-70. Link: AI Readiness Survey for Small Businesses across Food and Beverage Industry Your insights will contribute to real-world AI adoption strategies, AI toolkits, and experiential learning programs for small businesses. I'd love to hear your thoughts! Feel free to drop any comments or questions. We will share the results of the study on this subreddit once we analyze the result. Thank you very much in advance for your time and help!

(Academic) AI Readiness Survey for Small and Medium Businesses (SMB's) in Food and Beverage Industry. (Everyone 18+, Growing & Managing Small Business in Food and Beverage Industry, Canadian market)

Hi everyone! 👋 I'm conducting a research study on how AI-driven automation and hyper-personalization can enhance customer-centric innovation for small bakeries and food businesses. This survey will help understand and assess the awareness, key challenges, opportunities, and ethical concerns surrounding AI adoption among SMBs in the food and beverage industry. The results will help tailor AI adoption strategies, resources, and training programs. This survey will take about 10-15 minutes, and your responses will remain confidential. This study is also approved by Research Ethics Board (REB) #2024-70. Link: AI Readiness Survey for Small Businesses across Food and Beverage Industry Your insights will contribute to real-world AI adoption strategies, AI toolkits, and experiential learning programs for small businesses. I'd love to hear your thoughts! Feel free to drop any comments or questions. We will share the results of the study on this subreddit once we analyze the result. Thank you very much in advance for your time and help!

Seeking Quick Feedback: AI Tool for SMB Sustainability

Hi everyone, I’m working on an AI-powered toolkit to help small and medium-sized businesses (SMBs) with sustainability efforts and ESG reporting for a hackathon. I’d really appreciate a quick testimonial from those who find this tool valuable. Key Features: Generative AI for automatic ESG report creation. Machine Learning for optimizing operational data. NLP for easy-to-understand reports. If you find this concept useful for SMBs or sustainability efforts, could you share a brief testimonial or your thoughts? Your feedback would be incredibly helpful! Thank you!

𝐁𝐮𝐢𝐥𝐝 𝐋𝐋𝐌𝐬 𝐟𝐫𝐨𝐦 𝐬𝐜𝐫𝐚𝐭𝐜𝐡

“ChatGPT” is everywhere—it’s a tool we use daily to boost productivity, streamline tasks, and spark creativity. But have you ever wondered how it knows so much and performs across such diverse fields? Like many, I've been curious about how it really works and if I could create a similar tool to fit specific needs. 🤔 To dive deeper, I found a fantastic resource: “Build a Large Language Model (From Scratch)” by Sebastian Raschka, which is explained with an insightful YouTube series “Building LLM from Scratch” by Dr. Raj Dandekar (MIT PhD). This combination offers a structured, approachable way to understand the mechanics behind LLMs—and even to try building one ourselves! https://preview.redd.it/35sdlxdb2m0e1.jpg?width=1037&format=pjpg&auto=webp&s=dd228136fbf7cbdeeae253118ee7a46b04948c24 While AI and generative language models architecture shown in the figure can seem difficult to understand, I believe that by taking it step-by-step, it’s achievable—even for those without a tech background. 🚀 Learning one concept at a time can open the doors to this transformative field, and we at Vizuara.ai are excited to take you through the journey where each step is explained in detail for creating an LLM. For anyone interested, I highly recommend going through the following videos:  Lecture 1: Building LLMs from scratch: Series introduction https://youtu.be/Xpr8D6LeAtw?si=vPCmTzfUY4oMCuVl  Lecture 2: Large Language Models (LLM) Basics https://youtu.be/3dWzNZXA8DY?si=FdsoxgSRn9PmXTTz  Lecture 3: Pretraining LLMs vs Finetuning LLMs https://youtu.be/-bsa3fCNGg4?si=j49O1OX2MT2k68pl  Lecture 4: What are transformers? https://youtu.be/NLn4eetGmf8?si=GVBrKVjGa5Y7ivVY  Lecture 5: How does GPT-3 really work? https://youtu.be/xbaYCf2FHSY?si=owbZqQTJQYm5VzDx  Lecture 6: Stages of building an LLM from Scratch https://youtu.be/z9fgKz1Drlc?si=dzAqz-iLKaxUH-lZ  Lecture 7: Code an LLM Tokenizer from Scratch in Python https://youtu.be/rsy5Ragmso8?si=MJr-miJKm7AHwhu9  Lecture 8: The GPT Tokenizer: Byte Pair Encoding https://youtu.be/fKd8s29e-l4?si=aZzzV4qT\nbQ1lzk  Lecture 9: Creating Input-Target data pairs using Python DataLoader https://youtu.be/iQZFH8dr2yI?si=lH6sdboTXzOzZXP9  Lecture 10: What are token embeddings? https://youtu.be/ghCSGRgVB\o?si=PM2FLDl91ENNPJbd  Lecture 11: The importance of Positional Embeddings https://youtu.be/ufrPLpKnapU?si=cstZgif13kyYo0Rc  Lecture 12: The entire Data Preprocessing Pipeline of Large Language Models (LLMs) https://youtu.be/mk-6cFebjis?si=G4Wqn64OszI9ID0b  Lecture 13: Introduction to the Attention Mechanism in Large Language Models (LLMs) https://youtu.be/XN7sevVxyUM?si=aJy7Nplz69jAzDnC  Lecture 14: Simplified Attention Mechanism - Coded from scratch in Python | No trainable weights https://youtu.be/eSRhpYLerw4?si=1eiOOXa3V5LY-H8c  Lecture 15: Coding the self attention mechanism with key, query and value matrices https://youtu.be/UjdRN80c6p8?si=LlJkFvrC4i3J0ERj  Lecture 16: Causal Self Attention Mechanism | Coded from scratch in Python https://youtu.be/h94TQOK7NRA?si=14DzdgSx9XkAJ9Pp  Lecture 17: Multi Head Attention Part 1 - Basics and Python code https://youtu.be/cPaBCoNdCtE?si=eF3GW7lTqGPdsS6y  Lecture 18: Multi Head Attention Part 2 - Entire mathematics explained https://youtu.be/K5u9eEaoxFg?si=JkUATWM9Ah4IBRy2  Lecture 19: Birds Eye View of the LLM Architecture https://youtu.be/4i23dYoXp-A?si=GjoIoJWlMloLDedg  Lecture 20: Layer Normalization in the LLM Architecture https://youtu.be/G3W-LT79LSI?si=ezsIvNcW4dTVa29i  Lecture 21: GELU Activation Function in the LLM Architecture https://youtu.be/d\PiwZe8UF4?si=IOMD06wo1MzElY9J  Lecture 22: Shortcut connections in the LLM Architecture https://youtu.be/2r0QahNdwMw?si=i4KX0nmBTDiPmNcJ  Lecture 23: Coding the entire LLM Transformer Block https://youtu.be/dvH6lFGhFrs?si=e90uX0TfyVRasvel  Lecture 24: Coding the 124 million parameter GPT-2 model https://youtu.be/G3-JgHckzjw?si=peLE6thVj6bds4M0  Lecture 25: Coding GPT-2 to predict the next token https://youtu.be/F1Sm7z2R96w?si=TAN33aOXAeXJm5Ro  Lecture 26: Measuring the LLM loss function https://youtu.be/7TKCrt--bWI?si=rvjeapyoD6c-SQm3  Lecture 27: Evaluating LLM performance on real dataset | Hands on project | Book data https://youtu.be/zuj\NJNouAA?si=Y\vuf-KzY3Dt1d1r  Lecture 28: Coding the entire LLM Pre-training Loop https://youtu.be/Zxf-34voZss?si=AxYVGwQwBubZ3-Y9  Lecture 29: Temperature Scaling in Large Language Models (LLMs) https://youtu.be/oG1FPVnY0pI?si=S4N0wSoy4KYV5hbv  Lecture 30: Top-k sampling in Large Language Models https://youtu.be/EhU32O7DkA4?si=GKHqUCPqG-XvCMFG

What do you think about no-code AI development

A team of like-minded people and I are working on a no-code AI development platform. Our goal is to make deep learning technologies accessible for everyone, not just for machine learning engineers and big companies. We've decided to start with computer vision tasks. The workflow would look like the following: Select task (image classification, object detection, image tagging). Upload data (with annotation or annotate it in our platform). Wait for a model to be trained automatically (about 10 minutes). Integrate the created model into your product (through API, docker image, or through integration with other no-/low-code platforms). What do you think is there any future for no-code AI development platforms? I'd really appreciate it if you could share your thoughts.

No-code AI platform?

Hey there, A group of like-minded people and I are working on a no-code AI platform. Our goal is to make machine learning technologies accessible to people without any specific knowledge. The workflow would look like the following: Select a task and data types. Upload data (with annotation or annotate it in our platform). Wait for a model to be trained automatically (up to 30-40 minutes). Use the created model (through API, through integration with other no-/low-code platforms, or as a docker image). What do you think about our idea? Would anybody use it? I'd really appreciate it if you could share your thoughts.

My Manager Thinks ML Projects Takes 5 Minutes 🤦‍♀️

Hey, everyone! I’ve got to vent a bit because work has been something else lately. I’m a BI analyst at a bank, and I’m pretty much the only one dealing with machine learning and AI stuff. The rest of my team handles SQL and reporting—no Python, no R, no ML knowledge AT ALL. You could say I’m the only one handling data science stuff So, after I did a Python project for retail, my boss suddenly decided I’m the go-to for all things ML. Since then, I’ve been getting all the ML projects dumped on me (yay?), but here’s the kicker: my manager, who knows nothing about ML, acts like he’s some kind of expert. He keeps making suggestions that make zero sense and setting unrealistic deadlines. I swear, it’s like he read one article and thinks he’s cracked the code. And the best part? Whenever I finish a project, he’s all “we completed this” and “we came up with these insights.” Ummm, excuse me? We? I must’ve missed all those late-night coding sessions you didn’t show up for. The higher-ups know it’s my work and give me credit, but my manager just can’t help himself. Last week, he set a ridiculous deadline of 10 days for a super complex ML project. TEN DAYS! Like, does he even know that data preprocessing alone can take weeks? I’m talking about cleaning up messy datasets, handling missing values, feature engineering, and then model tuning. And that’s before even thinking about building the model! The actual model development is like the tip of the iceberg. But I just nodded and smiled because I was too exhausted to argue. 🤷‍♀️ And then, this one time, they didn’t even invite me to a meeting where they were presenting my work! The assistant manager came to me last minute, like, “Hey, can you explain these evaluation metrics to me so I can present them to the heads?” I was like, excuse me, what? Why not just invite me to the meeting to present my own work? But nooo, they wanted to play charades on me So, I gave the most complicated explanation ever, threw in all the jargon just to mess with him. He came back 10 minutes later, all flustered, and was like, “Yeah, you should probably do the presentation.” I just smiled and said, “I know… data science isn’t for everyone.” Anyway, they called me in at the last minute, and of course, I nailed it because I know my stuff. But seriously, the nerve of not including me in the first place and expecting me to swoop in like some kind of superhero. I mean, at least give me a cape if I’m going to keep saving the day! 🤦‍♀️ Honestly, I don’t know how much longer I can keep this up. I love the work, but dealing with someone who thinks they’re an ML guru when they can barely spell Python is just draining. I have built like some sort of defense mechanism to hit them with all the jargon and watch their eyes glaze over How do you deal with a manager who takes credit for your work and sets impossible deadlines? Should I keep pushing back or just let it go and keep my head down? Any advice! TL;DR: My manager thinks ML projects are plug-and-play, takes credit for my work, and expects me to clean and process data, build models, and deliver results in 10 days. How do I deal with this without snapping? #WorkDrama

Are Genetic Algorithms Still Relevant in 2025?

Hey everyone, I was first introduced to Genetic Algorithms (GAs) during an Introduction to AI course at university, and I recently started reading "Genetic Algorithms in Search, Optimization, and Machine Learning" by David E. Goldberg. While I see that GAs have been historically used in optimization problems, AI, and even bioinformatics, I’m wondering about their practical relevance today. With advancements in deep learning, reinforcement learning, and modern optimization techniques, are they still widely used in research and industry?I’d love to hear from experts and practitioners: In which domains are Genetic Algorithms still useful today? Have they been replaced by more efficient approaches? If so, what are the main alternatives? Beyond Goldberg’s book, what are the best modern resources (books, papers, courses) to deeply understand and implement them in real-world applications? I’m currently working on a hands-on GA project with a friend, and we want to focus on something meaningful rather than just a toy example.

TOP ML University Courses for beginners (FREE)

UC Berkeley UC Berkeley Full Stack Playlist - YouTube Stanford University STEFANO ERMON's Deep Generative Model classes - (Highly Recommended) Stanford CS234: Reinforcement Learning Spring 2024 - Playlist 1 Stanford CS234: Reinforcement Learning Spring 2024 - Playlist 2 Stanford XCS224U: Natural Language Understanding Spring 2023 - Playlist Stanford CS229M: Machine Learning Theory Fall 2021 - Playlist Stanford CS25 - Transformers United ML with Graphs MIT MIT 6.S191: Introduction to Deep Learning Harvard NLP Harvard NLP Code - Official Website CU Boulder AI BY HAND Cornell Tech ML Models UMICH DL for CV

I'm average at math and don't enjoy it. Is the ML path right for me?

I know machine learning is the future, and as an experienced sw engineer, I’m really interested in it. However, I struggle with math and don’t particularly enjoy it. For example, I tried reading Deep Learning by Goodfellow, but the math felt too complex and hard for me to understand. I have a degree in computer science, but I’m wondering if the ML path is right for me given my challenges with math. Should I start with simpler books, such as Introduction to Statistical Learning? Or maybe at deeplearning.ai ? Can you recommend me other resources?

Free YouTube course on introduction to AI and ML

Published a course on AI and ML (beginner to intermediate level) youtube.com/watch?v=ueHIUDYfAq4&list=PLoSocS9HiyjWVjPKLIF6aduFO1XODsviS Grab a coffee and start learning now!

MIT Introduction to Data-Centric AI

Announcing the first-ever course on Data-Centric AI. Learn how to train better ML models by improving the data. Course homepage | Lecture videos on YouTube | Lab Assignments The course covers: Data-Centric AI vs. Model-Centric AI Label Errors Dataset Creation and Curation Data-centric Evaluation of ML Models Class Imbalance, Outliers, and Distribution Shift Growing or Compressing Datasets Interpretability in Data-Centric ML Encoding Human Priors: Data Augmentation and Prompt Engineering Data Privacy and Security MIT, like most universities, has many courses on machine learning (6.036, 6.867, and many others). Those classes teach techniques to produce effective models for a given dataset, and the classes focus heavily on the mathematical details of models rather than practical applications. However, in real-world applications of ML, the dataset is not fixed, and focusing on improving the data often gives better results than improving the model. We’ve personally seen this time and time again in our applied ML work as well as our research. Data-Centric AI (DCAI) is an emerging science that studies techniques to improve datasets in a systematic/algorithmic way — given that this topic wasn’t covered in the standard curriculum, we (a group of PhD candidates and grads) thought that we should put together a new class! We taught this intensive 2-week course in January over MIT’s IAP term, and we’ve just published all the course material, including lecture videos, lecture notes, hands-on lab assignments, and lab solutions, in hopes that people outside the MIT community would find these resources useful. We’d be happy to answer any questions related to the class or DCAI in general, and we’d love to hear any feedback on how we can improve the course material. Introduction to Data-Centric AI is open-source opencourseware, so feel free to make improvements directly: https://github.com/dcai-course/dcai-course.

List of free educational ML resources I used to become a FAANG ML Engineer

Full commentary and notes here ➡️: https://www.trybackprop.com/blog/top\ml\learning\resources Used these to brush up on math and teach myself AI/ML over the course of two years. I'm now a staff ML engineer at FAANG. Hope these help. Fundamentals Linear Algebra – 3Blue1Brown's Essence of Linear Algebra series, binged all these videos on a one hour train ride visiting my parents Multivariable Calculus – Khan Academy's Multivariable Calculus lessons were a great refresher of what I had learned in college. Looking back, I just needed to have reviewed Unit 1 – intro and Unit 2 – derivatives. Calculus for ML – this amazing animated video explains calculus and backpropagation Information Theory – easy-to-understand book on information theory called Information Theory: A Tutorial Introduction. Statistics and Probability – the StatQuest YouTube channel Machine Learning Stanford Intro to Machine Learning by Andrew Ng – Stanford's CS229, the intro to machine learning course, published their lectures on YouTube for free. I watched lectures 1, 2, 3, 4, 8, 9, 11, 12, and 13, and I skipped the rest since I was eager to move onto deep learning. The course also offers a free set of course notes, which are very well written. Caltech Machine Learning – Caltech's machine learning lectures on YouTube, less mathematical and more intuition based Deep Learning Andrej Karpathy's Zero to Hero Series – Andrej Karpathy, an AI researcher who graduated with a Stanford PhD and led Tesla AI for several years, released an amazing series of hands on lectures on YouTube. highly highly recommend Neural networks – Stanford's CS231n course notes and lecture videos were my gateway drug*, so to speak, into the world of deep learning. Transformers and LLMs Transformers – watched these two lectures: lecture from the University of Waterloo and lecture from the University of Michigan. I have also heard good things about Jay Alammar's The Illustrated Transformer guide ChatGPT Explainer – Wolfram's YouTube explainer video on ChatGPT Interactive LLM Visualization – This LLM visualization that you can play with in your browser is hands down the best interactive experience with an LLM. Financial Times' Transformer Explainer – The Financial Times released a lovely interactive article that explains the transformer very well. Residual Learning – 2023 Future Science Prize Laureates Lecture on residual learning. Efficient ML and GPUs How are Microchips Made? – This YouTube video by Branch Education is one of the best free educational videos on the internet, regardless of subject, but also, it's the best video on understanding microchips. CUDA – My L8 and L9 FAANG coworkers acquired their CUDA knowledge from this series of lectures. TinyML and Efficient Deep Learning Computing – 2023 lectures on efficient ML techniques online. Chip War – Chip War is a bestselling book published in 2022 about microchip technology whose beginning chapters on the invention of the microchip actually explain CPUs very well

Getting Back Into AI/ML After a Career Break – Seeking Advice

Hi everyone, I’m a stay-at-home mom looking to restart my career in AI/ML. I have a Bachelor’s in AI and a Master’s in IT, along with experience teaching undergraduate courses like Fundamentals of AI and Artificial Neural Networks (ANN). However, I have a significant gap in my resume, which makes me feel a bit demotivated about re-entering the field. Despite the gap, my passion for AI hasn’t faded—I’m still fascinated by the field and would love to learn Machine Learning from scratch to build a strong foundation and transition into an ML career. I’d really appreciate any advice on: • The best way to relearn ML from scratch (courses, books, hands-on projects) • How to fill the resume gap and make myself a strong candidate again • Any communities, mentorship programs, or networking strategies that might help If anyone has been through a similar situation or has guidance on how to break back into AI/ML after a career break, I’d love to hear your thoughts! Thanks in advance.

How do I get a job in this job market? How do I stand out from the crowd?

About me - I am an international grad student graduating in Spring 2025. I have been applying for jobs and internships since September 2024 and so far I haven't even been able to land a single interview. I am not an absolute beginner in this field. Before coming to grad school I worked as an AI Software Engineer in a startup for more than a year. I have 2 publications one in the WACV workshop and another in ACM TALLIP. I have experience in computer vision and natural language processing, focusing on multimodal learning and real-world AI applications. My academic projects include building vision-language models, segmentation algorithms for medical imaging, and developing datasets with human attention annotations. I’ve also worked on challenging industry projects like automating AI pipelines and deploying real-time classifiers. How can I improve my chances in this competitive job market? Are there specific strategies for international students navigating U.S. tech job applications? How can I stand out, especially when competing with candidates from top schools and with more experience?

Strategies for training AI players on asymmetric games?

I'm familiar with things like self-play in training a player for games like Chess, Checkers, and many other games where move sets and goals are the same for both players - e.g. eliminate the other player's pieces, prevent the other player from moving (like in Amazons, for example), etc. But what about training a computer player for a game where one side has a different goal than the other? Thing like Maker-Breaker Games. I imagine I would want to train a strong Maker and then train a strong Breaker. So it seems like like an application of Reinforcement Learning and more like a Generative Adversarial Network. Does anyone have any reading on these types of problems? Thanks. Additionally, I'm looking to build a home computer with some funds I came into recently to help me train models (I can't depend on cloud services since the money is only available for a short time), and my budget is pretty big for a home system. Where should I go looking for something that is relatively quiet, usable, doesn't raise my electricity bill too high, and is still powerful enough to train models for years to come? I've looked into /r/buildapcforme but folks seem more focused on gaming over there. And I'm pretty hardware ignorant.

Well, I'm starting to read som reaserch paper and to truth I haven't read any till now.

So I have just finished deeplearning.ai course 1and wanted to see som reasrech papers regarding suprivised learning as beginner So, the vetrans of ML can you please suggest some papers for me that I can re-implement on my own.

ZeroToHeroML: Beginner-Friendly ML & AI Course (Free)

Hey r/learnmachinelearning! A friend of mine, who's been a software developer at Sony for 10 years, recently expressed interest in learning Machine Learning (ML) and Artificial Intelligence (AI). Leveraging my background in ML and neural computation (learned at UCSD) to create a beginner-friendly course guiding him through the basics and into more complex projects. Foundational Concepts: Predicting House Prices (Regression): Master regression techniques to forecast housing prices based on various factors. Iris Flower Species Prediction (Classification): Learn classification algorithms by predicting flower species using the famous Iris dataset. Overcoming Overfitting: Explore methods to prevent models from overfitting and enhance their generalizability. In Progress: Customer Segmentation (Unsupervised Learning): Delve into unsupervised learning to group customers based on purchase history or demographics (valuable for targeted marketing campaigns). Deep Learning for Image Recognition: Implement Convolutional Neural Networks (CNNs) to build models that recognize objects or scenes in images. Natural Language Processing Sentiment Analysis: Analyze the sentiment (positive, negative, or neutral) expressed in text data (e.g., reviews, social media posts) using NLP techniques. Introduction to Reinforcement Learning: Get acquainted with the fundamentals of reinforcement learning by creating an agent that learns to navigate a maze. Want to Learn or Contribute? I thought I'd share ZeroToHeroML here so others who want to learn ML/AI or know someone who does can benefit from this free resource! &#x200B; Fork the repo: https://github.com/DilrajS/ZeroToHeroML Share with others interested in ML/AI! Pull requests welcome (help the community grow!). All help is appriciated! Let's conquer ML/AI together!

𝗠𝗮𝘀𝘁𝗲𝗿 𝗟𝗶𝗻𝗲𝗮𝗿 𝗥𝗲𝗴𝗿𝗲𝘀𝘀𝗶𝗼𝗻: 𝗔 𝗠𝘂𝘀𝘁-𝗞𝗻𝗼𝘄 𝗳𝗼𝗿 𝗕𝗲𝗴𝗶𝗻𝗻𝗲𝗿𝘀

Scikit-learn vs Statsmodel Linear regression is often the first model introduced to those stepping into the world of data science and machine learning. A deep understanding of this fundamental concept is crucial for building a solid foundation. In this post, I explore two widely used approaches to linear regression, each with distinct purposes: 1️⃣ 𝗦𝗰𝗶𝗸𝗶𝘁-𝗟𝗲𝗮𝗿𝗻’𝘀 𝗟𝗶𝗻𝗲𝗮𝗿 𝗥𝗲𝗴𝗿𝗲𝘀𝘀𝗶𝗼𝗻: Optimized for machine learning applications and large datasets, this model focuses on efficiency and scalability. 2️⃣ 𝗦𝘁𝗮𝘁𝘀𝗺𝗼𝗱𝗲𝗹𝘀’ 𝗢𝗿𝗱𝗶𝗻𝗮𝗿𝘆 𝗟𝗲𝗮𝘀𝘁 𝗦𝗾𝘂𝗮𝗿𝗲𝘀 (𝗢𝗟𝗦): Known for its comprehensive statistical insights, this approach provides a detailed report ideal for understanding relationships and diagnosing issues like multicollinearity. It’s essential to gain hands-on experience with both libraries to appreciate their unique strengths. To make this learning process more accessible, I’ve created detailed videos and example code to guide you through practical applications: 🎥 𝗛𝗮𝗻𝗱𝘀-𝗢𝗻 𝗧𝘂𝘁𝗼𝗿𝗶𝗮𝗹𝘀: 📌 Learn Linear Regression in Python with LLM Prompt Chaining : https://www.youtube.com/watch?v=KOEG4rs1SUU 📌 In-Depth Linear Regression: Statsmodels OLS, Multicollinearity, and VIF : https://www.youtube.com/watch?v=QQWKY30XzNA 💻 𝗖𝗼𝗱𝗲 𝗳𝗼𝗿 𝗣𝗿𝗮𝗰𝘁𝗶𝗰𝗲: 🔗 Scikit-Learn Implementation: https://github.com/pritkudale/ML-for-Teachers/blob/main/Linear%20Regression/Linear\Regression.ipynb 🔗 Statsmodels Implementation: https://github.com/pritkudale/ML-for-Teachers/blob/main/Linear%20Regression/Linear\regression\using\stats\model.ipynb What makes these tutorials unique? I’ve incorporated LLM prompt chaining, enabling beginners to confidently write code without requiring extensive Python expertise. 📩 𝘚𝘵𝘢𝘺 𝘢𝘩𝘦𝘢𝘥 𝘪𝘯 𝘈𝘐 𝘢𝘥𝘷𝘢𝘯𝘤𝘦𝘮𝘦𝘯𝘵𝘴! 𝘚𝘶𝘣𝘴𝘤𝘳𝘪𝘣𝘦 𝘵𝘰 𝘰𝘶𝘳 𝘯𝘦𝘸𝘴𝘭𝘦𝘵𝘵𝘦𝘳 𝘧𝘰𝘳 𝘦𝘹𝘱𝘦𝘳𝘵 𝘪𝘯𝘴𝘪𝘨𝘩𝘵𝘴: 𝘝𝘪𝘻𝘶𝘢𝘳𝘢 𝘈𝘐 𝘕𝘦𝘸𝘴𝘭𝘦𝘵𝘵𝘦𝘳: https://vizuara.ai/email-newsletter/

Advice Needed

Hey everyone, I’ve been diving into Artificial Intelligence, Machine Learning, and Deep Learning recently, but I find myself a little confused about how to approach the learning process effectively. My goal isn’t just to secure a job but to actually build cool AI products or startups—something innovative and impactful, like what companies such as OpenAI, Anthropic, or ElevenLabs are doing. I often see founders or engineers building incredible AI-driven startups, and I can’t help but wonder: • What kind of learning path did these people follow? • Surely they didn’t just stick to basic Udemy or YouTube courses that most people use for job prep. • What resources or approaches do serious AI practitioners use? I’ve heard that implementing research papers is a great way to gain a deep, intuitive understanding of AI concepts. But as someone who is still a beginner, I’m unsure how to start implementing papers without feeling overwhelmed. Here’s what I’m hoping to get clarity on: Where should I begin as a complete beginner? What resources, projects, or habits would you recommend to build solid fundamentals in AI/ML? How do I progress from beginner to a level where I can implement research papers? Are there intermediate steps I need to take before diving into papers? What would the ideal roadmap look like for someone who wants to build startups in AI? If you’re an AI practitioner, researcher, or startup founder, I’d love to hear about your experiences and learning pathways. What worked for you? What didn’t? Any advice or resources would be immensely appreciated. I’m ready to put in the hard work, I just want to make sure I’m moving in the right direction. Thanks in advance! Looking forward to learning from this community.

Looking for the Best Resources to Level Up in Python, AI, ML, and Data Science!

Hey everyone, I've been diving into AI, ML, and Data Science for a while now and have completed the IBM AI Engineering Course and the Machine Learning Specialization by Andrew Ng on Coursera. Both were super helpful to get me started on beginner-level implementation. However, I'm really looking to take my skills to the next level and go pro! 🎯 I’m looking for awesome from 0 to total hero tutorials/coding videos, especially on YouTube, and the best books you’ve come across. I'm particularly interested in: Python for AI/ML/Data Science Advanced AI/ML topics (hands-on projects would be a plus!) Awesome books (I already have a PDF of O'Reilly's Data Science* book with the black and yellow reptile on the cover and just started reading that since its a bit pricy in India) Any recommendations for resources (free or affordable if possible) would be amazing. Also, if anyone could suggest a solid book for Java Data Structures and Algorithms, that’d be awesome. I already know the concepts but want something to keep on hand for reference. Thanks a ton in advance for any suggestions! 🙌

Neural Networks you can try to implement from scratch (for beginners)

I was reading a tweet talking about how useful it is to implement neural networks from scratch. How it allowed for a greater understanding of the topic. The author said he found it more useful than other people explaining the concept to him. While I disagree with the author’s opinion that it stops the need for explanations. It certainly does help the understanding of one’s model. I recommend giving it a go. In the blog post, I will suggest which models you should try to implement from scratch using NumPy or your favourite library. Also, I will link to some accompanying resources. Simple Feedforward Network This is the most famous example because it’s so simple. But allows you to learn so much. I heard about this idea from Andrew Trask. It also helped me think about implementing networks from scratch in general. In the Feedforward network, you will be using NumPy. As you won't need Pytorch or TensorFlow. To do the heavy-lifting for complex calculations. You can simply create a Numpy Array for training and testing data. You can also create a nonlinear function using Numpy. Then work out the error rate between the layer’s guess and real data. Resource for this task: https://iamtrask.github.io/2015/07/12/basic-python-network/ Follow this tutorial. It does a much better job of explaining how to do this in NumPy. With code examples to follow. Feedforward Network with Gradient Descent This is an extension of the network above. In this network, we allow the model to optimise its weights. This can also be done in NumPy. Resource for this task: https://iamtrask.github.io/2015/07/27/python-network-part2/ A follow-on from the previous article. Pytorch version of Perceptrons and Multi-layered Perceptrons. Here will go up a level by using a library. Examples I'm using will be done in Pytorch. But you can use whatever library you prefer. When implementing these networks, you learn how much a library does the work for you. Recourses for the task: https://medium.com/@tomgrek/building-your-first-neural-net-from-scratch-with-pytorch-56b0e9c84d54 https://becominghuman.ai/pytorch-from-first-principles-part-ii-d37529c57a62 K Means Clustering Yes, this does not count as a neural network. But a traditional machine learning algorithm is still very useful. As this is non deep learning algorithm it should be easier to understand. This can be done just using NumPy or Pandas depending on the implementation. Recourse for this task: https://www.machinelearningplus.com/predictive-modeling/k-means-clustering/ http://madhugnadig.com/articles/machine-learning/2017/03/04/implementing-k-means-clustering-from-scratch-in-python.html https://gdcoder.com/implementation-of-k-means-from-scratch-in-python-9-lines/ There are quite a few choices to choose from. So pick whatever implementation helps you understand the concepts better. These networks or models should be simple enough that you won't get lost trying to implement them. But still, help learn a few stuff along the way. \- If you found this post useful, then check out my mailing list where I write more stuff like this.

Best AI/ML course for Beginners to advanced - recommendations?

Hey everyone, I’m looking for some solid AI/ML courses that cover everything from the basics to advanced topics. I want a structured learning path that helps me understand fundamental concepts like linear regression, neural networks, and deep learning, all the way to advanced topics like transformers, reinforcement learning, and real-world applications. Ideally, the course(s) should: • Be beginner-friendly but progress to advanced topics • Have practical, hands-on projects • Cover both theory and implementation (Python, TensorFlow, PyTorch, etc.) • Be well-structured and up to date I’m open to free and paid options (Coursera, Udemy, YouTube, etc.). What are some of the best courses you’d recommend? Thanks in advance!

[Help Needed] How to tackle AI for DNS Security in a Hackathon for Beginner.

Hi everyone! I've been selected to participate in an AI and Cybersecurity Hackathon, and the group I'm in focuses on AI for DNS Security. Our goal is to implement AI algorithms to detect anomalies and enhance DNS security. Here’s the catch: I have no prior background in cybersecurity, and I’m also a beginner in applying AI to real-world security problems. I’d really appreciate some guidance from this amazing community on how to approach this challenge. A bit more about the project: Objective: Detect anomalies in DNS traffic (e.g., malicious requests, tunneling, etc.). AI tools: We’re free to choose algorithms, but I’m unsure where to start—supervised vs. unsupervised learning? My skillset: Decent grasp of Python (Pandas, Scikit-learn, etc.) and basic ML concepts. No practical experience in network security or analyzing DNS traffic. What I’m looking for: Datasets: Any recommendations for open-source DNS datasets or synthetic data creation methods? AI methods: Which models work best for anomaly detection in DNS logs? Are there any relevant GitHub projects? Learning resources: Beginner-friendly material on DNS security and the application of AI in this domain. Hackathon tips: How can I make the most of this opportunity and contribute effectively to my team? Bonus question: If you’ve participated in similar hackathons, what strategies helped you balance learning and execution within a short timeframe? Thank you so much in advance for any advice, resources, or personal experiences you can share! I’ll make sure to share our project results and lessons learned after the hackathon.

Seeking Guidance on Implementing LLM and Generative AI in a New Role.

Hi everyone, I recently got a job that involves implementing LLM and Generative AI. During the interview, we discussed topics like Reinforcement Learning, Deep Learning, and Machine Learning. I’m finishing my MSc in Computer Science, where I’ve worked on projects involving simple Deep Learning implementations (data extraction, cleaning some MLP). Essentially, I will have access to servers for computing and a laptop, and I’ll be the sole programmer responsible for establishing and demonstrating value. I am looking for resources and maybe some examples of how to do that so far I have recommended: Hugging Face - Documentation Intro to Large Language Models by Andrej Karpathy I also plan to attend local meetups about LLM and PyTorch. I’m looking for practical advice on learning these technologies while developing them, particularly regarding development workflows, cloud backups, and coding standards, as I will be working independently. I know if I can achieve something easier and faster with a simple Machine Learning model I will do that. Any help would be greatly appreciated.

How is ML/AI implemented in your company?

Hi, I am currently working as a full time SWE. I generally get to work with data/build solutions using data but I don't have any official ML/Data science title or background. Ideally, I'd like to be able to start making more intelligent decisions using that data and that's why I am interested on machine learning. Ideally, I'd like to write production systems that leverage models that I can build and understand end to end but after some research, I am not sure if such jobs exist today or if teams are usually split between modelling team (people that only train and analyze models) and SWE teams (people that take such models and focus on deploying them on production). My current company is using that model of development, so I might need to leave to be able to do what I want. I imagine startups work that way, but I am looking for some stability. Thanks!

What is the best setup to implement for Ai

first of all I'm a fresh machine learning eng(not working yet) and my laptop system running on 128gb ssd + usual 1tb hdd + gtx1050. I used to install python locally and its libraries (from numpy and pandas to tensorflow and pytorch) with vscode (instead of anaconda) and I was happy about that. whenever I do project and want to deploy it i used pepenv. I got problems in storage when it comes to docker or cuda or wsl recently I got an storage upgrade to 512gb ssd and looking for new ideas and approaches about my new instlations What Should I do for each aspect use anaconda and make different environments (I feel this gonna drain storage specially I don't know what should each env contain) Shoul I use docker for windows or install wsl and install docker through it. Same for cuda should i install cuda native windows installation or intall it using wsl I don't try how to use programs in wsl for ex. I don't know how to use cuda on local development if it installed in wsl same as docker I know my gtx1050 won't be effecient when it comes to cuda and maybe more effective to use colab or kaggle gpu. but it's better practice i guess to develop on cuda.

GPT Weekly - 19the June Edition - OpenAI's function calling, Meta's free LLM, EU Regulation and more.

This is a recap covering the major news from last week. 🔥Top 3 news - OpenAI’s updates, Meta’s upcoming free LLM and EU Regulation 🗞️Interesting reads include PSA about protecting your keys, The GPT ouroboros, Reddit - OpenAI’s moat, and more.. 🧑‍🎓Learning includes a Step-by-step guide from a non-technical founder who launched his MVP, Chatbot for your Gdrive and more 🔥Top 3 AI news in the past week OpenAI: New Pricing, Models, & Functions OpenAI has been on a roll. Last week we saw the release of OpenAI best practice on using GPT. This week we saw some amazing updates. Three major buckets were: First, the price decreases for both embeddings and GPT-3.5 tokens. Second, new models for gpt-4 and gpt-3.5. A new longer context model for gpt-3.5. Third, a new function calling capability. Why is it important? Previously, the output from OpenAI was all text. So, calling an external API from GPT was quite difficult. You had to parse the text data and things were often incorrect. Langchain created the Agents and Tools feature to tackle this problem. It was still unreliable and prone to issues. Now you get native support to generate a fixed format output. You can use the output to generate functional calls and also pass functions which need to be called. For example, if your app has multiple API endpoints then you can use GPT to generate the API calls with parameters. You can also pass the endpoints as function calls to ensure the correct function is executed. This functionality can further be used to generate structured data (JSON) out of GPT. So, you can generate data from GPT and load it into your backend. What’s next? This functionality allows turning natural language responses into structured data. This can be used to create “intelligent” backends using LLMs. We might see implementations in no-code tools to allow more robust and natural-language tools for non-technical folks. The structured data process goes both ways. You can also feed structured data into GPT for better responses. This feature also has its share of issues. Function calling suffers from the same prompt injection issues. Malicious actors can pass malicious code in function or the responses. For example, creation of queries using functions might contain malicious code to delete data. Without proper user validation this code will be executed automatically and delete data. So, using LLM as the back-end layer needs proper security implementation. Meta's LLM: Commercial Use Ahead Llama has been a boon for the open source community. Many of the open source models rely on Llama. The issue is that Llama is research-only and cannot be used commercially. So, no one can use it to build any product. Meta is now working on the next version of the model. This model will be available for commercial use. This is in stark contrast to both OpenAI and Google. Both safe-guarde their models and make it available through API. Why is it important? Certain industries cannot use LLM APIs because of strict restrictions on data privacy. These companies would want to run their own instance of a foundational model. A commercially available foundational model is also going to help people who want to keep their “API call” costs next to 0. A commercially available free-for-all model will also help push the open source community further. Just like Llama. What’s next? Sam Altman has said OpenAI didn’t release GPT-3 as open-source because they didn’t think people would be able to run it. Now OpenAI is working on an open-source model. This is going to be weaker than GPT-4. Let the battle of LLMs begin. EU's Proposed Legislation and Its Impact on AI Usage The EU parliament voted to move ahead with the E.U. AI Act. This act aims to ensure consumer protection against the dangers of AI. Why is it important? OpenAI and Sam Altman want regulations for models. They have proposed a IAEA-type of agency to stop the proliferation of LLM models. As per OpenAI, all models should be regulated and monitored. The suggestion of a license based regulation has led to significant backlash. Many people have called it “regulatory capture” - with the aim of shutting down competing LLMs. Licensing based regulations might not really be effective. The EU is approaching regulation from a different angle. It doesn’t focus on how models are developed. Rather focuses on how AI will/can be used. They have broken down use cases into 4 categories - unacceptable (prohibited), high, medium and low risk. For example, Building a Pre-Crime software,on%20crimes%20not%20yet%20committed.) to predict crimes? Building a Social credit system? Unacceptable. Using tools to influence elections or recommendation algorithms? High (Highly regulated). Using generative AI tools to create text or images on news sites? Medium (Add label that the content is AI generated) AI providers also need to disclose their training source. To me this sounds like good legislation. What do you guys think? But, OpenAI has warned that EU regulations might force them to pull out completely. What’s next? The disclosure requirements might help various publishing companies. AI and media companies are in talks to pay for training data. Google has been leading the charge. Additionally, OpenAI and Deepmind will open their models for safety and research purposes to the UK government. 🗞️10 AI news highlights and interesting reads PSA: If you are using Repl to write code, you might want to check your OpenAI API keys. If you have left them embedded then people can pirate and steal the keys. LLMs rely on human annotation or human feedback to learn. And one way to generate human annotation is crowdsourcing. But what if the crowdsource human annotators use LLMs? Research shows 33-46% workers used LLMs. So, basically we go from Human -> AI -> Human -> AI. The AI ouroboros. Researchers also say generated data to train models might cause serious issue. All the talks about moats \- Reddit might be OpenAI’s \future\ moat. Given the amount of complaints about how Google search experience has deteriorated during the blackout, this might be true? Doctors are using ChatGPT but not to diagnose.Rather to be more empathetic. We discussed this just a month ago. And guess where the data for this study came from? Reddit AskDocs. Moat FTW?! Beatles to make a comeback…using Generative AI. SnapFusion - Text to Image diffusion on mobile phones. Large context lengths are important for better GPT experience. The secret sauce for 100k context length. There is a lot of bad AI research out there. Some border on snake oil. Most AI “research” should be double checked and challenged. A new research on huggingface said that GPT-4 can ace MIT curriculum. Now someone is replicating the results and say that GPT-4 can’t beat MIT. Are we seeing peak AI? Especially when people from Deepmind and Meta are involved? Mistral AI raised $113 million in seed round with no product. Some might say this funding is for the team and the team is really solid. The issue though is whether the valuation is justified when OpenAI and Google already have a head start. The AI Hype Wall of Shame. \- Collection of articles which mislead people about AI in various aspects. 🧑‍🎓3 Learning Resources Building and Launching a company using GPT-4 with prompts. (The author didn’t know how to code but created and launched the MVP in a month). Chatbot for your Gdrive - https://www.haihai.ai/gpt-gdrive/ Building ChatGPT plugin using Supabase - https://supabase.com/blog/building-chatgpt-plugins-template That’s it folks. Thank you for reading and have a great week ahead. If you are interested in a focused weekly recap delivered to your inbox on Mondays you can subscribe here. It is FREE!

A little help, please!

I'm working on a prototype and could use some feedback! Would any business leaders be interested in a platform that provides personalized ML/AI solutions at much lower costs and higher efficiency compared to generic LLMs? I'm finding that LLMs aren't the best solution for every ML problem, and I'm wondering if there's a demand for a more tailored, cost-effective alternative. Would love to hear your thoughts or experiences! #AI #MachineLearning #Entrepreneur #Tech

Randomly asked ChatGPT and Claude for a 4 year roadmap for an ML Engineer

Title, Is it actually a good plan ?? If no, why not ?? \\🚀 4-Year Roadmap to Becoming a High-Earning ML Engineer & Entrepreneur\\ \\(With Smartwork & Realistic 60-70% Execution Feasibility)\\ \\🟢 Year 1: Strong Foundation & Initial Projects (0-12 Months)\\ 🎯 \\Goal: Master Python & ML Fundamentals\\ \\🔹 1-4 Months (Python & Math Strengthening)\\ ✅ Python Mastery \- Daily LeetCode Easy problems (minimum 2) \- Build automation projects \- NumPy & Pandas mastery \- DSA fundamentals ✅ Mathematics Foundation \- Linear Algebra basics \- Statistics fundamentals \- Basic calculus concepts ✅ First Mini-Hackathon Participation \- Join beginner-friendly hackathons \- Focus on Python-based challenges \- Team up with other beginners 💡 \\Smart Move:\\ \- Join Discord/Slack hackathon communities \- Practice collaborative coding \- Build network with fellow participants \\🔹 5-8 Months (ML Foundations)\\ ✅ Machine Learning Basics \- Supervised Learning \- Model evaluation \- Feature engineering \- scikit-learn projects ✅ Participate in 2-3 ML Hackathons \- Kaggle Getting Started competitions \- Local ML hackathons \- University hackathons ✅ Start LinkedIn & GitHub Portfolio 💡 \\Smart Move:\\ \- Document hackathon experiences \- Share learnings on LinkedIn \- Focus on completion over winning \\🔹 9-12 Months (Deep Learning Introduction)\\ ✅ Basic Deep Learning \- Neural network fundamentals \- PyTorch basics \- Computer vision tasks \- Basic NLP ✅ Advanced Hackathon Participation \- AI/ML specific hackathons \- Team lead in 1-2 hackathons \- Start mentoring beginners \\🔵 Year 1 Expected Outcome (60-70% Execution)\\ ✔ \\Strong Python & ML foundations\\ ✔ \\5-6 hackathon participations\\ ✔ \\Active GitHub (100+ commits)\\ ✔ \\Growing LinkedIn (300+ connections)\\ 💰 \\Earning Expectation → ₹8K-₹20K per month (Projects/Internship)\\ \\🟢 Year 2: Professional Growth & Specialization (12-24 Months)\\ 🎯 \\Goal: Build Professional Experience & Recognition\\ \\🔹 1-6 Months (Technical Depth)\\ ✅ Advanced ML Topics \- Deep Learning architectures \- Computer Vision OR NLP \- MLOps basics (Docker, FastAPI) \- Cloud fundamentals (AWS/GCP) ✅ Hackathon Achievements \- Win minor prizes in 2-3 hackathons \- Lead teams in major hackathons \- Network with sponsors ✅ Start Technical Blogging 💡 \\Smart Move:\\ \- Focus on hackathon projects that align with career goals \- Build relationships with companies at hackathons \- Create detailed project documentation \\🔹 7-12 Months (Professional Experience)\\ ✅ Secure ML Role/Internship ✅ Advanced Project Building ✅ Open Source Contributions ✅ Organize Small Hackathons 💡 \\Smart Move:\\ \- Use hackathon network for job referrals \- Convert hackathon projects into full products \- Build mentor reputation \\🔵 Year 2 Expected Outcome (60-70% Execution)\\ ✔ \\Professional ML experience\\ ✔ \\10+ hackathon participations\\ ✔ \\1-2 hackathon wins\\ ✔ \\Strong industry network\\ 💰 \\Earning Expectation → ₹40K-₹70K per month (Job/Freelancing)\\ \\🟢 Year 3: Scaling & Business Foundation (24-36 Months)\\ 🎯 \\Goal: Establish Multiple Income Streams\\ \\🔹 1-4 Months (Expertise Building)\\ ✅ Choose Specialization \- MLOps \- Computer Vision \- NLP/LLMs \- Generative AI ✅ Advanced Competitions \- International hackathons \- High-prize competitions \- Corporate ML challenges ✅ Start Consulting Services 💡 \\Smart Move:\\ \- Use hackathon wins for marketing \- Build service packages around expertise \- Network with corporate sponsors \\🔹 5-8 Months (Business Development)\\ ✅ Scale Services ✅ Build Client Network ✅ Create Training Programs ✅ Hackathon Mentorship Program 💡 \\Smart Move:\\ \- Convert hackathon projects to products \- Use event networks for client acquisition \- Build authority through speaking \\🔹 9-12 Months (Growth & Innovation)\\ ✅ Product Development ✅ Team Building ✅ Innovation Focus ✅ Hackathon Organization \\🔵 Year 3 Expected Outcome (60-70% Execution)\\ ✔ \\Established ML business/career\\ ✔ \\Known in hackathon community\\ ✔ \\Multiple income streams\\ ✔ \\Strong industry presence\\ 💰 \\Earning Expectation → ₹1L-₹2L per month (Multiple Streams)\\ \\🟢 Year 4: Scale & Leadership (36-48 Months)\\ 🎯 \\Goal: Build AI Company & Achieve Financial Freedom\\ \\🔹 1-4 Months (Business Scaling)\\ ✅ Company Formation \- AI consulting firm \- Product development \- Training programs ✅ Hackathon Innovation \- Launch own hackathon series \- Corporate partnerships \- Prize sponsorships ✅ Team Expansion 💡 \\Smart Move:\\ \- Use hackathon network for hiring \- Create unique event formats \- Build corporate relationships \\🔹 5-8 Months (Market Leadership)\\ ✅ Product Launch ✅ Service Expansion ✅ International Presence ✅ Innovation Hub Creation 💡 \\Smart Move:\\ \- Create hackathon-to-hiring pipeline \- Build educational programs \- Establish thought leadership \\🔹 9-12 Months (Empire Building)\\ ✅ Multiple Revenue Streams \- AI products \- Consulting services \- Educational programs \- Event organization \- Investment returns ✅ Industry Leadership \- Conference speaking \- Published content \- Community leadership \\🔵 Year 4 Expected Outcome (60-70% Execution)\\ ✔ \\Established AI company\\ ✔ \\Major hackathon organizer\\ ✔ \\Multiple product lines\\ ✔ \\Industry authority status\\ 💰 \\Earning Expectation → ₹3L-₹5L+ per month (Business Income)\\ \\📊 FINAL RATING\\ ✅ \\Comprehensive growth plan\\ ✅ \\Strong community focus\\ ✅ \\Multiple income pathways\\ 💡 \\If 100% Execution → 8.5/10 Feasibility\\ 💡 \\If 50% Execution → 6/10 Feasibility\\ 🔥 \\Conclusion: A balanced path to ML mastery and entrepreneurship, built through consistent growth and community engagement!\\ 🚀 \\Key Success Factors:\\ Regular hackathon participation Strong community involvement Consistent skill development Strategic network building Focus on both technical and business growth

AI for Entrepreneurs Podcast- Adrian Rosebrock

We have a new episode of our podcast series AI for Entrepreneurs! Today, we will talk to Adrian Rosebrock, a successful entrepreneur and the author of a popular computer vision and machine learning blog PyImageSearch.  Adrian shares his thoughts on how to build an audience, how to come up with product ideas, and how to manage time for maximum productivity. In addition, he gives advice to people who want to get started in AI. His story is one of tremendous grit, extreme discipline, and relentless execution and you can watch it at https://www.youtube.com/watch?v=z5KWHMOb1H8.

MMML | Deploy HuggingFace training model rapidly based on MetaSpore

A few days ago, HuggingFace announced a $100 million Series C funding round, which was big news in open source machine learning and could be a sign of where the industry is headed. Two days before the HuggingFace funding announcement, open-source machine learning platform MetaSpore released a demo based on the HuggingFace Rapid deployment pre-training model. As deep learning technology makes innovative breakthroughs in computer vision, natural language processing, speech understanding, and other fields, more and more unstructured data are perceived, understood, and processed by machines. These advances are mainly due to the powerful learning ability of deep learning. Through pre-training of deep models on massive data, the models can capture the internal data patterns, thus helping many downstream tasks. With the industry and academia investing more and more energy in the research of pre-training technology, the distribution warehouses of pre-training models such as HuggingFace and Timm have emerged one after another. The open-source community release pre-training significant model dividends at an unprecedented speed. In recent years, the data form of machine modeling and understanding has gradually evolved from single-mode to multi-mode, and the semantic gap between different modes is being eliminated, making it possible to retrieve data across modes. Take CLIP, OpenAI’s open-source work, as an example, to pre-train the twin towers of images and texts on a dataset of 400 million pictures and texts and connect the semantics between pictures and texts. Many researchers in the academic world have been solving multimodal problems such as image generation and retrieval based on this technology. Although the frontier technology through the semantic gap between modal data, there is still a heavy and complicated model tuning, offline data processing, high performance online reasoning architecture design, heterogeneous computing, and online algorithm be born multiple processes and challenges, hindering the frontier multimodal retrieval technologies fall to the ground and pratt &whitney. DMetaSoul aims at the above technical pain points, abstracting and uniting many links such as model training optimization, online reasoning, and algorithm experiment, forming a set of solutions that can quickly apply offline pre-training model to online. This paper will introduce how to use the HuggingFace community pre-training model to conduct online reasoning and algorithm experiments based on MetaSpore technology ecology so that the benefits of the pre-training model can be fully released to the specific business or industry and small and medium-sized enterprises. And we will give the text search text and text search graph two multimodal retrieval demonstration examples for your reference. Multimodal semantic retrieval The sample architecture of multimodal retrieval is as follows: Our multimodal retrieval system supports both text search and text search application scenarios, including offline processing, model reasoning, online services, and other core modules: https://preview.redd.it/mdyyv1qmdz291.png?width=1834&format=png&auto=webp&s=e9e10710794c78c64cc05adb75db385aa53aba40 Offline processing, including offline data processing processes for different application scenarios of text search and text search, including model tuning, model export, data index database construction, data push, etc. Model inference. After the offline model training, we deployed our NLP and CV large models based on the MetaSpore Serving framework. MetaSpore Serving helps us conveniently perform online inference, elastic scheduling, load balancing, and resource scheduling in heterogeneous environments. Online services. Based on MetaSpore’s online algorithm application framework, MetaSpore has a complete set of reusable online search services, including Front-end retrieval UI, multimodal data preprocessing, vector recall and sorting algorithm, AB experimental framework, etc. MetaSpore also supports text search by text and image scene search by text and can be migrated to other application scenarios at a low cost. The HuggingFace open source community has provided several excellent baseline models for similar multimodal retrieval problems, which are often the starting point for actual optimization in the industry. MetaSpore also uses the pre-training model of the HuggingFace community in its online services of searching words by words and images by words. Searching words by words is based on the semantic similarity model of the question and answer field optimized by MetaSpore, and searching images by words is based on the community pre-training model. These community open source pre-training models are exported to the general ONNX format and loaded into MetaSpore Serving for online reasoning. The following sections will provide a detailed description of the model export and online retrieval algorithm services. The reasoning part of the model is standardized SAAS services with low coupling with the business. Interested readers can refer to my previous post: The design concept of MetaSpore, a new generation of the one-stop machine learning platform. 1.1 Offline Processing Offline processing mainly involves the export and loading of online models and index building and pushing of the document library. You can follow the step-by-step instructions below to complete the offline processing of text search and image search and see how the offline pre-training model achieves reasoning at MetaSpore. 1.1.1 Search text by text Traditional text retrieval systems are based on literal matching algorithms such as BM25. Due to users’ diverse query words, a semantic gap between query words and documents is often encountered. For example, users misspell “iPhone” as “Phone,” and search terms are incredibly long, such as “1 \~ 3 months old baby autumn small size bag pants”. Traditional text retrieval systems will use spelling correction, synonym expansion, search terms rewriting, and other means to alleviate the semantic gap but fundamentally fail to solve this problem. Only when the retrieval system fully understands users’ query terms and documents can it meet users’ retrieval demands at the semantic level. With the continuous progress of pre-training and representational learning technology, some commercial search engines continue to integrate semantic vector retrieval methods based on symbolic learning into the retrieval ecology. Semantic retrieval model This paper introduces a set of semantic vector retrieval applications. MetaSpore built a set of semantic retrieval systems based on encyclopedia question and answer data. MetaSpore adopted the Sentence-Bert model as the semantic vector representation model, which fine-tunes the twin tower BERT in supervised or unsupervised ways to make the model more suitable for retrieval tasks. The model structure is as follows: The query-Doc symmetric two-tower model is used in text search and question and answer retrieval. The vector representation of online Query and offline DOC share the same vector representation model, so it is necessary to ensure the consistency of the offline DOC library building model and online Query inference model. The case uses MetaSpore’s text representation model Sbert-Chinese-QMC-domain-V1, optimized in the open-source semantically similar data set. This model will express the question and answer data as a vector in offline database construction. The user query will be expressed as a vector by this model in online retrieval, ensuring that query-doc in the same semantic space, users’ semantic retrieval demands can be guaranteed by vector similarity metric calculation. Since the text presentation model does vector encoding for Query online, we need to export the model for use by the online service. Go to the q&A data library code directory and export the model concerning the documentation. In the script, Pytorch Tracing is used to export the model. The models are exported to the “./export “directory. The exported models are mainly ONNX models used for wired reasoning, Tokenizer, and related configuration files. The exported models are loaded into MetaSpore Serving by the online Serving system described below for model reasoning. Since the exported model will be copied to the cloud storage, you need to configure related variables in env.sh. \Build library based on text search \ The retrieval database is built on the million-level encyclopedia question and answer data set. According to the description document, you need to download the data and complete the database construction. The question and answer data will be coded as a vector by the offline model, and then the database construction data will be pushed to the service component. The whole process of database construction is described as follows: Preprocessing, converting the original data into a more general JSonline format for database construction; Build index, use the same model as online “sbert-Chinese-qmc-domain-v1” to index documents (one document object per line); Push inverted (vector) and forward (document field) data to each component server. The following is an example of the database data format. After offline database construction is completed, various data are pushed to corresponding service components, such as Milvus storing vector representation of documents and MongoDB storing summary information of documents. Online retrieval algorithm services will use these service components to obtain relevant data. 1.1.2 Search by text Text and images are easy for humans to relate semantically but difficult for machines. First of all, from the perspective of data form, the text is the discrete ID type of one-dimensional data based on words and words. At the same time, images are continuous two-dimensional or three-dimensional data. Secondly, the text is a subjective creation of human beings, and its expressive ability is vibrant, including various turning points, metaphors, and other expressions, while images are machine representations of the objective world. In short, bridging the semantic gap between text and image data is much more complex than searching text by text. The traditional text search image retrieval technology generally relies on the external text description data of the image or the nearest neighbor retrieval technology and carries out the retrieval through the image associated text, which in essence degrades the problem to text search. However, it will also face many issues, such as obtaining the associated text of pictures and whether the accuracy of text search by text is high enough. The depth model has gradually evolved from single-mode to multi-mode in recent years. Taking the open-source project of OpenAI, CLIP, as an example, train the model through the massive image and text data of the Internet and map the text and image data into the same semantic space, making it possible to implement the text and image search technology based on semantic vector. CLIP graphic model The text search pictures introduced in this paper are implemented based on semantic vector retrieval, and the CLIP pre-training model is used as the two-tower retrieval architecture. Because the CLIP model has trained the semantic alignment of the twin towers’ text and image side models on the massive graphic and text data, it is particularly suitable for the text search graph scene. Due to the different image and text data forms, the Query-Doc asymmetric twin towers model is used for text search image retrieval. The image-side model of the twin towers is used for offline database construction, and the text-side model is used for the online return. In the final online retrieval, the database data of the image side model will be searched after the text side model encodes Query, and the CLIP pre-training model guarantees the semantic correlation between images and texts. The model can draw the graphic pairs closer in vector space by pre-training on a large amount of visual data. Here we need to export the text-side model for online MetaSpore Serving inference. Since the retrieval scene is based on Chinese, the CLIP model supporting Chinese understanding is selected. The exported content includes the ONNX model used for online reasoning and Tokenizer, similar to the text search. MetaSpore Serving can load model reasoning through the exported content. Build library on Image search You need to download the Unsplash Lite library data and complete the construction according to the instructions. The whole process of database construction is described as follows: Preprocessing, specify the image directory, and then generate a more general JSOnline file for library construction; Build index, use OpenAI/Clip-Vit-BASE-Patch32 pre-training model to index the gallery, and output one document object for each line of index data; Push inverted (vector) and forward (document field) data to each component server. Like text search, after offline database construction, relevant data will be pushed to service components, called by online retrieval algorithm services to obtain relevant data. 1.2 Online Services The overall online service architecture diagram is as follows: &#x200B; https://preview.redd.it/nz8zrbbpdz291.png?width=1280&format=png&auto=webp&s=28dae7e031621bc8819519667ed03d8d085d8ace Multi-mode search online service system supports application scenarios such as text search and text search. The whole online service consists of the following parts: Query preprocessing service: encapsulate preprocessing logic (including text/image, etc.) of pre-training model, and provide services through gRPC interface; Retrieval algorithm service: the whole algorithm processing link includes AB experiment tangent flow configuration, MetaSpore Serving call, vector recall, sorting, document summary, etc.; User entry service: provides a Web UI interface for users to debug and track down problems in the retrieval service. From a user request perspective, these services form invocation dependencies from back to front, so to build up a multimodal sample, you need to run each service from front to back first. Before doing this, remember to export the offline model, put it online and build the library first. This article will introduce the various parts of the online service system and make the whole service system step by step according to the following guidance. See the ReadME at the end of this article for more details. 1.2.1 Query preprocessing service Deep learning models tend to be based on tensors, but NLP/CV models often have a preprocessing part that translates raw text and images into tensors that deep learning models can accept. For example, NLP class models often have a pre-tokenizer to transform text data of string type into discrete tensor data. CV class models also have similar processing logic to complete the cropping, scaling, transformation, and other processing of input images through preprocessing. On the one hand, considering that this part of preprocessing logic is decoupled from tensor reasoning of the depth model, on the other hand, the reason of the depth model has an independent technical system based on ONNX, so MetaSpore disassembled this part of preprocessing logic. NLP pretreatment Tokenizer has been integrated into the Query pretreatment service. MetaSpore dismantlement with a relatively general convention. Users only need to provide preprocessing logic files to realize the loading and prediction interface and export the necessary data and configuration files loaded into the preprocessing service. Subsequent CV preprocessing logic will also be integrated in this manner. The preprocessing service currently provides the gRPC interface invocation externally and is dependent on the Query preprocessing (QP) module in the retrieval algorithm service. After the user request reaches the retrieval algorithm service, it will be forwarded to the service to complete the data preprocessing and continue the subsequent processing. The ReadMe provides details on how the preprocessing service is started, how the preprocessing model exported offline to cloud storage enters the service, and how to debug the service. To further improve the efficiency and stability of model reasoning, MetaSpore Serving implements a Python preprocessing submodule. So MetaSpore can provide gRPC services through user-specified preprocessor.py, complete Tokenizer or CV-related preprocessing in NLP, and translate requests into a Tensor that deep models can handle. Finally, the model inference is carried out by MetaSpore, Serving subsequent sub-modules. Presented here on the lot code: https://github.com/meta-soul/MetaSpore/compare/add\python\preprocessor 1.2.2 Retrieval algorithm services Retrieval algorithm service is the core of the whole online service system, which is responsible for the triage of experiments, the assembly of algorithm chains such as preprocessing, recall, sorting, and the invocation of dependent component services. The whole retrieval algorithm service is developed based on the Java Spring framework and supports multi-mode retrieval scenarios of text search and text search graph. Due to good internal abstraction and modular design, it has high flexibility and can be migrated to similar application scenarios at a low cost. Here’s a quick guide to configuring the environment to set up the retrieval algorithm service. See ReadME for more details: Install dependent components. Use Maven to install the online-Serving component Search for service configurations. Copy the template configuration file and replace the MongoDB, Milvus, and other configurations based on the development/production environment. Install and configure Consul. Consul allows you to synchronize the search service configuration in real-time, including cutting the flow of experiments, recall parameters, and sorting parameters. The project’s configuration file shows the current configuration parameters of text search and text search. The parameter modelName in the stage of pretreatment and recall is the corresponding model exported in offline processing. Start the service. Once the above configuration is complete, the retrieval service can be started from the entry script. Once the service is started, you can test it! For example, for a user with userId=10 who wants to query “How to renew ID card,” access the text search service. 1.2.3 User Entry Service Considering that the retrieval algorithm service is in the form of the API interface, it is difficult to locate and trace the problem, especially for the text search image scene can intuitively display the retrieval results to facilitate the iterative optimization of the retrieval algorithm. This paper provides a lightweight Web UI interface for text search and image search, a search input box, and results in a display page for users. Developed by Flask, the service can be easily integrated with other retrieval applications. The service calls the retrieval algorithm service and displays the returned results on the page. It’s also easy to install and start the service. Once you’re done, go to http://127.0.0.1:8090 to see if the search UI service is working correctly. See the ReadME at the end of this article for details. Multimodal system demonstration The multimodal retrieval service can be started when offline processing and online service environment configuration have been completed following the above instructions. Examples of textual searches are shown below. Enter the entry of the text search map application, enter “cat” first, and you can see that the first three digits of the returned result are cats: https://preview.redd.it/d7syq47rdz291.png?width=1280&format=png&auto=webp&s=b43df9abd380b7d9a52e3045dd787f4feeb69635 If you add a color constraint to “cat” to retrieve “black cat,” you can see that it does return a black cat: &#x200B; https://preview.redd.it/aa7pxx8tdz291.png?width=1280&format=png&auto=webp&s=e3727c29d1bde6eea2e1cccf6c46d3cae3f4750e Further, strengthen the constraint on the search term, change it to “black cat on the bed,” and return results containing pictures of a black cat climbing on the bed: &#x200B; https://preview.redd.it/2mw4qpjudz291.png?width=1280&format=png&auto=webp&s=1cf1db667892b9b3a40451993680fbd6980b5520 The cat can still be found through the text search system after the color and scene modification in the above example. Conclusion The cutting-edge pre-training technology can bridge the semantic gap between different modes, and the HuggingFace community can greatly reduce the cost for developers to use the pre-training model. Combined with the technological ecology of MetaSpore online reasoning and online microservices provided by DMetaSpore, the pre-training model is no longer mere offline dabbling. Instead, it can truly achieve end-to-end implementation from cutting-edge technology to industrial scenarios, fully releasing the dividends of the pre-training large model. In the future, DMetaSoul will continue to improve and optimize the MetaSpore technology ecosystem: More automated and wider access to HuggingFace community ecology. MetaSpore will soon release a common model rollout mechanism to make HuggingFace ecologically accessible and will later integrate preprocessing services into online services. Multi-mode retrieval offline algorithm optimization. For multimodal retrieval scenarios, MetaSpore will continuously iteratively optimize offline algorithm components, including text recall/sort model, graphic recall/sort model, etc., to improve the accuracy and efficiency of the retrieval algorithm. For related code and reference documentation in this article, please visit: https://github.com/meta-soul/MetaSpore/tree/main/demo/multimodal/online Some images source: https://github.com/openai/CLIP/raw/main/CLIP.png https://www.sbert.net/examples/training/sts/README.html

ML/AI and Digital Marketing

M28, studied Economics in school, have 5 years of experience in Digital Marketing, and have a good grasp of Python. More and more, I see that my full time job in Digital Advertising is becoming automated due to Machine Learning on platforms like Meta/Google. I'm concerned that in the long run I won't be very valuable. Advertising is already a mid-paying career as is. My thought is to learn about machine learning/AI for the first half of this year and then create a side project to showcase to future employers. My questions are: How should I learn about ML/AI? Is Andrew Ng's Coursera course a good place to start? I often feel that with courses I struggle to retain the information as I don't use it. Should I start a side project before or after completing a course? Also thought about creating a newsletter just so I can distill the learnings. 10 years from now, how valuable will knowing AI/ML be? Will the AI/ML systems get so advanced that human intervention is not needed and therefore isn't a skill to invest in? Should I instead invest in a creative skill set?

Advise Needed] Mechanical engineer trying to venture into ML

Hello fellow redditors, &#x200B; As the title suggests, I am a mechanical engineer with a masters in mechanical design from a top institute in India. Directly after my masters, I got a job but left it after exactly one year to pursue civil services. And that decision has left a 3 year void in my career sheet. During these three years, the most I have been in touch with tech/science was through random personal automations using python and digital notetaking systems or a few readings here and there. I don't know if they have anything to do with each other, but I am lazy (for repetitive work) and have an eye to optimize /automate my workflow. The later led to me learning python, a bit of git and css/html. With regard to my prgramming skills, I learn quickly and had good grades in all the computer science courses we had at the college (C++, DSA and Modelling-Simulation). I have also programmed in Matlab for basic usage in research and also in LAMDA for nanomechanics/molecular simulation. At my work, I had written a python code to automate the process of model setup for FE which reduced the human intervention from very menial routine work (hindi: gadha majdoori). As for my mechanical engineering skills, I am good with CAE softwares and can readily work with them. So first thing I am doing right now is applying in various positions in the same domain as I had worked 3 years ago. All this while, I got introduced to the world of Machine Learning, AI and Deep Learning. So, I wish to learn ML to slowly venture into that line. So yeah, my question here to the CS veterans is, how to start with the learning, from where, what can I expect from the field and how much time is necessary for be able to get a decent opportunity in that domain? Currently, I have started with Andrew Ng's course on Courcera: Course 1 of Deep Learning Specialisation. https://www.coursera.org/learn/neural-networks-deep-learning but it seems rather theoretical to me and without implementation it will be difficult for me to grasp (I feel). Also, I explored fast.ai course which follows top-down approach unlike Andrew. I haven't committed to it. Kindly guide. All kinds of opinon are welcome. PS. I am 28yo

6 principles to data architecture that facilitate innovation

My team and I have been re-building our company's data architecture. In the process of doing so, I got together six key principles to transforming data architectures and thought I would share them, as a strong data architecture is crucial for businesses looking to stay competitive in the digital landscape, as it improves decision-making, time to market, and data security. When executed with efficiency, a resilient data architecture unleashes unparalleled degrees of agility. Principle 1: Agility and flexibility To quickly adjust to market fluctuations, businesses must create adaptable data infrastructures that can effortlessly manage an ever-growing influx of data. To accomplish this objective, we recommend to our clients to implement Enterprise Service Bus, Enterprise Data Warehouse, and Master Data Management integrated together. &#x200B; I believe the best option is this: \- By centralizing communication, ESB reduces the time and effort required to integrate new systems; \- EDW consolidates data from different sources, resulting in a 50% reduction in software implementation time; \- Finally, MDM ensures consistency and accuracy across the organization, leading to better decision-making and streamlined operations. Implementing these solutions can lead to reduced software implementation time, better ROI, and more manageable data architecture. By fostering a culture of collaboration and adopting modern technologies and practices, businesses can prioritize agility and flexibility in their data architecture to increase the pace of innovation. Principle 2: Modularity and reusability Data architecture that fosters modularity and reusability is essential for accelerating innovation within an organization. By breaking data architecture components into smaller, more manageable pieces, businesses can enable different teams to leverage existing architecture components, reducing redundancy and improving overall efficiency. MDM can promote modularity and reusability by creating a central repository for critical business data. This prevents duplication and errors, improving efficiency and decision-making. MDM enables a single source of truth for data, accessible across multiple systems, which promotes integration and scalability. MDM also provides standardized data models, rules, and governance policies that reduce development time, increase quality, and ensure proper management throughout the data’s lifecycle. Another way to achieve modularity in data architecture is through the use of microservices and scripts for Extract, Transform, and Load (ETL) processes. Adopting a structured methodology and framework can ensure these components are well-organized, making it easier for teams to collaborate and maintain the system. Microservices can also contribute to modularity and reusability in data architecture. These small, independent components can be developed, deployed, and scaled independently of one another. By utilizing microservices, organizations can update or replace individual components without affecting the entire system, improving flexibility and adaptability. Principle 3: Data quality and consistency The efficiency of operations depends on data’s quality, so a meticulously crafted data architecture plays a pivotal role in preserving it, empowering enterprises to make well-informed decisions based on credible information. Here are some key factors to consider that will help your company ensure quality: \- Implementing Master Data Management (MDM) – this way, by consolidating, cleansing, and standardizing data from multiple sources, your IT department will be able to create a single, unified view of the most important data entities (customers, products, and suppliers); \- Assigning data stewardship responsibilities to a small team or an individual specialist; \- Considering implementing data validation, data lineage, and data quality metrics; \- By implementing MDM and adopting a minimal data stewardship approach, organizations can maintain high-quality data that drives innovation and growth. Principle 4: Data governance Data governance is a strategic framework that goes beyond ensuring data quality and consistency. It includes ensuring data security, privacy, accessibility, regulatory compliance, and lifecycle management. Here are some key aspects of data governance: \- Implementing robust measures and controls to protect sensitive data from unauthorized access, breaches, and theft. This is only possible through including encryption, access controls, and intrusion detection systems into your company’s IT architecture; \- Adhering to data privacy regulations and guidelines, such as the General Data Protection Regulation (GDPR) and the California Consumer Privacy Act (CCPA); \- Defining stringent conditions for who has access to specific data assets to maintain control over data and ensure its accessibility only for legitimate purposes. Managing the entire lifecycle of data, from creation and storage to archiving and disposal, including defining policies for data retention, archiving, and deletion in compliance with legal and regulatory requirements. To facilitate effective data governance, organizations can leverage various tools and technologies, such as: \- Data cataloging tools: Solutions like Collibra, Alation, or Informatica Enterprise Data Catalog help organizations discover, understand, and manage their data assets. \- Data lineage tools: Tools like Talend, IBM InfoSphere, or Apache Atlas help track data’s origin, transformation, and usage, providing insights into data quality issues and potential areas for improvement. \- Data quality tools: Solutions like Informatica Data Quality, Trifacta, or SAS Data Quality help organizations maintain high-quality data by identifying and correcting errors, inconsistencies, and inaccuracies. \- Data security and privacy tools: Tools like Varonis, BigID, or Spirion help protect sensitive data and ensure compliance with data privacy regulations. Principle 5: Cloud-first approach A cloud-first approach prioritizes cloud-based solutions over on-premises ones when it comes to data management. Cloud-based data management pros: \- Virtually limitless scalability, so that organizations can grow and adapt to changing data requirements without significant infrastructure investments; \- The pay-as-you-go model of cloud services reduces maintenance costs usually associated with the on-premise choice; \- Greater flexibility for deploying and integrating new technologies and services; \- Cloud can be accessed from anywhere, at any time, turning team collaboration and remote work into a breeze; \- Built-in backup and disaster recovery capabilities, ensuring data safety and minimizing downtime in case of emergencies. Cloud-based data management cons: \- Cloud-first approach raises many data security, privacy, and compliance concerns; \- Transferring large data volumes to and from cloud is often time-consuming and results in increased latency for certain apps; \- Relying on a single cloud provider makes it difficult to switch them or move back to the on-premises option without significant funds and effort. Challenges that organizations that choose a cloud-first approach face: \- Integrating cloud-based systems with on-premises ones can be complex and time-consuming; \- Ensuring data governance and compliance in a multi-cloud or hybrid environment is also another problem reported by my clients. How EDW, ESB, and MDM promote cloud-first approach: A cloud-based EDW centralizes data from multiple sources, enabling a unified view of the organization’s data and simplifying data integration across cloud and on-premises systems. An ESB facilitates communication between disparate cloud and on-premises systems, streamlining data integration and promoting a modular architecture. Cloud-based MDM solutions are used for maintaining data quality and consistency across multiple data sources and environments. Principle 6: Automation and artificial intelligence Incorporating automation tools and AI technologies into data architecture can optimize processes and decision-making. Key Applications: \- Data ingestion and integration: Automation simplifies data schema updates and identifies data quality issues, while AI-assisted development helps create tailored connectors, scripts, and microservices. \- Data quality management: Machine learning algorithms improve data quality and consistency by automatically detecting and correcting inconsistencies and duplicates. \- Predictive analytics: AI and machine learning models analyze historical data to predict trends, identify opportunities, and uncover hidden patterns for better-informed decisions. How No-Code Tools and AI-Assisted Development Work: Business users define data requirements and workflows using no-code tools, enabling AI models to understand their needs. AI models process the information, generating recommendations for connector creation, ETL scripts, and microservices. Developers use AI-generated suggestions to accelerate development and tailor solutions to business needs. By combining automation, AI technologies, and no-code tools, organizations can streamline data architecture processes and bridge the gap between business users and developers, ultimately accelerating innovation. I share more tips on building an agile data architectures in my blog.

Let’s Build Small AI Buzz, Offer ‘Claim Processing’ to Mid/Big Companies

Discover How AI Can Transform Businesses, Every Details Spelled Out. Full Article https://preview.redd.it/jp0vc5g6e86d1.png?width=1421&format=png&auto=webp&s=efa43e2a9b04b6996b00adac4e4947a3b21c7e63 Artificial Intelligence (AI) is rapidly reshaping business landscapes, promising unprecedented efficiency and accuracy across industries. In this article, we delve into how Aniket Insurance Inc. (Imaginary) leverages AI to revolutionize its claim processing operations, offering insights into the transformative power of AI in modern business environments. ➡️ What’s This Article About? \* The article explores how Aniket Insurance Inc. uses AI to transform its claim processing. \* It details the three main workflows: User claim submission, Admin + AI claim processing, and Executive + AI claim analysis. https://preview.redd.it/ql0ec20ae86d1.png?width=769&format=png&auto=webp&s=4b6889dd85f848194d6adfc92c9c699138eb1fe7 ➡️ Why Read This Article \* Readers can see practical ways AI boosts efficiency in business, using Aniket Insurance as an example. \* AI speeds up routine tasks, like data entry, freeing up humans for more strategic work. It shows how AI-driven data analysis can lead to smarter business decisions. ➡️Let’s Design: Aniket Insurance Inc. has implemented AI architecture that encompasses three pivotal workflows: User Claim Submission Flow, Admin + AI Claim Processing Flow, and Executive + AI Claim Analysis Flow. Powered by AI models and integrated with store, this architecture ensures seamless automation and optimization of the entire claim processing lifecycle. By leveraging AI technologies like machine learning models and data visualization tools, Aniket Insurance how business can enhance operational efficiency, and strategic decision-making capabilities. https://preview.redd.it/qgdmzs3ee86d1.png?width=733&format=png&auto=webp&s=445295beb52a56d826e5527859cf62879116ddb0 ➡️Closing Thoughts: Looking ahead, the prospects of AI adoption across various industries are incredibly exciting. Imagine manufacturing plants where AI optimizes production lines, predicts maintenance needs, and ensures quality control. Envision healthcare facilities where AI assists in diagnosis, treatment planning, and drug discovery. Picture retail operations where AI personalizes product recommendations, streamlines inventory management, and enhances customer service. The possibilities are endless, as AI’s capabilities in pattern recognition, predictive modeling, and automation can be leveraged to tackle complex challenges and uncover valuable insights in virtually any domain. https://preview.redd.it/w3hr913ge86d1.png?width=754&format=png&auto=webp&s=d839a7703f5b28314a3278c8d628ae5f05d3668f

Seeking Guidance to Transition from SRE to Quant Developer/HFT

Hey Reddit! Let me introduce myself: I’m a 2024 B.Tech (IT) graduate from a state-level college in India. Currently, I’m working as an SRE (Site Reliability Engineer) at one of the world’s largest custodian banks (not naming the company). I’ve been with the organization for about a year now, combining my internship and full-time role. During this time, I’ve developed a strong foundation in AI/ML and have primarily been working on projects to automate BAU (Business-As-Usual) activities using these technologies. Outside of work, I have a deep interest in trading and stock markets—something that runs in the family, as my father has been trading for over 40 years. My ultimate goal is to transition into the field of quantitative development or high-frequency trading (HFT) and work for top-tier firms like HRT, Optiver, or Tower Research. To make this dream a reality, I’ve started preparing in the following ways: Learning the basics of stock markets and financial instruments. Studying statistics and experimenting with different algorithms to analyze stocks (mainly on a fundamental level for now). Getting back to practicing DSA (Data Structures and Algorithms). I’ll admit I’m rusty here since I haven’t been consistent with it for a while. I’m aware that transitioning from SRE to Quant Developer/HFT is ambitious and might seem like a pipe dream, but it’s a challenge I’m willing to take on. I’d love to hear from people in the quant field or those who’ve made similar career transitions. What should I focus on? Any recommended resources, books, or courses? Are there any specific skill sets or certifications that could make me stand out? Any guidance, advice, or encouragement would mean a lot. Thank you!

How I Built A Simple ‘BPO’ Company, All AI Employees (All Local)

Disrupting the BPO Industry: My Journey Building a Fully Automated Company with AI Employees Full Article : https://medium.com/@learn-simplified/how-i-built-a-simple-bpo-company-all-ai-employees-all-local-631e48fa908a &#x200B; https://preview.redd.it/htjo1mancl2d1.png?width=1586&format=png&auto=webp&s=7e77f4c66e5ca55a8b0ea6969c43a458503ad921 ● What Are We Doing Today? We are building a BPO (Business Process Outsourcing) call center for an imaginary electric company called "Aniket Very General Electric Company". We will create different departments staffed by AI agents who can chat (and eventually speak in next part) with customers to answer questions, handle complaints, or provide services. ● Why Should You Read This Article? Learning how to build AI agents that can do tasks in real setting, co ordinate w/ human, AI, providing technical support will be a highly valuable skill. ● How Are We Going to Build Our All AI Employees Company? ○ We will explain what BPO and call centers are. ○ Our AI company will have departments like Customer Service, Tech Support, Billing & Payments, Outage Management, and Onboarding Customers. ○ We will use Docker containers to run the Dify AI platform as the base. ○ The AI agents will use the LLaMA-3 language model from Meta AI. ○ We may use Groq's AI accelerator chip to make LLaMA-3 faster. ○ Each department will have a knowledge base of text files that the AI agents can reference. ● Let's Get Cooking! This section provides setup instructions for installing Docker, Ollama (for running LLaMA-3), and the Dify AI platform. It also outlines the different AI agents we will create for departments like Reception, Customer Service, Billing, Tech Support, etc. ● Let's Design our Organization ○ We explain how each department's AI agents will have their own knowledge base, like an employee handbook. ○ The knowledge bases will contain policies, procedures, and other key information. ○ The AI agents can quickly reference this information to provide accurate and knowledgeable responses. ● Let's Meet Our AI Employees ○ We chose the LLaMA-3 70B model as the base for all AI agents across departments. ○ We give the AI agents customized prompts to define their personalities and roles. ○ The knowledge bases act as training materials tailored to each department. ○ In the future, AI agents could have additional tools like ticket systems and integrations. ● Let's Run Our BPO Organization Now that the AI workforce and knowledge bases are ready, we can open our BPO company and have the AI agents start handling customer inquiries across different departments like billing, tech support, outages, and new connections. ● Debugging This section highlights the importance of debugging, showing traces of how the language model understands customer queries and retrieves relevant context from knowledge bases to provide good responses. ● Future Work ○ Scale up to handle more customers using cloud services or distributed computing. ○ Move AI agents and knowledge bases to the cloud for accessibility and maintenance. ○ Fine-tune language models for better performance in each department. ○ Use scalable vector databases for faster knowledge retrieval. ○ Enable voice interfaces and computer vision for more natural interactions. ○ Implement continuous learning so AI agents can expand their knowledge over time. The article demonstrates the potential of building an actual AI-powered company and raises thought-provoking questions about the role of humans, ethics, and using AI to create a better world. &#x200B;

I’m building 30 AI-powered businesses in 30 days with no experience. Here’s why.

Hey everyone! For the past 15 years, I worked in real estate development and sales, but I recently decided to make a career pivot into AI and automation.  I am starting from scratch with absolutely no experience in the space. But instead of just learning about AI, in March I'll be embarking on a challenge to build a business a day for 30 days using AI automation. Each one will be a fully functional product that could generate passive income. My goal? Learn by doing Document the entire process in public Share insights on what works (and what flops) I don't have any followers yet, but I just posted my first thread about my journey here:  https://x.com/RealEstateToAI/status/1886806315260953079 Would love to hear your thoughts: What resources did you find most valuable when starting with no experience in the space? What AI tools do you think are most valuable for automation?

Randomly asked ChatGPT and Claude for a 4 year roadmap for an ML Engineer

Title, Is it actually a good plan ?? If no, why not ?? \\🚀 4-Year Roadmap to Becoming a High-Earning ML Engineer & Entrepreneur\\ \\(With Smartwork & Realistic 60-70% Execution Feasibility)\\ \\🟢 Year 1: Strong Foundation & Initial Projects (0-12 Months)\\ 🎯 \\Goal: Master Python & ML Fundamentals\\ \\🔹 1-4 Months (Python & Math Strengthening)\\ ✅ Python Mastery \- Daily LeetCode Easy problems (minimum 2) \- Build automation projects \- NumPy & Pandas mastery \- DSA fundamentals ✅ Mathematics Foundation \- Linear Algebra basics \- Statistics fundamentals \- Basic calculus concepts ✅ First Mini-Hackathon Participation \- Join beginner-friendly hackathons \- Focus on Python-based challenges \- Team up with other beginners 💡 \\Smart Move:\\ \- Join Discord/Slack hackathon communities \- Practice collaborative coding \- Build network with fellow participants \\🔹 5-8 Months (ML Foundations)\\ ✅ Machine Learning Basics \- Supervised Learning \- Model evaluation \- Feature engineering \- scikit-learn projects ✅ Participate in 2-3 ML Hackathons \- Kaggle Getting Started competitions \- Local ML hackathons \- University hackathons ✅ Start LinkedIn & GitHub Portfolio 💡 \\Smart Move:\\ \- Document hackathon experiences \- Share learnings on LinkedIn \- Focus on completion over winning \\🔹 9-12 Months (Deep Learning Introduction)\\ ✅ Basic Deep Learning \- Neural network fundamentals \- PyTorch basics \- Computer vision tasks \- Basic NLP ✅ Advanced Hackathon Participation \- AI/ML specific hackathons \- Team lead in 1-2 hackathons \- Start mentoring beginners \\🔵 Year 1 Expected Outcome (60-70% Execution)\\ ✔ \\Strong Python & ML foundations\\ ✔ \\5-6 hackathon participations\\ ✔ \\Active GitHub (100+ commits)\\ ✔ \\Growing LinkedIn (300+ connections)\\ 💰 \\Earning Expectation → ₹8K-₹20K per month (Projects/Internship)\\ \\🟢 Year 2: Professional Growth & Specialization (12-24 Months)\\ 🎯 \\Goal: Build Professional Experience & Recognition\\ \\🔹 1-6 Months (Technical Depth)\\ ✅ Advanced ML Topics \- Deep Learning architectures \- Computer Vision OR NLP \- MLOps basics (Docker, FastAPI) \- Cloud fundamentals (AWS/GCP) ✅ Hackathon Achievements \- Win minor prizes in 2-3 hackathons \- Lead teams in major hackathons \- Network with sponsors ✅ Start Technical Blogging 💡 \\Smart Move:\\ \- Focus on hackathon projects that align with career goals \- Build relationships with companies at hackathons \- Create detailed project documentation \\🔹 7-12 Months (Professional Experience)\\ ✅ Secure ML Role/Internship ✅ Advanced Project Building ✅ Open Source Contributions ✅ Organize Small Hackathons 💡 \\Smart Move:\\ \- Use hackathon network for job referrals \- Convert hackathon projects into full products \- Build mentor reputation \\🔵 Year 2 Expected Outcome (60-70% Execution)\\ ✔ \\Professional ML experience\\ ✔ \\10+ hackathon participations\\ ✔ \\1-2 hackathon wins\\ ✔ \\Strong industry network\\ 💰 \\Earning Expectation → ₹40K-₹70K per month (Job/Freelancing)\\ \\🟢 Year 3: Scaling & Business Foundation (24-36 Months)\\ 🎯 \\Goal: Establish Multiple Income Streams\\ \\🔹 1-4 Months (Expertise Building)\\ ✅ Choose Specialization \- MLOps \- Computer Vision \- NLP/LLMs \- Generative AI ✅ Advanced Competitions \- International hackathons \- High-prize competitions \- Corporate ML challenges ✅ Start Consulting Services 💡 \\Smart Move:\\ \- Use hackathon wins for marketing \- Build service packages around expertise \- Network with corporate sponsors \\🔹 5-8 Months (Business Development)\\ ✅ Scale Services ✅ Build Client Network ✅ Create Training Programs ✅ Hackathon Mentorship Program 💡 \\Smart Move:\\ \- Convert hackathon projects to products \- Use event networks for client acquisition \- Build authority through speaking \\🔹 9-12 Months (Growth & Innovation)\\ ✅ Product Development ✅ Team Building ✅ Innovation Focus ✅ Hackathon Organization \\🔵 Year 3 Expected Outcome (60-70% Execution)\\ ✔ \\Established ML business/career\\ ✔ \\Known in hackathon community\\ ✔ \\Multiple income streams\\ ✔ \\Strong industry presence\\ 💰 \\Earning Expectation → ₹1L-₹2L per month (Multiple Streams)\\ \\🟢 Year 4: Scale & Leadership (36-48 Months)\\ 🎯 \\Goal: Build AI Company & Achieve Financial Freedom\\ \\🔹 1-4 Months (Business Scaling)\\ ✅ Company Formation \- AI consulting firm \- Product development \- Training programs ✅ Hackathon Innovation \- Launch own hackathon series \- Corporate partnerships \- Prize sponsorships ✅ Team Expansion 💡 \\Smart Move:\\ \- Use hackathon network for hiring \- Create unique event formats \- Build corporate relationships \\🔹 5-8 Months (Market Leadership)\\ ✅ Product Launch ✅ Service Expansion ✅ International Presence ✅ Innovation Hub Creation 💡 \\Smart Move:\\ \- Create hackathon-to-hiring pipeline \- Build educational programs \- Establish thought leadership \\🔹 9-12 Months (Empire Building)\\ ✅ Multiple Revenue Streams \- AI products \- Consulting services \- Educational programs \- Event organization \- Investment returns ✅ Industry Leadership \- Conference speaking \- Published content \- Community leadership \\🔵 Year 4 Expected Outcome (60-70% Execution)\\ ✔ \\Established AI company\\ ✔ \\Major hackathon organizer\\ ✔ \\Multiple product lines\\ ✔ \\Industry authority status\\ 💰 \\Earning Expectation → ₹3L-₹5L+ per month (Business Income)\\ \\📊 FINAL RATING\\ ✅ \\Comprehensive growth plan\\ ✅ \\Strong community focus\\ ✅ \\Multiple income pathways\\ 💡 \\If 100% Execution → 8.5/10 Feasibility\\ 💡 \\If 50% Execution → 6/10 Feasibility\\ 🔥 \\Conclusion: A balanced path to ML mastery and entrepreneurship, built through consistent growth and community engagement!\\ 🚀 \\Key Success Factors:\\ Regular hackathon participation Strong community involvement Consistent skill development Strategic network building Focus on both technical and business growth

Best way to pivot into AI/ML as a non-dev engineer?

I’m a biomedical engineer with a Masters, working in the Medical device industry for over a decade now. I have an interest in learning AI/ML to pivot my career. I know some basic python but I’m not a developer by any means. Most of my career is in the product/design quality engineering and regulatory compliance side of the business. Currently my role is in Failure Analysis for software medical devices. I’ve considered taking the Google Cloud ML Engineer related courses to get the certification, but I’m not sure if it will actually help pivot me into this field. Perhaps my focus should be more on the MLOps side of things as it may be an easier leap? I want to make a jump due a higher salary ceiling for AI/ML roles and I also have a genuine interest in automation. Overall just a bit confused and wanted to know what are the best options to pursue, and path to follow. Any guidance from folks who pivoted from other non-dev engineering would be super helpful. Thanks!

Is fine-tunig dead?

Hello, I am leading a business creation project in AI in France (Europe more broadly). To concretize and structure this project, my partners recommend me to collect feedback from professionals in the sector, and it is in this context that I am asking for your help. Lately, I have learned a lot about data annotation and I have seen a division of thoughts and I admit to being a little lost. Several questions come to mind, in particular is fine-tunig dead? RAG is it really better? Will we see few-shot learning gain momentum or will conventional learning with millions of data continue? And for whom? Too many questions, which I have grouped together in a form, if you would like to help me see more clearly the data needs of the market, I suggest you answer this short form (4 minutes): https://forms.gle/ixyHnwXGyKSJsBof6. This form is more for businesses, but if you have a good vision of the sector, feel free to respond. Your answers will remain confidential and anonymous. No personal or sensitive data is requested. This does not involve a monetary transfer. Thank you for your valuable help. You can also express your thoughts in response to this post. If you have any questions or would like to know more about this initiative, I would be happy to discuss it. Subnotik

Best way to pivot into AI/ML as a non-dev engineer?

I’m a biomedical engineer with a Masters, working in the Medical device industry for over a decade now. I have an interest in learning AI/ML to pivot my career. I know some basic python but I’m not a developer by any means. Most of my career is in the product/design quality engineering and regulatory compliance side of the business. Currently my role is in Failure Analysis for software medical devices. I’ve considered taking the Google Cloud ML Engineer related courses to get the certification, but I’m not sure if it will actually help pivot me into this field. Perhaps my focus should be more on the MLOps side of things as it may be an easier leap? I want to make a jump due a higher salary ceiling for AI/ML roles and I also have a genuine interest in automation. Overall just a bit confused and wanted to know what are the best options to pursue, and path to follow. Any guidance from folks who pivoted from other non-dev engineering would be super helpful. Thanks!

How difficult would it be to make my own AI porn generator as a complete beginner in ml

https://www.reddit.com/r/learnmachinelearning/s/5D6ihR10q9 Inspired by the post above ,I want to be able to do this,I know python but that's about it. Edit:This is for a business idea

I’m AI/ML product manager. What I would have done differently on Day 1 if I knew what I know today

I’m a software engineer and product manager, and I’ve working with and studying machine learning models for several years. But nothing has taught me more than applying ML in real-world projects. Here are some of top product management lessons I learned from applying ML: Work backwards: In essence, creating ML products and features is no different than other products. Don’t jump into Jupyter notebooks and data analysis before you talk to the key stakeholders. Establish deployment goals (how ML will affect your operations), prediction goals (what exactly the model should predict), and evaluation metrics (metrics that matter and required level of accuracy) before gathering data and exploring models.  Bridge the tech/business gap in your organization: Business professionals don’t know enough about the intricacies of machine learning, and ML professionals don’t know about the practical needs of businesses. Educate your business team on the basics of ML and create joint teams of data scientists and business analysts to define and measure goals and progress of ML projects. ML projects are more likely to fail when business and data science teams work in silos. Adjust your priorities at different stages of the project: In the early stages of your ML project, aim for speed. Choose the solution that validates/rejects your hypotheses the fastest, whether it’s an API, a pre-trained model, or even a non-ML solution (always consider non-ML solutions). In the more advanced stages of the project, look for ways to optimize your solution (increase accuracy and speed, reduce costs, increase flexibility). There is a lot more to share, but these are some of the top experiences that would have made my life a lot easier if I had known them before diving into applied ML.  What is your experience?

How I landed an internship in AI

For motivational purposes only! I see a lot of posts on here from people without “traditional” machine learning, data science, etc.. backgrounds asking how they can break into the field, so I wanted to share my experience. EDIT Learning Resources and Side Project Ideas * My background: I graduated from a decent undergraduate school with a degree in Political Science several years ago. Following school I worked in both a client services role at a market research company and an account management role at a pretty notable fintech start-up. Both of these roles exposed me to ML, AI and more sophisticated software concepts in general, and I didn’t really care for the sales side of things, so I decided to make an attempt at switching careers into something more technical. While working full time I began taking night classes at a local community college, starting with pre calculus all the way up to Calc 2 and eventually more advanced classes like linear algebra and applied probability. I also took some programming courses including DSA. I took these classes for about two years while working, and on the side had been working through various ML books and videos on YouTube. What worked the best for me was Hands-on Machine Learning with Scikit Learn, Keara’s and Tensorflow. I eventually had enough credits where I was able to begin applying to MS in Data Science programs and was fortunate enough to get accepted into one and also get a position in their Robotics Lab doing Computer Vision work. When it came time to apply for internships, it was a BLOODBATH. I must have applied to over 100 roles with my only responses being video interviews and OA’s. Finally I got an interview for an AI Model Validation internship with a large insurance company and after completing the interviews was told I performed well but they were still interviewing several candidates. I ended up getting the offer and accepting the role where I’ll be working on a Computer Vision model and some LLM related tasks this summer and could not be more fortunate / excited. A couple things stood out to them during the interview process. 1, the fact that I was working and taking night classes with the intent to break into the field. It showed a genuine passion as opposed to someone who watched a YouTube video and claims they are now an expert. 2, side projects. I not only had several projects, but I had some that were relevant to the work I’d be doing this summer from the computer vision standpoint. 3, business sense. I emphasized during my interviews how working in a business role prior to beginning my masters would give me a leg up as intern because I would be able to apply the work of a data scientist to solving actual business challenges. For those of you trying to break into the field, keep pushing, keep building, and focus on what makes you unique and able to help a company! Please feel free to contact me if you would like any tips I can share, examples of projects, or anything that would be helpful to your journey.

I started with 0 AI knowledge on the 2nd of Jan 2024 and blogged and studied it for 365. Here is a summary.

FULL BLOG POST AND MORE INFO IN THE FIRST COMMENT :) Edit in title: 365 days\* (and spelling) Coming from a background in accounting and data analysis, my familiarity with AI was minimal. Prior to this, my understanding was limited to linear regression, R-squared, the power rule in differential calculus, and working experience using Python and SQL for data manipulation. I studied free online lectures, courses, read books. \Time Spent on Theory vs Practice\ At the end it turns out I spent almost the same amount of time on theory and practice. While reviewing my year, I found that after learning something from a course/lecture in one of the next days I immediately applied it - either through exercises, making a Kaggle notebook or by working on a project. \2024 Learning Journey Topic Breakdown\ One thing I learned is that \fundamentals\ matter. I discovered that anyone can make a model, but it's important to make models that add business value. In addition, in order to properly understand the inner-workings of models I wanted to do a proper coverage of stats & probability, and the math behind AI. I also delved into 'traditional' ML (linear models, trees), and also deep learning (NLP, CV, Speech, Graphs) which was great. It's important to note that I didn't start with stats & math, I was guiding myself and I started with traditional and some GenAI but soon after I started to ask a lot of 'why's as to why things work and this led me to study more about stats&math. Soon I also realised \Data is King\ so I delved into data engineering and all the practices and ideas it covers. In addition to Data Eng, I got interested in MLOps. I wanted to know what happens with models after we evaluate them on a test set - well it turns out there is a whole field behind it, and I was immediately hooked. Making a model is not just taking data from Kaggle and doing train/test eval, we need to start with a business case, present a proper case to add business value and then it is a whole lifecycle of development, testing, maintenance and monitoring. \Wordcloud\ After removing some of the generically repeated words, I created this work cloud from the most used works in my 365 blog posts. The top words being:- model and data - not surprising as they go hand in hand- value - as models need to deliver value- feature (engineering) - a crucial step in model development- system - this is mostly because of my interest in data engineering and MLOps I hope you find my summary and blog interesting. https://preview.redd.it/pxohznpy4dae1.png?width=2134&format=png&auto=webp&s=03c16bb3535d75d1f009b44ee5164cc3e6483ac4 https://preview.redd.it/0y47rrpy4dae1.png?width=1040&format=png&auto=webp&s=f1fdf7764c7151ff0a05ae92777c5bb7d52f4359 https://preview.redd.it/e59inppy4dae1.png?width=1566&format=png&auto=webp&s=2566033777a90410277350947617d3ce8406be15

AI Courses for Business Leaders

I’m been spending a last few months learning the fundamentals of AI through blog post, podcast and did online short course on intro to AI from IBM and Coursera. And looking to take the “next step” either through a certification program (I don’t care about the cert - but more so learning opportunity) offered through MIT, Penn, etc…they seem like a money grab and not confident I will get what I am looking for through them. Are there better options? Willing to spend money, open to learning online/hybrid through a structured curriculum or patch-work solution online —- just need insight on a path forward. I’m not looking to pivot, but rather learn about the technology, seek opportunities to incorporate elements of it into our organization - and for also, I’m genuinely interested in its potential - from an application/deployment/business perspective. I’m 40yrs, senior leader focusing on innovation and entrepreneurship in emerging economies - pretty tech savvy (though not from a CS background) and looking for a new learning opportunity to stay ahead of the curve and leverage it to our organization’s mission. Many thanks in advance!

MarkDrop

I’m excited to share my Python package, Markdrop, which has hit 5.01k+ downloads in just a month, so updated it just now! 🚀 It’s a powerful tool for converting PDF documents into structured formats like Markdown (.md) and HTML (.html) while automatically processing images and tables into descriptions for downstream use. Here's what Markdrop does: Key Features: PDF to Markdown/HTML Conversion: Converts PDFs into clean, structured Markdown files (.md) or HTML outputs, preserving the content layout. AI-Powered Descriptions: Replaces tables and images with descriptive summaries generated by LLM, making the content fully textual and easy to analyze. Earlier I added support of 6 different LLM Clients, but to improve the inference time, now this supports only GEMINI\API\KEY and OPENAI\API\KEY. Downloadable Tables: Can add accurate download buttons in HTML for tables, allowing users to download them as Excel files. Seamless Table and Image Handling: Extracts tables and images, generating detailed summaries for each, which are then embedded into the final Markdown document. At the end, one can have a .md file that contains only textual data, including the AI-generated summaries of tables, images, graphs, etc. This results in a highly portable format that can be used directly for several downstream tasks, such as: Can be directly integrated into a RAG pipeline for enhanced content understanding and querying on documents containg useful images and tabular data. Ideal for automated content summarization and report generation. Facilitates extracting key data points from tables and images for further analysis. The .md files can serve as input for machine learning tasks or data-driven projects. Ideal for data extraction, simplifying the task of gathering key data from tables and images. The downloadable table feature is perfect for analysts, reducing the manual task of copying tables into Excel. Markdrop streamlines workflows for document processing, saving time and enhancing productivity. You can easily install it via: pip install markdrop There’s also a Colab demo available to try it out directly: Open in Colab. Github Repo If you've used Markdrop or plan to, I’d love to hear your feedback! Share your experience, any improvements, or how it helped in your workflow. Check it out on PyPI and let me know your thoughts!

Backend dev wants to learn ML

Hello ML Experts, I am staff engineer, working in a product based organization, handling the backend services. I see myself becoming Solution Architect and then Enterprise Architect one day. With the AI and ML trending now a days, So i feel ML should be an additional skill that i should acquire which can help me leading and architecting providing solutions to the problems more efficiently, I think however it might not replace the traditional SWEs working on backend APIs completely, but ML will be just an additional diamention similar to the knowledge of Cloud services and DevOps. So i would like to acquire ML knowledge, I dont have any plans to be an expert at it right now, nor i want to become a full time data scientist or ML engineer as of today. But who knows i might diverge, but thats not the plan currently. I did some quick promting with ChatGPT and was able to comeup with below learning path for me. So i would appreciate if some of you ML experts can take a look at below learning path and provide your suggestions 📌 PHASE 1: Core AI/ML & Python for AI (3-4 Months) Goal: Build a solid foundation in AI/ML with Python, focusing on practical applications. 1️⃣ Python for AI/ML (2-3 Weeks) Course: [Python for Data Science and Machine Learning Bootcamp]() (Udemy) Topics: Python, Pandas, NumPy, Matplotlib, Scikit-learn basics 2️⃣ Machine Learning Fundamentals (4-6 Weeks) Course: Machine Learning Specialization by Andrew Ng (C0ursera) Topics: Linear & logistic regression, decision trees, SVMs, overfitting, feature engineering Project: Build an ML model using Scikit-learn (e.g., predicting house prices) 3️⃣ Deep Learning & AI Basics (4-6 Weeks) Course: Deep Learning Specialization by Andrew Ng (C0ursera) Topics: Neural networks, CNNs, RNNs, transformers, generative AI (GPT, Stable Diffusion) Project: Train an image classifier using TensorFlow/Keras 📌 PHASE 2: AI/ML for Enterprise & Cloud Applications (3-4 Months) Goal: Learn how AI is integrated into cloud applications & enterprise solutions. 4️⃣ AI/ML Deployment & MLOps (4 Weeks) Course: MLOps Specialization by Andrew Ng (C0ursera) Topics: Model deployment, monitoring, CI/CD for ML, MLflow, TensorFlow Serving Project: Deploy an ML model as an API using FastAPI & Docker 5️⃣ AI/ML in Cloud (Azure, AWS, OpenAI APIs) (4-6 Weeks) Azure AI Services: Course: Microsoft AI Fundamentals (C0ursera) Topics: Azure ML, Azure OpenAI API, Cognitive Services AWS AI Services: Course: [AWS Certified Machine Learning – Specialty]() (Udemy) Topics: AWS Sagemaker, AI workflows, AutoML 📌 PHASE 3: AI Applications in Software Development & Future Trends (Ongoing Learning) Goal: Explore AI-powered tools & future-ready AI applications. 6️⃣ Generative AI & LLMs (ChatGPT, GPT-4, LangChain, RAG, Vector DBs) (4 Weeks) Course: [ChatGPT Prompt Engineering for Developers]() (DeepLearning.AI) Topics: LangChain, fine-tuning, RAG (Retrieval-Augmented Generation) Project: Build an LLM-based chatbot with Pinecone + OpenAI API 7️⃣ AI-Powered Search & Recommendations (Semantic Search, Personalization) (4 Weeks) Course: [Building Recommendation Systems with Python]() (Udemy) Topics: Collaborative filtering, knowledge graphs, AI search 8️⃣ AI-Driven Software Development (Copilot, AI Code Generation, Security) (Ongoing) Course: AI-Powered Software Engineering (C0ursera) Topics: AI code completion, AI-powered security scanning 🚀 Final Step: Hands-on Projects & Portfolio Once comfortable, work on real-world AI projects: AI-powered document processing (OCR + LLM) AI-enhanced search (Vector Databases) Automated ML pipelines with MLOps Enterprise AI Chatbot using LLMs ⏳ Suggested Timeline 📅 6-9 Months Total (10-12 hours/week) 1️⃣ Core ML & Python (3-4 months) 2️⃣ Enterprise AI/ML & Cloud (3-4 months) 3️⃣ AI Future Trends & Applications (Ongoing) Would you like a customized plan with weekly breakdowns? 🚀

I’m building 30 AI-powered businesses in 30 days with no experience. Here’s why.

Hey everyone! For the past 15 years, I worked in real estate development and sales, but I recently decided to make a career pivot into AI and automation.  I am starting from scratch with absolutely no experience in the space. But instead of just learning about AI, in March I'll be embarking on a challenge to build a business a day for 30 days using AI automation. Each one will be a fully functional product that could generate passive income. My goal? Learn by doing Document the entire process in public Share insights on what works (and what flops) I don't have any followers yet, but I just posted my first thread about my journey here:  https://x.com/RealEstateToAI/status/1886806315260953079 Would love to hear your thoughts: What resources did you find most valuable when starting with no experience in the space? What AI tools do you think are most valuable for automation?

Why isn't there automated AI data cleaning software already?

I've been getting into machine learning and data science, and I keep wondering: why isn't there more automated AI data cleaning software? I know there are some tools out there, but it feels like we’re missing a fully automated, easy-to-use solution. Data cleaning is such a crucial part of any ML project, so it seems like this should be a no-brainer.

Why no code tools for building ai models failed?

Business folks have tasks where neural networks could help but they don’t know Python or deep learning, right? Meanwhile ML engineers know AI models but often don’t have an actual problem to solve. So the first group hires the second. Same thing happened with websites a while ago—at first you had to code everything then came drag-and-drop editors, no-code tools, and now even this "vibe coding" stuff. It’s not the most flexible or maintainable, but it works for a lot of people who just need to get something done without spending months learning to code. So why isn’t the same thing happening with building AI models? Like if I run a business I could save a ton of money by automating manual tasks with models trained on my own data. But I have zero clue what Jupyter Notebook or Keras are, and honestly, I don’t want to know. So I have to hire an ML engineer just to get it done because there’s no viable no-code solution for this.

Building a No-Code AI Customer Service Tool While Working 9-5 | All real - No BS

I want to share my journey of building Chaterimo, my first revenue-generating side project that I've been working on for the past 1.5 years alongside my day job. What started as a solution to make AI chatbots more accessible has grown to over 300 signups, 30 paying customers, and 50,000+ customer queries handled. The Problem I Wanted to Solve: It started with my father's business struggling with customer service - hiring staff was expensive and they would eventually leave, creating a constant cycle of training new people. I decided to help by building a livechat chatbot powered by AI to handle customer queries. The first version was basic (running on ChatGPT-3 with 4k tokens), but it worked! Seeing its success at my father's business, I realized this could help many other businesses too. As I kept improving it and adding features, I expanded to focus on e-commerce stores facing similar challenges. What Makes Chaterimo Different: True no-code setup: Install and run in seconds Choice of AI Models: ChatGPT by default, with options for Claude and the latest Gemini Flexible API Integration: Bring your own API keys for cheaper, unlimited messaging Smart Context Understanding: Can search Google or scan the current webpage to provide relevant answers Lead Generation: Capture and manage potential customer information Rich Integrations: Works with Shopify, Facebook Messenger, and Make for automation Customizable Bot Personality: Edit your chatbot's role and behavior through system prompts The Journey: This is my first side project that's actually generating revenue ($500+ MRR), unlike my previous "just for fun" projects. The past 1.5 years have been a learning experience, balancing development with a full-time job. What started as a simple idea has evolved based on real user feedback and needs. Current Metrics: 300+ total signups 30 paying customers 50,000+ customer queries successfully handled by AI $500+ monthly recurring revenue All while maintaining a 9-5 job Some Things I've Learned: Focus on making things simpler, not adding more features Listen to users - they'll tell you what they really need Flexibility matters - letting users use their own API keys was a game-changer Building something you believe in makes all the difference I'm still actively improving Chaterimo based on feedback. If you're running a website or e-commerce store and want to try it out, I'd love to hear your thoughts. What's Next: I'm focused on making the onboarding even smoother and adding more customization options while keeping the core simplicity that makes Chaterimo work. Would love to hear your thoughts or answer any questions! Has anyone else built successful side projects while working full-time? What were your biggest learnings?

How I got 1000 users on day one.

This might sound like a small number, depending on who you ask, but you know it’s a start. I’ll just share my learnings so far. Introduction: The product is simple: you type what you want to build, like, let's say, a SaaS idea, and it generates the code using a framework of your choice (like NextJS). Currently, it only generates front-end code. The marketing strategy was mainly focused on social media. My social media stats are as follows: I have a whopping 14 followers on Twitter, and 10 of them are bot accounts, and on LinkedIn, it’s about 400 or so. Launching on LinkedIn: LinkedIn is unique in two different ways: The algorithm is friendly to the little guy. Your network (the people) aren’t always friendly to the little guy. Let me elaborate. This is something I learned today, actually. When I posted for the first time and asked about three of my friends to repost it, within the first hour there were about 200 views, and the click-through rate was around 40%. This was really good, given that it was in the morning. I don’t know the exact factors, but I did have a video in my post, and those three reposts probably amplified it. However, people don’t seem to like or comment on it as much as you would think. Most of my connections are CS students because I am a recent grad, so it seems like most people can relate to this product, but none of them would even put a comment or a like. At the same time, I see people liking posts from big brands like OpenAI, Microsoft, etc. I am really confused, to be honest. However, throughout the day, the view count was going up, and people were coming. Launching on Twitter: Twitter didn’t really work for me at all. I think you need a decent audience. But there are tweets like “What startup are you working on?” type questions, and from that, I find you get a couple of views on your profile. Even though Twitter didn’t really help with the views, one guy tweeted, “Keep posting on Twitter and one day this might become something like Notion.” That really made my day, to be honest. Launching on Discord: This worked really well, to be honest, especially given that I was in a lot of Discord servers where there are software devs. If you use the right language that resonates with them, it’s a home run. Not much to say, but don’t use marketing lingo; people don’t like it there. Instagram and TikTok didn’t really work. Mainly, I think my video didn’t really resonate much. Finally, Facebook Launch: The Facebook reels didn’t really do the trick. Then I posted in a bunch of groups, and still, it didn’t really do anything. But then I sent cold DMs on Facebook, and that had a pretty high open rate because I sent them to people who I saw commented on posts related to what my product was solving. Obviously, after a while, Facebook blocks the ability to send DMs. That’s all for now. Thanks I’ll post my promo video in the comment section just so that you know the video and why it might have resonated with some platforms. Also this is the first time I made a video and I’m actually proud of making that more than the product itself. To summarize, for this idea LinkedIn worked really well, because of the algorithm not the ppl commenting and liking which is what I thought should be the way. Followed by Discord groups and Facebook DMs. The video I made seemed to resonate really well with the LinkedIn audience (the engagement was around 60%) despite falling in TikTok and other video sharing platforms.

Just hit $6k MRR, ask me anything

Hey everyone! After months (or years) of late nights, countless iterations, and endless learning, my side hustle just hit $6K MRR. It feels surreal to finally hit this milestone, and I wanted to share it with the community that’s been a constant source of inspiration and motivation. I’d love to pay it forward, answer questions, and chat with anyone on a similar journey! Whether you’re just starting out, scaling, or stuck in the grind, ask me anything about: What worked and what didn’t during the early stages How I managed time and stress with a full-time job Building a customer base and retention strategies Tools, tech stack, or marketing strategies that got me here How I’m planning to scale further from here Feel free to ask about the challenges too—because there have been many! 😂 Thanks to everyone who’s been part of the community here—it’s helped me push through. Let’s chat and grow together! 🚀 My app: https://dietapp.ai https://preview.redd.it/0d3mu80fd5xd1.png?width=972&format=png&auto=webp&s=50139d47258bc5910ea51a12d0bff2335d0e9909

How me and my team made 15+ apps and not made a single sale in 2023

Hey, my name is Michael, I am in Auckland NZ. This year was the official beginning of my adult life. I graduated from university and started a full-time job. I’ve also really dug into indiehacking/bootstrapping and started 15 projects (and it will be at least 17 before the year ends). I think I’ve learned a lot but I consciously repeated mistakes. Upto (Nov) Discord Statuses + Your Location + Facebook Poke https://preview.redd.it/4nqt7tp2tf5c1.png?width=572&format=png&auto=webp&s=b0223484bc54b45b5c65e0b1afd0dc52f9c02ad1 This was the end of uni, I often messaged (and got messaged) requests of status and location to (and from my) friends. I thought, what if we make a social app that’s super basic and all it does is show you where your friends are? To differentiate from snap maps and others we wanted something with more privacy where you select the location. However, never finished the codebase or launched it. This is because I slowly started to realize that B2C (especially social networks) are way too hard to make into an actual business and the story with Fistbump would repeat itself. However, this decision not to launch it almost launched a curse on our team. From that point, we permitted ourselves to abandon projects even before launching. Lessons: Don’t do social networks if your goal is 10k MRR ASAP. If you build something to 90% competition ship it or you will think it’s okay to abandon projects Insight Bites (Nov) Youtube Summarizer Extension &#x200B; https://preview.redd.it/h6drqej4tf5c1.jpg?width=800&format=pjpg&auto=webp&s=0f211456c390ac06f4fcb54aa51f9d50b0826658 Right after Upto, we started ideating and conveniently the biggest revolution in the recent history of tech was released → GPT. We instantly began ideating. The first problem we chose to use AI for is to summarize YouTube videos. Comical. Nevertheless, I am convinced we have had the best UX because you could right-click on a video to get a slideshow of insights instead of how everyone else did it. We dropped it because there was too much competition and unit economics didn’t work out (and it was a B2C). PodPigeon (Dec) Podcast → Tweet Threads https://preview.redd.it/0ukge245tf5c1.png?width=2498&format=png&auto=webp&s=23303e1cab330578a3d25cd688fa67aa3b97fb60 Then we thought, to make unit economics work we need to make this worthwhile for podcasters. This is when I got into Twitter and started seeing people summarize podcasts. Then I thought, what if we make something that converts a podcast into tweets? This was probably one of the most important projects because it connected me with Jason and Jonaed, both of whom I regularly stay in contact with and are my go-to experts on ideas related to content creation. Jonaed was even willing to buy Podpigeon and was using it on his own time. However, the unit economics still didn’t work out (and we got excited about other things). Furthermore, we got scared of the competition because I found 1 - 2 other people who did similar things poorly. This was probably the biggest mistake we’ve made. Very similar projects made 10k MRR and more, launching later than we did. We didn’t have a coherent product vision, we didn’t understand the customer well enough, and we had a bad outlook on competition and a myriad of other things. Lessons: I already made another post about the importance of outlook on competition. Do not quit just because there are competitors or just because you can’t be 10x better. Indiehackers and Bootstrappers (or even startups) need to differentiate in the market, which can be via product (UX/UI), distribution, or both. Asking Ace Intro.co + Crowdsharing &#x200B; https://preview.redd.it/0hu2tt16tf5c1.jpg?width=1456&format=pjpg&auto=webp&s=3d397568ef2331e78198d64fafc1a701a3e75999 As I got into Twitter, I wanted to chat with some people I saw there. However, they were really expensive. I thought, what if we made some kind of crowdfunding service for other entrepreneurs to get a private lecture from their idols? It seemed to make a lot of sense on paper. It was solving a problem (validated via the fact that Intro.co is a thing and making things cheaper and accessible is a solid ground to stand on), we understood the market (or so we thought), and it could monetize relatively quickly. However, after 1-2 posts on Reddit and Indiehackers, we quickly learned three things. Firstly, no one cares. Secondly, even if they do, they think they can get the same information for free online. Thirdly, the reasons before are bad because for the first point → we barely talked to people, and for the second people → we barely talked to the wrong people. However, at least we didn’t code anything this time and tried to validate via a landing page. Lessons Don’t give up after 1 Redditor says “I don’t need this” Don’t be scared to choose successful people as your audience. Clarito Journaling with AI analyzer https://preview.redd.it/8ria2wq6tf5c1.jpg?width=1108&format=pjpg&auto=webp&s=586ec28ae75003d9f71b4af2520b748d53dd2854 Clarito is a classic problem all amateur entrepreneurs have. It’s where you lie to yourself that you have a real problem and therefore is validated but when your team asks you how much you would pay you say I guess you will pay, maybe, like 5 bucks a month…? Turns out, you’d have to pay me to use our own product lol. We sent it off to a few friends and posted on some forums, but never really got anything tangible and decided to move away. Honestly, a lot of it is us in our own heads. We say the market is too saturated, it’ll be hard to monetize, it’s B2C, etc. Lessons: You use the Mom Test on other people. You have to do it yourself as well. However, recognizing that the Mom Test requires a lot of creativity in its investigation because knowing what questions to ask can determine the outcome of the validation. I asked myself “Do I journal” but I didn’t ask myself “How often do I want GPT to chyme in on my reflections”. Which was practically never. That being said I think with the right audience and distribution, this product can work. I just don’t know (let alone care) about the audience that much (and I thought I was one of them)/ Horns & Claw Scrapes financial news texts you whether you should buy/sell the stock (news sentiment analysis) &#x200B; https://preview.redd.it/gvfxdgc7tf5c1.jpg?width=1287&format=pjpg&auto=webp&s=63977bbc33fe74147b1f72913cefee4a9ebec9c2 This one we didn’t even bother launching. Probably something internal in the team and also seemed too good to be true (because if this works, doesn’t that just make us ultra-rich fast?). I saw a similar tool making 10k MRR so I guess I was wrong. Lessons: This one was pretty much just us getting into our heads. I declared that without an audience it would be impossible to ship this product and we needed to start a YouTube channel. Lol, and we did. And we couldn’t even film for 1 minute. I made bold statements like “We will commit to this for at least 1 year no matter what”. Learnery Make courses about any subject https://preview.redd.it/1nw6z448tf5c1.jpg?width=1112&format=pjpg&auto=webp&s=f2c73e8af23b0a6c3747a81e785960d4004feb48 This is probably the most “successful” project we’ve made. It grew from a couple of dozen to a couple of hundred users. It has 11 buy events for $9.99 LTD (we couldn’t be bothered connecting Stripe because we thought no one would buy it anyway). However what got us discouraged from seriously pursuing it more is, that this has very low defensibility, “Why wouldn’t someone just use chatGPT?” and it’s B2C so it’s hard to monetize. I used it myself for a month or so but then stopped. I don’t think it’s the app, I think the act of learning a concept from scratch isn’t something you do constantly in the way Learnery delivers it (ie course). I saw a bunch of similar apps that look like Ass make like 10k MRR. Lessons: Don’t do B2C, or if you do, do it properly Don’t just Mixpanel the buy button, connect your Stripe otherwise, it doesn’t feel real and you won’t get momentum. I doubt anyone (even me) will make this mistake again. I live in my GPT bubble where I make assumptions that everyone uses GPT the same way and as much as I do. In reality, the argument that this has low defensibility against GPT is invalid. Platforms that deliver a differentiated UX from ChatGPT to audiences who are not tightly integrated into the habit of using ChatGPT (which is like - everyone except for SOME tech evangelists). CuriosityFM Make podcasts about any subject https://preview.redd.it/zmosrcp8tf5c1.jpg?width=638&format=pjpg&auto=webp&s=d04ddffabef9050050b0d87939273cc96a8637dc This was our attempt at making Learnery more unique and more differentiated from chatGPT. We never really launched it. The unit economics didn’t work out and it was actually pretty boring to listen to, I don’t think I even fully listened to one 15-minute episode. I think this wasn’t that bad, it taught us more about ElevenLabs and voice AI. It took us maybe only 2-3 days to build so I think building to learn a new groundbreaking technology is fine. SleepyTale Make children’s bedtime stories https://preview.redd.it/14ue9nm9tf5c1.jpg?width=807&format=pjpg&auto=webp&s=267e18ec6f9270e6d1d11564b38136fa524966a1 My 8-year-old sister gave me that idea. She was too scared of making tea and I was curious about how she’d react if she heard a bedtime story about that exact scenario with the moral that I wanted her to absorb (which is that you shouldn’t be scared to try new things ie stop asking me to make your tea and do it yourself, it’s not that hard. You could say I went full Goebbels on her). Zane messaged a bunch of parents on Facebook but no one really cared. We showed this to one Lady at the place we worked from at Uni and she was impressed and wanted to show it to her kids but we already turned off our ElevenLabs subscription. Lessons: However, the truth behind this is beyond just “you need to be able to distribute”. It’s that you have to care about the audience. I don’t particularly want to build products for kids and parents. I am far away from that audience because I am neither a kid anymore nor going to be a parent anytime soon, and my sister still asked me to make her tea so the story didn’t work. I think it’s important to ask yourself whether you care about the audience. The way you answer that even when you are in full bias mode is, do you engage with them? Are you interested in what’s happening in their communities? Are you friends with them? Etc. User Survey Analyzer Big User Survey → GPT → Insights Report Me and my coworker were chatting about AI when he asked me to help him analyze a massive survey for him. I thought that was some pretty decent validation. Someone in an actual company asking for help. Lessons Market research is important but moving fast is also important. Ie building momentum. Also don’t revolve around 1 user. This has been a problem in multiple projects. Finding as many users as possible in the beginning to talk to is key. Otherwise, you are just waiting for 1 person to get back to you. AutoI18N Automated Internationalization of the codebase for webapps This one I might still do. It’s hard to find a solid distribution strategy. However, the idea came from me having to do it at my day job. It seems a solid problem. I’d say it’s validated and has some good players already. The key will be differentiation via the simplicity of UX and distribution (which means a slightly different audience). In the backlog for now because I don’t care about the problem or the audience that much. Documate - Part 1 Converts complex PDFs into Excel https://preview.redd.it/8b45k9katf5c1.jpg?width=1344&format=pjpg&auto=webp&s=57324b8720eb22782e28794d2db674b073193995 My mom needed to convert a catalog of furniture into an inventory which took her 3 full days of data entry. I automated it for her and thought this could have a big impact but there was no distribution because there was no ICP. We tried to find the ideal customers by talking to a bunch of different demographics but I flew to Kazakhstan for a holiday and so this kind of fizzled out. I am not writing this blog post linearity, this is my 2nd hour and I am tired and don’t want to finish this later so I don’t even know what lessons I learned. Figmatic Marketplace of high-quality Figma mockups of real apps https://preview.redd.it/h13yv45btf5c1.jpg?width=873&format=pjpg&auto=webp&s=aaa2896aeac2f22e9b7d9eed98c28bb8a2d2cdf1 This was a collab between me and my friend Alex. It was the classic Clarito where we both thought we had this problem and would pay to fix it. In reality, this is a vitamin. Neither I, nor I doubt Alex have thought of this as soon as we bought the domain. We posted it on Gumroad, sent it to a bunch of forums, and called it a day. Same issue as almost all the other ones. No distribution strategy. However, apps like Mobin show us that this concept is indeed profitable but it takes time. It needs SEO. It needs a community. None of those things, me and Alex had or was interested in. However shortly after HTML → Figma came out and it’s the best plugin. Maybe that should’ve been the idea. Podcast → Course Turns Podcaster’s episodes into a course This one I got baited by Jason :P I described to him the idea of repurposing his content for a course. He told me this was epic and he would pay. Then after I sent him the demo, he never checked it out. Anyhow during the development, we realized that doesn’t actually work because A podcast doesn’t have the correct format for the course, the most you can extract are concepts and ideas, seldom explanations. Most creators want video-based courses to be hosted on Kajabi or Udemy Another lesson is that when you pitch something to a user, what you articulate is a platform or a process, they imagine an outcome. However, the end result of your platform can be a very different outcome to what they had in mind and there is even a chance that what they want is not possible. You need to understand really well what the outcome looks like before you design the process. This is a classic problem where we thought of the solution before the problem. Yes, the problem exists. Podcasters want to make courses. However, if you really understand what they want, you can see how repurposing a podcast isn’t the best way to get there. However I only really spoke to 1-2 podcasters about this so making conclusions is dangerous for this can just be another asking ace mistake with the Redditor. Documate Part 2 Same concept as before but now I want to run some ads. We’ll see what happens. https://preview.redd.it/xb3npj0ctf5c1.jpg?width=1456&format=pjpg&auto=webp&s=3cd4884a29fd11d870d010a2677b585551c49193 In conclusion https://preview.redd.it/2zrldc9dtf5c1.jpg?width=1840&format=pjpg&auto=webp&s=2b3105073e752ad41c23f205dbd1ea046c1da7ff It doesn’t actually matter that much whether you choose to do a B2C, or a social network or focus on growing your audience. All of these can make you successful. What’s important is that you choose. If I had to summarize my 2023 in one word it’s indecision. Most of these projects succeeded for other people, nothing was as fundamentally wrong about them as I proclaimed. In reality that itself was an excuse. New ideas seduce, and it is a form of discipline to commit to a single project for a respectful amount of time. https://preview.redd.it/zy9a2vzdtf5c1.jpg?width=1456&format=pjpg&auto=webp&s=901c621227bba0feb4efdb39142f66ab2ebb86fe Distribution is not just posting on Indiehackers and Reddit. It’s an actual strategy and you should think of it as soon as you think of the idea, even before the Figma designs. I like how Denis Shatalin taught me. You have to build a pipeline. That means a reliable way to get leads, launch campaigns at them, close deals, learn from them, and optimize. Whenever I get an idea now I always try to ask myself “Where can I find 1000s leads in one day?” If there is no good answer, this is not a good project to do now. &#x200B; https://preview.redd.it/2boh3fpetf5c1.jpg?width=1456&format=pjpg&auto=webp&s=1c0d5d7b000716fcbbb00cbad495e8b61e25be66 Talk to users before doing anything. Jumping on designing and coding to make your idea a reality is a satisfying activity in the short term. Especially for me, I like to create for the sake of creation. However, it is so important to understand the market, understand the audience, understand the distribution. There are a lot of things to understand before coding. https://preview.redd.it/lv8tt96ftf5c1.jpg?width=1456&format=pjpg&auto=webp&s=6c8735aa6ad795f216ff9ddfa2341712e8277724 Get out of your own head. The real reason we dropped so many projects is that we got into our own heads. We let the negative thoughts creep in and kill all the optimism. I am really good at coming up with excuses to start a project. However, I am equally as good at coming up with reasons to kill a project. And so you have this yin and yang of starting and stopping. Building momentum and not burning out. I can say with certainty my team ran out of juice this year. We lost momentum so many times we got burnt out towards the end. Realizing that the project itself has momentum is important. User feedback and sales bring momentum. Building also creates momentum but unless it is matched with an equal force of impact, it can stomp the project down. That is why so many of our projects died quickly after we launched. The smarter approach is to do things that have a low investment of momentum (like talking to users) but result in high impact (sales or feedback). Yes, that means the project can get invalidated which makes it more short-lived than if we built it first, but it preserves team life energy. At the end of 2023 here is a single sentence I am making about how I think one becomes a successful indiehacker. One becomes a successful Indiehacker when one starts to solve pain-killer problems in the market they understand, for an audience they care about and consistently engage with for a long enough timeframe. Therefore an unsuccessful Indiehacker in a single sentence is An unsuccessful Indiehacker constantly enters new markets they don’t understand to build solutions for people whose problems they don’t care about, in a timeframe that is shorter than than the time they spent thinking about distribution. However, an important note to be made. Life is not just about indiehacking. It’s about learning and having fun. In the human world, the best journey isn’t the one that gets you the fastest to your goals but the one you enjoy the most. I enjoyed making those silly little projects and although I do not regret them, I will not repeat the same mistakes in 2024. But while it’s still 2023, I have 2 more projects I want to do :) EDIT: For Devs, frontend is always react with vite (ts) and backend is either node with express (ts) or python. For DB either Postgres or mongo (usually Prisma for ORM). For deployment all of it is on AWS (S3, EC2). In terms of libraries/APIs Whisper.cpp is best open source for transcription Obviously the gpt apis Eleven labs for voice related stuff And other random stuff here and there

I retired at 32 from my side project. Here's the path I took.

EDIT 2: Thanks for the award kind stranger! I've stopped responding to reddit comments for this post. I'm adding an FAQ to the original post based on the most common high quality questions. If you have a question that you're dying to know the answer to and that only I can help you with (vs. Google, ChatGPT, etc.), DM me. EDIT: I love how controversial this post has become (50% upvote rate), and only in this subreddit (vs. other subreddits that I posted the same content in). I trust that the open-minded half of you will find something useful in this post and my other posts and comments. I retired at 32 years old, in large part thanks to a B2C SaaS app that I developed on my own. Now, I don't have to work in order to cover my living expenses, and wouldn't have to work for quite a while. In other words, I can finally sip mai tais at the beach. I've condensed how I got there into this post. First, a super simplified timeline of events, followed by some critical details. Timeline 2013 Graduated college in the US 2013 Started first corporate job 2013 Started side project (B2C app) that would eventually lead to my retirement 2020 Started charging for use of my B2C app (was free, became freemium) 2021 Quit my last corporate job 2022 Retired: time freedom attained Details First, some summary statistics of my path to retirement: 9 years: time between graduating college and my retirement. 8 years: total length of my career where I worked at some corporate day job. 7 years: time it took my B2C app to make its first revenue dollar 2 years: time between my first dollar of SaaS revenue and my retirement. "Something something overnight success a decade in the making". I got extremely lucky on my path to retirement, both in terms of the business environment I was in and who I am as a person. I'd also like to think that some of the conscious decisions I made along the way contributed to my early retirement. Lucky Breaks Was born in the US middle class. Had a natural affinity for computer programming and entrepreneurial mindset (initiative, resourcefulness, pragmatism, courage, growth mindset). Had opportunities to develop these mindsets throughout life. Got into a good college which gave me the credentials to get high paying corporate jobs. Was early to a platform that saw large adoption (see "barnacle on whale" strategy). Business niche is shareworthy: my SaaS received free media. Business niche is relatively stable, and small enough to not be competitive. "Skillful" Decisions I decided to spend the nights and weekends of my early career working on side projects in the hopes that one would hit. I also worked a day job to support myself and build my savings. My launch funnel over roughly 7 years of working on side projects: Countless side projects prototyped. 5 side projects publically launched. 2 side projects made > $0. 1 side project ended up becoming the SaaS that would help me retire. At my corporate day jobs, I optimized for learning and work-life balance. My learning usually stalled after a year or two at one company, so I’d quit and find another job. I invested (and continute to do so) in physical and mental wellbeing via regular workouts, meditation, journaling, traveling, and good food. My fulfilling non-work-life re-energized me for my work-life, and my work-life supported my non-work-life: a virtuous cycle. I automated the most time-consuming aspects of my business (outside of product development). Nowadays, I take long vacations and work at most 20 hours a week / a three-day work week . I decided to keep my business entirely owned and operated by me. It's the best fit for my work-style (high autonomy, deep focus, fast decision-making) and need to have full creative freedom and control. I dated and married a very supportive and inspiring partner. I try not to succumb to outrageous lifestyle creep, which keeps my living expenses low and drastically extends my burn-rate. Prescription To share some aphorisms I’ve leaned with the wantrepreneurs or those who want to follow a similar path: Maximize your at bats, because you only need one hit. Bias towards action. Launch quickly. Get your ideas out into the real world for feedback. Perfect is the enemy of good. If you keep swinging and improving, you'll hit the ball eventually. Keep the big picture in mind. You don't necessarily need a home-run to be happy: a base hit will often do the job. Think about what matters most to you in life: is it a lot of money or status? Or is it something more satisfying, and often just as if not more attainable, like freedom, loving relationships, or fulfillment? Is what you’re doing now a good way to get what you want? Or is there a better way? At more of a micro-level of "keep the big picture in mind", I often see talented wantrepreneurs get stuck in the weeds of lower-level optimizations, usually around technical design choices. They forget (or maybe subconsciously avoid) the higher-level and more important questions of customer development, user experience, and distribution. For example: “Are you solving a real problem?” or “Did you launch an MVP and what did your users think?” Adopt a growth mindset. Believe that you are capable of learning whatever you need to learn in order to do what you want to do. The pain of regret is worse than the pain of failure. I’ve noticed that fear of failure is the greatest thing holding people back from taking action towards their dreams. Unless failure means death in your case, a debilitating fear of failure is a surmountable mental block. You miss 100% of the shots you don't take. When all is said and done, we often regret the things we didn't do in life than the things we did. There’s more to life than just work. Blasphemous (at least among my social circle)! But the reality is that many of the dying regret having worked too much in their lives. As Miss Frizzle from The Magic Schoolbus says: "Take chances, make mistakes, get messy!" Original post

Any strategies to Build an Audience for My AI-Powered Educational Study App?

I'm seeking advice on how to effectively build an audience for my AI-powered educational study app. This app offers a wide range of features designed to enhance the learning experience, including: AI-assisted note-taking and plagiarism checking A collaboration chatting platform for group assignments with AI assistant integration Search and save course materials from the internet Access and interact with YouTube content using AI A content creation and sharing platform for authors and content creators Despite the presence of similar apps in the market, my aim is to create a unique environment where users can create, share, and interact with educational content in novel ways. The app is ready for user feedback, but I'm facing challenges in getting the word out due to my limited social media presence. I would greatly appreciate any tips or strategies to help launch and promote my app successfully. You can explore the app using this link: drixai.com

An Algorithm for Making Truly Stand-Out Advertising Content (+ something more | Part 1)

Hi everyone. my friend and I are software engineers and new to marketing. A few months ago we decided to leverage our software skills for a colleague in ecommerce. It started by implementing a Flux.1 model, then began using texture-based recreations with a canny mask, and then found that we could optimize on both with an added layer of inpainting...and the list goes on. This is the first of a series of posts here about it and I look forward to learning from your feedback. I realized that the most difficult parts of the marketing process when I started out (and most likely for other beginners too) are: Customer Acquisition Costs / Brand Differentiation: Competition is intensifying and it is getting more difficult to stand out in crowded markets and target ad spend more effectively. Maintaining Authenticity at Scale / Data Overload: Balancing growth with authenticity and leveraging available data to successfully engage with customers is a big ask. Creative Fatigue: Maintaining multiple marketing channels in hard, and it becomes harder when you're constantly demanding more and more creative content for campaigns. For 1) I tried using AI to help me summarize, systematize, and gain insights from the information available for a given brand or product (from a page link, prompt, input image, etc.). I know AI is everywhere now, many people are using it unnecessarily and many people are skeptical about it. However, I know from experience, that it is quite helpful in gaining insights/summarizing large amounts of data, and helping people make sense of the creative content, strategy, campaign, etc., that should be created. For 2) By leveraging reviews, forums, and other relevant brand information, AI is able to maintain the story that your brand currently tells, and enhance it based on how your customer base. For 3) Faster results means less creative fatigue- this translates to an easier time managing omnichannel marketing efforts and scaling advertising. If you're interested, please have a look at the result at madsimpleads.com You’ll need to log in to access the solution, and I'll add credits to your account to try it out! (we want to prevent from random people or bots using it because I'm paying to multiple providers for model access). DM me here or drop me a line at austin@madsimpleads.com if you need more. Thank you so much, I'll be happy to get your thoughts I hope the website will help with your advertising, please reach out if you like what I do and want to support the project! Disclaimers: the website looks a bit rough in terms of UI/UX, but we tried focusing on the functionality first available on mobile, works better on desktop I hope this doesn't come across as trying to advertise for my business or breaking any of the community rules. genuinely looking for feedback. Thank you

I made a super niche app for sailors and scaled it to 500k downloads

I started developing this app in 2016, and it was my first app ever. I already had several years of programming experience. Since I was studying maritime navigation, I came up with the idea of creating a maritime app to help students with various nautical calculations and learn maritime regulations. Although I had no experience in mobile app development, I chose the Ionic framework and started development gradually. First Version The first version took me about four months to develop because I literally had to learn everything from scratch: how to develop mobile apps, how to publish them, and everything needed to enable downloads on the app stores. Many of you might recognize me from my story about developing Sintelly and its late monetization. I made the same mistake with this maritime app. At that time, in my country, there was no possibility of earning through in-app purchases, only through ad displays. Since the app was predominantly downloaded in countries like India, the Philippines, and Indonesia, the ad revenue was quite low, and after some time, I removed the ads. Abandonment and Realization As I started developing other apps, this one fell into obscurity. I even just remembered that I needed to renew the domain, which resulted in losing it. The domain buyer tried to sell it back to me for years for $20k, which was absurd. All this led me to rebrand and start working on this app again. Interestingly, during these 8 years, the app never showed a declining trend in installations or active users. I'll share some numbers to give you insight: Total installations (Android + iOS): 501,000 Active installations (Android): 48,000 Monthly active users: 20,000 Average rating: Android 4.8, iOS 4.7 When I considered these numbers, I realized they weren't bad at all and that I was far ahead of most competitors. This led to my decision to rebrand and create a new website. I quickly built the website using WordPress and published lots of existing content from the app. What surprises me is that today, after a year and a half, the website has about 8-10k monthly organic visits. Choosing a Direction Based on all this, I decided it was time to create a Premium version and start selling the app. Since I've been working with AI for many years (which I've written about here), I started thinking about using AI to help seafarers speed up some of their tasks. This led to the idea of creating a multi-agent system equipped with numerous tools to help seafarers. I developed various agents with functionalities, including retrieving maritime weather information, locating and tracking ships, doing various nautical calculations, calculating the shortest maritime routes and unit conversions, and learning about all courses and maritime regulations. All this required considerable work, but thanks to tools like Cursor and Claude, I implemented it in less than four weeks. Last week, I published this new version and started selling subscriptions, and I can already boast that I've earned slightly over $100. This isn't much, but I'm happy to see my first app generating some income, which I always thought impossible. Along this journey, I learned many lessons, and the most important one is to never give up or write off a product. With a little effort, everything can be brought back to life and secure at least some passive income, enough for your morning coffee. Additionally, I learned how to develop mobile apps, which has shaped my career since then. If it weren't for this app, I probably would never have become a developer. I have numerous plans for what to add next and how to improve. I'll base everything on AI features and push the app in that direction.

Learn how to code in 24 hours with a Private AI Tutor

Learning how to code is REALLY HARD. I remember I struggled a lot learning how to code. I just wanted to build a simple app or website but the task was super daunting. There were so many steps, so many things to learn. Terminal, git, command prompt, IDE, library, package, React, Express, GAH! It was hard. I did a lot of courses but I always got 10-20% through and gave up. They were just SO BORING. Some of the courses were too advanced, some were too beginner, and all required me to keep pausing & playing. So, I built Athens: https://www.tryathens.com/ Athens gives you a personal AI tutor that understands your skill level and modifies each challenge/lesson to your skill level. No nothing about programming? Learn from the basics of HTML. Already know the basics of React? Implement it, and then learn the backend. All of this while you build a fully-fledged clone of Instagram, Netflix, or one of the many other projects! What do you guys think about this? Would you use it? Do you have any feedback? PS: Athens will normally go for $299/year but currently it's on pre-sale for $159 (sometimes $99 with lifetime discount)

I spent 6 months on a web app as a side project, and got 0 users. Here is my story.

Edit Thank you all so much for your time reading my story. Your support, feedback, criticism, and skepticism; all helped me a lot, and I couldn't appreciate it enough \^\_\^ I very rarely have stuff to post on Reddit, but I share how my project is going on, just random stuff, and memes on X. In case few might want to keep up 👀 TL;DR I spent 6 months on a tool that currently has 0 users. Below is what I learned during my journey, sharing because I believe most mistakes are easily avoidable. Do not overestimate your product and assume it will be an exception to fundamental principles. Principles are there for a reason. Always look for validation before you start. Avoid building products with a low money-to-effort ratio/in very competitive fields. Unless you have the means, you probably won't make it. Pick a problem space, pick your target audience, and talk to them before thinking about a solution. Identify and match their pain points. Only then should you think of a solution. If people are not overly excited or willing to pay in advance for a discounted price, it might be a sign to rethink. Sell one and only one feature at a time. Avoid everything else. If people don't pay for that one core feature, no secondary feature will change their mind. Always spend twice as much time marketing as you do building. You will not get users if they don't know it exists. Define success metrics ("1000 users in 3 months" or "$6000 in the account at the end of 6 months") before you start. If you don't meet them, strongly consider quitting the project. If you can't get enough users to keep going, nothing else matters. VALIDATION, VALIDATION, VALIDATION. Success is not random, but most of our first products will not make a success story. Know when to admit failure, and move on. Even if a product of yours doesn't succeed, what you learned during its journey will turn out to be invaluable for your future. My story So, this is the story of a product that I’ve been working on for the last 6 months. As it's the first product I’ve ever built, after watching you all from the sidelines, I have learned a lot, made many mistakes, and did only a few things right. Just sharing what I’ve learned and some insights from my journey so far. I hope that this post will help you avoid the mistakes I made — most of which I consider easily avoidable — while you enjoy reading it, and get to know me a little bit more 🤓. A slow start after many years Summ isn’t the first product I really wanted to build. Lacking enough dev skills to even get started was a huge blocker for so many years. In fact, the first product I would’ve LOVED to build was a smart personal shopping assistant. I had this idea 4 years ago; but with no GPT, no coding skills, no technical co-founder, I didn’t have the means to make it happen. I still do not know if such a tool exists and is good enough. All I wanted was a tool that could make data-based predictions about when to buy stuff (“buy a new toothpaste every three months”) and suggest physical products that I might need or be strongly interested in. AFAIK, Amazon famously still struggles with the second one. Fast-forward a few years, I learned the very basics of HTML, CSS, and Vanilla JS. Still was not there to build a product; but good enough to code my design portfolio from scratch. Yet, I couldn’t imagine myself building a product using Vanilla JS. I really hated it, I really sucked at it. So, back to tutorial hell, and to learn about this framework I just heard about: React.React introduced so many new concepts to me. “Thinking in React” is a phrase we heard a lot, and with quite good reasons. After some time, I was able to build very basic tutorial apps, both in React, and React Native; but I have to say that I really hated coding for mobile. At this point, I was already a fan of productivity apps, and had a concept for a time management assistant app in my design portfolio. So, why not build one? Surely, it must be easy, since every coding tutorial starts with a todo app. ❌ WRONG! Building a basic todo app is easy enough, but building one good enough for a place in the market was a challenge I took and failed. I wasted one month on that until I abandoned the project for good. Even if I continued working on it, as the productivity landscape is overly competitive, I wouldn’t be able to make enough money to cover costs, assuming I make any. Since I was (and still am) in between jobs, I decided to abandon the project. 👉 What I learned: Do not start projects with a low ratio of money to effort and time. Example: Even if I get 500 monthly users, 200 of which are paid users (unrealistically high number), assuming an average subscription fee of $5/m (such apps are quite cheap, mostly due to the high competition), it would make me around $1000 minus any occurring costs. Any founder with a product that has 500 active users should make more. Even if it was relatively successful, due to the high competition, I wouldn’t make any meaningful money. PS: I use Todoist today. Due to local pricing, I pay less than $2/m. There is no way I could beat this competitive pricing, let alone the app itself. But, somehow, with a project that wasn’t even functional — let alone being an MVP — I made my first Wi-Fi money: Someone decided that the domain I preemptively purchased is worth something. By this point, I had already abandoned the project, certainly wasn’t going to renew the domain, was looking for a FT job, and a new project that I could work on. And out of nowhere, someone hands me some free money — who am I not to take it? Of course, I took it. The domain is still unused, no idea why 🤔. Ngl, I still hate the fact that my first Wi-Fi money came from this. A new idea worth pursuing? Fast-forward some weeks now. Around March, I got this crazy idea of building an email productivity tool. We all use emails, yet we all hate them. So, this must be fixed. Everyone uses emails, in fact everyone HAS TO use emails. So, I just needed to build a tool and wait for people to come. This was all, really. After all, the problem space is huge, there is enough room for another product, everyone uses emails, no need for any further validation, right? ❌ WRONG ONCE AGAIN! We all hear from the greatest in the startup landscape that we must validate our ideas with real people, yet at least some of us (guilty here 🥸) think that our product will be hugely successful and prove them to be an exception. Few might, but most are not. I certainly wasn't. 👉 Lesson learned: Always validate your ideas with real people. Ask them how much they’d pay for such a tool (not if they would). Much better if they are willing to pay upfront for a discount, etc. But even this comes later, keep reading. I think the difference between “How much” and “If” is huge for two reasons: (1) By asking them for “How much”, you force them to think in a more realistic setting. (2) You will have a more realistic idea on your profit margins. Based on my competitive analysis, I already had a solution in my mind to improve our email usage standards and email productivity (huge mistake), but I did my best to learn about their problems regarding those without pushing the idea too hard. The idea is this: Generate concise email summaries with suggested actions, combine them into one email, and send it at their preferred times. Save as much as time the AI you end up with allows. After all, everyone loves to save time. So, what kind of validation did I seek for? Talked with only a few people around me about this crazy, internet-breaking idea. The responses I got were, now I see, mediocre; no one got excited about it, just said things along the lines of “Cool idea, OK”. So, any reasonable person in this situation would think “Okay, not might not be working”, right? Well, I did not. I assumed that they were the wrong audience for this product, and there was this magical land of user segments waiting eagerly for my product, yet unknowingly. To this day, I still have not reached this magical place. Perhaps, it didn’t exist in the first place. If I cannot find it, whether it exists or not doesn’t matter. I am certainly searching for it. 👉 What I should have done: Once I decide on a problem space (time management, email productivity, etc.), I should decide on my potential user segments, people who I plan to sell my product to. Then I should go talk to those people, ask them about their pains, then get to the problem-solving/ideation phase only later. ❗️ VALIDATION COMES FROM THE REALITY OUTSIDE. What validation looks like might change from product to product; but what invalidation looks like is more or less the same for every product. Nico Jeannen told me yesterday “validation = money in the account” on Twitter. This is the ultimate form of validation your product could get. If your product doesn’t make any money, then something is invalidated by reality: Your product, you, your idea, who knows? So, at this point, I knew a little bit of Python from spending some time in tutorial hell a few years ago, some HTML/CSS/JS, barely enough React to build a working app. React could work for this project, but I needed easy-to-implement server interactivity. Luckily, around this time, I got to know about this new gen of indie hackers, and learned (but didn’t truly understand) about their approach to indie hacking, and this library called Nextjs. How good Next.js still blows my mind. So, I was back to tutorial hell once again. But, this time, with a promise to myself: This is the last time I would visit tutorial hell. Time to start building this "ground-breaking idea" Learning the fundamentals of Next.js was easier than learning of React unsurprisingly. Yet, the first time I managed to run server actions on Next.js was one of the rarest moments that completely blew my mind. To this day, I reject the idea that it is something else than pure magic under its hood. Did I absolutely need Nextjs for this project though? I do not think so. Did it save me lots of time? Absolutely. Furthermore, learning Nextjs will certainly be quite helpful for other projects that I will be tackling in the future. Already got a few ideas that might be worth pursuing in the head in case I decide to abandon Summ in the future. Fast-forward few weeks again: So, at this stage, I had a barely working MVP-like product. Since the very beginning, I spent every free hour (and more) on this project as speed is essential. But, I am not so sure it was worth it to overwork in retrospect. Yet, I know I couldn’t help myself. Everything is going kinda smooth, so what’s the worst thing that could ever happen? Well, both Apple and Google announced their AIs (Apple Intelligence and Google Gemini, respectively) will have email summarization features for their products. Summarizing singular emails is no big deal, after all there were already so many similar products in the market. I still think that what truly matters is a frictionless user experience, and this is why I built this product in a certain way: You spend less than a few minutes setting up your account, and you get to enjoy your email summaries, without ever visiting its website again. This is still a very cool concept I really like a lot. So, at this point: I had no other idea that could be pursued, already spent too much time on this project. Do I quit or not? This was the question. Of course not. I just have to launch this product as quickly as possible. So, I did something right, a quite rare occurrence I might say: Re-planned my product, dropped everything secondary to the core feature immediately (save time on reading emails), tried launching it asap. 👉 Insight: Sell only one core feature at one time. Drop anything secondary to this core feature. Well, my primary occupation is product design. So one would expect that a product I build must have stellar design. I considered any considerable time spent on design at this stage would be simply wasted. I still think this is both true and wrong: True, because if your product’s core benefits suck, no one will care about your design. False, because if your design looks amateurish, no one will trust you and your product. So, I always targeted an average level design with it and the way this tool works made it quite easy as I had to design only 2 primary pages: Landing page and user portal (which has only settings and analytics pages). However, even though I knew spending time on design was not worth much of my time, I got a bit “greedy”: In fact, I redesigned those pages three times, and still ended up with a so-so design that I am not proud of. 👉 What I would do differently: Unless absolutely necessary, only one iteration per stage as long as it works. This, in my mind, applies to everything. If your product’s A feature works, then no need to rewrite it from scratch for any reason, or even refactor it. When your product becomes a success, and you absolutely need that part of your codebase to be written, do so, but only then. Ready to launch, now is th etime for some marketing, right? By July 26, I already had a “launchable” product that barely works (I marked this date on a Notion docs, this is how I know). Yet, I had spent almost no time on marketing, sales, whatever. After all, “You build and they will come”. Did I know that I needed marketing? Of course I did, but knowingly didn’t. Why, you might ask. Well, from my perspective, it had to be a dev-heavy product; meaning that you spend most of your time on developing it, mostly coding skills. But, this is simply wrong. As a rule of thumb, as noted by one of the greatests, Marc Louvion, you should spend at least twice of the building time on marketing. ❗️ Time spent on building \* 2 people don’t know your product > they don’t use your product > you don’t get users > you don’t make money Easy as that. Following the same reasoning, a slightly different approach to planning a project is possible. Determine an approximate time to complete the project with a high level project plan. Let’s say 6 months. By the reasoning above, 2 months should go into building, and 4 into marketing. If you need 4 months for building instead of 2, then you need 8 months of marketing, which makes the time to complete the project 12 months. If you don’t have that much time, then quit the project. When does a project count as completed? Well, in reality, never. But, I think we have to define success conditions even before we start for indie projects and startups; so we know when to quit when they are not met. A success condition could look like “Make $6000 in 12 months” or “Have 3000 users in 6 months”. It all depends on the project. But, once you set it, it should be set in stone: You don’t change it unless absolutely necessary. I suspect there are few principles that make a solopreneur successful; and knowing when to quit and when to continue is definitely one of them. Marc Louvion is famously known for his success, but he got there after failing so many projects. To my knowledge, the same applies to Nico Jeannen, Pieter Levels, or almost everyone as well. ❗️ Determining when to continue even before you start will definitely help in the long run. A half-aed launch Time-leap again. Around mid August, I “soft launched” my product. By soft launch, I mean lazy marketing. Just tweeting about it, posting it on free directories. Did I get any traffic? Surely I did. Did I get any users? Nope. Only after this time, it hit me: “Either something is wrong with me, or with this product” Marketing might be a much bigger factor for a project’s success after all. Even though I get some traffic, not convincing enough for people to sign up even for a free trial. The product was still perfect in my eyes at the time (well, still is ^(\_),) so the right people are not finding my product, I thought. Then, a question that I should have been asking at the very first place, one that could prevent all these, comes to my mind: “How do even people search for such tools?” If we are to consider this whole journey of me and my so-far-failed product to be an already destined failure, one metric suffices to show why. Search volume: 30. Even if people have such a pain point, they are not looking for email summaries. So, almost no organic traffic coming from Google. But, as a person who did zero marketing on this or any product, who has zero marketing knowledge, who doesn’t have an audience on social media, there is not much I could do. Finally, it was time to give up. Or not… In my eyes, the most important element that makes a founder (solo or not) successful (this, I am not by any means) is to solve problems. ❗️ So, the problem was this: “People are not finding my product by organic search” How do I make sure I get some organic traffic and gets more visibility? Learn digital marketing and SEO as much as I can within very limited time. Thankfully, without spending much time, I came across Neil Patel's YT channel, and as I said many times, it is an absolute gold mine. I learned a lot, especially about the fundamentals, and surely it will be fruitful; but there is no magic trick that could make people visit your website. SEO certainly helps, but only when people are looking for your keywords. However, it is truly a magical solution to get in touch with REAL people that are in your user segments: 👉 Understand your pains, understand their problems, help them to solve them via building products. I did not do this so far, have to admit. But, in case you would like to have a chat about your email usage, and email productivity, just get in touch; I’d be delighted to hear about them. Getting ready for a ProductHunt launch The date was Sept 1. And I unlocked an impossible achievement: Running out of Supabase’s free plan’s Egres limit while having zero users. I was already considering moving out of their Cloud server and managing a Supabase CLI service on my Hetzner VPS for some time; but never ever suspected that I would have to do this quickly. The cheapest plan Supabase offers is $25/month; yet, at that point, I am in between jobs for such a long time, basically broke, and could barely afford that price. One or two months could be okay, but why pay for it if I will eventually move out of their Cloud service? So, instead of paying $25, I spent two days migrating out of Supabase Cloud. Worth my time? Definitely not. But, when you are broke, you gotta do stupid things. This was the first time that I felt lucky to have zero users: I have no idea how I would manage this migration if I had any. I think this is one of the core tenets of an indie hacker: Controlling their own environment. I can’t remember whose quote this is, but I suspect it was Naval: Entrepreneurs have an almost pathological need to control their own fate. They will take any suffering if they can be in charge of their destiny, and not have it in somebody else’s hands. What’s truly scary is, at least in my case, we make people around us suffer at the expense of our attempting to control our own fates. I know this period has been quite hard on my wife as well, as I neglected her quite a bit, but sadly, I know that this will happen again. It is something that I can barely help with. Still, so sorry. After working the last two weeks on a ProductHunt Launch, I finally launched it this Tuesday. Zero ranking, zero new users, but 36 kind people upvoted my product, and many commented and provided invaluable feedback. I couldn't be more grateful for each one of them 🙏. Considering all these, what lies in the future of Summ though? I have no idea, to be honest. On one hand, I have zero users, have no job, no income. So, I need a way to make money asap. On the other hand, the whole idea of it revolves around one core premise (not an assumption) that I am not so willing to share; and I couldn’t have more trust in it. This might not be the best iteration of it, however I certainly believe that email usage is one of the best problem spaces one could work on. 👉 But, one thing is for certain: I need to get in touch with people, and talk with them about this product I built so far. In fact, this is the only item on my agenda. Nothing else will save my brainchild <3. Below are some other insights and notes that I got during my journey; as they do not 100% fit into this story, I think it is more suitable to list them here. I hope you enjoyed reading this. Give Summ a try, it comes with a generous free trial, no credit card required. Some additional notes and insights: Project planning is one of the most underestimated skills for solopreneurs. It saves you enormous time, and helps you to keep your focus up. Building B2B products beats building B2C products. Businesses are very willing to pay big bucks if your product helps them. On the other hand, spending a few hours per user who would pay $5/m probably is not worth your time. It doesn’t matter how brilliant your product is if no one uses it. If you cannot sell a product in a certain category/niche (or do not know how to sell it), it might be a good idea not to start a project in it. Going after new ideas and ventures is quite risky, especially if you don’t know how to market it. On the other hand, an already established category means that there is already demand. Whether this demand is sufficient or not is another issue. As long as there is enough demand for your product to fit in, any category/niche is good. Some might be better, some might be worse. Unless you are going hardcore B2B, you will need people to find your product by means of organic search. Always conduct thorough keyword research as soon as possible.

What's the s way to implement AI - Free Tire API - Initial Phase

hi there, I'm working on a project where I need to implement AI for text generation.For that I use gemini api but it has limitations for 15 users per minute just like others. so in your projects how did you manage this in initial phase to get this effectively with no budgets. I'm just starting with this and I don't have that much idea about model as I'm learning it and exploring.

Running and selling multiple side projects alongside a 9-5

My current side project started 56 days ago when I started writing 1,000 words per day. My core businesses are an agency and job board, and I just needed a creative outlet. The likes of Chris Guillebeau and Nathan Barry attribute their progression to writing so I thought I’d see if it might do the same for me. At first I was just vomiting words onto the screen, I made a blog and wrote mainly technical guides related to my skills. Over time I realised I was writing more and more about running a business as a solopreneur, or lean operator. There is tons of content out there giving you the Birds Eye of going from 0 to £10m. Inspiring stuff, but I think there is a void in real content, explaining the nuts and bolts of the how.  What is the day-to-day like for the solopreneurs who make a good living and have plenty of free time? That’s what I’m striving for anyway. I’m not talking about the 7-figure outliers. Or the ones teaching you to make content so you can have a business teaching others how to make content, and so on. I’m also sick of the ‘I made $X in 5 minutes and how you can too’  So, I started chatting to people in my network who run lean businesses and/or side hustles. I ask them a bit about their journey and ask them to teach something - how they operate, or a skill/process/system/tool that other people like you/me will find useful. One of my first chats was with Sam Dickie, who runs multiple side projects so thought I’d share here, see if others find it useful and get some feedback. I’ve removed all links as I’ve never posted on Reddit before so conscious of not being promotional, I’m posting this stuff to a tiny email list of friends with no upsells. Just finding my feet on whether others find it useful or not: — Sam is a serial entrepreneur who builds projects in his spare time whilst working a 9-5. He’s scaled and sold multiple ventures and currently runs one of the best newsletters out there for builders and entrepreneurs. Building audience through newsletters has always been a cornerstone strategy for him, so, along with sharing his advice on solopreneurism, he’s also generously shared his lean newsletter writing process. About Sam Sam is a Senior Product Manager who has spent the last 15 years working in the tech sector after starting his career as a town planner. In addition to his job he spends some of his spare time building side projects. These have included a 3D printing startup, a tech directory, a newsletter, a beta product directory, and consultancy. Sam is the epitome of making a success out of following your interest and curiosity. It’s clear he enjoys his business ventures and builds in a risk-free way.   It’s often touted by business gurus to avoid building around your interests, but Sam bucks the trend successfully. I think he’s someone who has already found his 1,000 true fans.  Descending rabbit holes, Sam’s journey of invention and curation 3D printing Sam’s first foray into launching a startup was with Fiilo, a 3D printing business. This was at the height of the 3D printing craze and he self-admits that he used the launch as an excuse to buy a 3D printer. He ended up with two and launching a product called GrowGo. GrowGo is a sustainable 3D-printed product that turns any bottle into somewhere that you can grow plants and herbs. He eventually sold this business and the printers, making around £10k. Along the way, he was exposed to various business tasks, including building a website in Weebly, the biggest nocode website builder of the time, and built an API that enabled print on demand for his product. NoCode.Tech The experiences of building as someone non-technical led to numerous friends asking how he built all of this tech. Back then, nocode wasn’t popular, and it had almost zero search volume, so Sam created a basic directory. A quick landing page on Weebly with a basic value prop, a short explanation and a list of the tools he had used before. It hit the top spot on Product Hunt, and he landed 2,000 subscribers in the first 48 hours. But, he hadn’t built it at this point, so he set about getting to work. He built the directory and list to 30,000 subs and monetised the site through advertising. At its peak with Sam, it was receiving about £2,000 per month in ad revenue. He was still working his 9-5 at this point, so thought it might be a good time to exit. The site was still growing, but it was becoming anxiety inducing whilst he was still working full-time. So, he ended up selling the site and making friend’s with the buyer. Fast forwarding a bit, Nocode.tech was eventually acquired by Stackr, a nocode app. Sam was working for their competitor at the time and ended up being offered a job by his friend who acquired the site. All of this from a side project in his area of passion. Creator Club After selling the directory, Sam lost his outlet for sharing his tools and learnings.  Being fascinated with curation and loving sifting through for nuggets, he invested more time into his personal website and launched Creator Club newsletter. Sam writes monthly and currently has over 8,000 subs. It’s one of the few newsletters that I let bypass my email filters and land in my main inbox. Life as a Part-Time Multipreneur Side Hustler If it’s not obvious already Sam is a curiosity led business creator. He’s found that the products without a revenue focus or intention have ironically outperformed those created for the sole purpose of creating money. He enjoys working on his side hustles. He could have run the Nocode.Tech for 10 more years and wouldn’t have tired of it as it’s a byproduct of his interest. For this reason, he has also created the Beta Directory, simply because he loves unearthing early-stage products. He admits he gets the fear when he thinks about quitting his 9-5, although he suspects if he devoted the same energy to one of his projects it could replace his income (no doubts from me here). This same fear means that he can run his ventures with less fear. This way, he can experiment with freedom and isn’t risking the ranch with a young family to consider. For example, recently he stopped paid sponsors on his newsletter as it was more stress than the value of the income to him. Sam divides his time on evenings and weekends (unequally) between the following: Creator Club Validation Co Beta directory Consultancy The pure side hustle status magnifies the need to run lean, let’s jump into his process…. Sam’s lean newsletter curation and creation process Starting out publishing his personal newsletter Going against his expertise, Sam originally over-engineered his process.  He curated with Feedly and tried to automate the full writing process with Zapier. The trouble is that there are too many points of failure which can lead the whole  chain to break down, and you spend more time fixing the system. For a 200 subscriber newsletter, he needed to pare things back. His set-up now Sam scaled back and now simple builds automations when he needs them. He keeps the process simple, right down to the design and any welcome automations. Keeping things real We touched on the trend that keeping things raw is better. Content has come full circle with the advent of AI. Everything looks too perfect and consequently, people’s tastes are changing. Sam mentioned watermarks that show content isn’t AI written, and we referenced content such as Greg Isenberg’s sketches, and Chris Donnelly’s image posts. \\Step by Step Process:\\ Using Stoop Inbox to manage sources Curation with Pocket Managing content with Airtable and Zapier Using Bearly to summarise Substack for writing Monitoring content sources Sam uses Stoop Inbox, an RSS curation tool, to manage his content sources. It gives him a dedicated email address for newsletters and he follows an Inbox Zero methodology. He checks in daily in Stoop, and on X, Reddit and IndieHackers. With X, he just uses the standard interface but has been careful to curate his feed, sometimes adding in extra notifications to hear from interesting people. Highlighting content When curating links, Sam uses Arc browser and the Pocket extension to save links. It’s super simple and lightweight. He creates tags which trigger an automation that curates the link to Airtable. If you watch the video, here’s a shoutout to Alice, the AI interface I use which has recently featured on Product Hunt. It’s a fantastic tool with bags of potential to enhance a solopreneur’s life. Ranking and sorting content He sends the links indexed using Pocket to a basic Airtable base via Zapier. From there, he grades the content and sets aside some time to read it in more depth. Pocket pulls through the title, metadata, and URL link. Review Sam does this manually but has used a tool as a shortcut for digesting long form content — Bearly.ai. Bearly.ai was created by Trung Phan and linking back to raw content, Trung is 1/3 of the hosts on the Not Investment Advice podcast. Its irreverent style and thumbnail are an example of a successful podcast that doesn’t over polish. Writing it all up Being a huge Notion fan (check out the free templates on his site), Sam originally used Notion for writing and linked it into Revue. When Elon sunsetted Revue, he switched to Substack. He loves the Substack interface so drafts in Substack based on a duplication of last month’s edition. Before publishing, Sam runs through a 10-point Notion checklist, which he shared with me. Parting Advice Keep your tool stack as lean as possible. Avoid tool switching to the shiny new object. Getting launched quickly is key. Don’t think that you have to be everywhere for distribution, Sam sticks with what he knows on X and LinkedIn. Overall, he advises just keeping things simple and therefore minimising risk. Resources He says they’re cliche, but I don’t agree; they’re timeless. Paul Graham of Y Combinator is someone Sam recommends following. He doesn’t write much, which is great as Sam gets anxiety when someone good often writes and he can’t keep up with the writing. His content is well thought out and distills complex concepts in entrepreneurship and startups. In addition, Sam loves Naval Ravikant’s approach. He mentions checking out the Almanac of Naval Ravikant for collected wisdom. Follow Sam’s Journey Again, not going to link here but you can find Sam’s stuff easily enough if you want to. His personal website is beautiful and contains loads of free downloads. He has also curated personal websites he admires if you need some inspiration. Sam is a super nice guy so reach out to him, I did before I started my personal blog recently, and he gave me some great advice. Also, worth keeping an eye on Validation Co, where he aims to help early-stage makers and creators validate their ideas. He’s building super slow — trying to enjoy the process without unachievable deadlines. Maintaining his stamina and passion. Amazing, I hope he writes more about that soon! -- That’s my second shot at an interview, hope you enjoyed it and found something useful in it. I’m talking to a marketplace founder who spends 2–3 hours per month his project, a multiple job board owner with a 9-5 and a leading book designer next. As this is my side project, should I keep going?

I am building my agency to help founders build AI startups after 2 successful AI SaaS exits and 4 failures

Hey everyone, I have been building AI products before ChatGPT was launched. In these years, I have managed to launch, scale and exit 2 SaaS products successfully. Today I am launching a new service offering - Query Labs - Helping you build AI agents for your startups. Like all my previous products, I will be building this in public and share my learning along the way. Here's what I have built so far : Microsponsors ( Fail ) My first product ever. I tried to create a marketplace for newsletter writers to find sponsorship opportunity. Got a few very big newsletter listed on the marketplace as well. However, building marketplace is tough. I found it very difficult to bring in sponsors. Ended up shutting it down, AI Query (Exit - Pre revenue ) It was the second half of 2022 and GPT-3 was the most advance AI on the market. I decided to build a tool that can help developers and non-technical folks write SQL queries by just asking in plain english. I got my first taste of success with this. Had a decent offer even before I figured out monetisation. Accepted the offer to focus on my next product which had already started gaining traction AI Excel Bot ( Exit - Revenue Generating ) AI Excel Bot was my wild success. I had worked hard on the SEO for the site, along with the UI / UX to make it the best AI to write excel formulas and general excel task. There was already a large competitor in the market. However, the reality is that you don't need to be the top player. There is always room for multiple players to survive in a large market. You just need to find the good differentiating factor For AI Excel Bot, the differentiator was the chrome extension, that helped users access it anywhere on the internet. Scaled the product to more than 40k users at the time of exit. However, in the end I decided to exit and focus on my software service business that needed more time. Tutore AI ( Fail ) I wanted to build something useful for students to help them learn better. Tutore was my idea to build AI tools for students. I did launch quickly with multiple tools. However, wasn't motivated enough to continue with the grind. I have decided to sell the product. Have had some meetings with potential buyers but didn't agree on price. Prompt Hackers ( 1k users but no revenue ) Prompt Hackers is a directory of AI prompts for all the use cases you can image. I focused a lot on bringing traffic and newsletter subscription from the day 1. I have never had a problem bringing initial set of users to my products. Prompt Hackers was getting close to 20k page views a month. At the same time we had close to 1k newsletter subscribers. Since our target customers were people choosing to use ChatGPT / Bard instead of some specific software for their task, I built a Prompt Generation and Prompt Optimisation AI. Along with this I also created features to build private prompt library. To make the experience even better, I launched a Chrome Extension that helps users access the prompt generation AI and their prompt library while using ChatGPT. However, I couldn't figure out monetisation. I still get close to 4k page views per month with no marketing at all. There are users who use the AI tools and the prompt library feature daily. But, since I couldn't figure out monetisation, I decided to not put time into the project. There you go. These are all the products I have built in the last 3 years. I have been heavy investing myself in the latest tech in LLMs and AI agents. I know the biggest challenge for AI founders is the AI agents and backend pipelines. That's why I am launching Query Labs. To help you build the best AI implementation for your innovative AI startup. I would love to hear feedback from the community. I will be sharing my learning with my new service along the way. Thanks!

Solopreneur making $40k MRR with a No Code SaaS sideproject

Hey, I'm Elias and I do case studies analyzing successful startups and solopreneurs. I wanted to share the summarized version of this one with you because this entrepreneurial journey blew my mind. This post will be about FormulaBot (ExcelFormulaBot), an AI No Code SaaS founded by David Bressler back in August 2022. FormulaBot is currently making $40k MRR (monthly recurring revenue). How did the founder come up with the idea. David is a data guy who worked in analytics for several years. In July 2022, David got really interested in AI, especially ChatGPT. One night, he tried it out at home, just like we all did back in the time. But in his case, trying ChatGPT gave him a big idea. That idea ended up making him a lot of money and changing the life of 750 million people who use Excel. That night David started by asking GPT easy questions, then complex ones. Since he used Excel a lot and helped his colleagues with it, he thought about an AI that could make Excel easier, like generating formulas from text. He looked online but found nothing. Seeing a big chance, he decided to do something about it. What challenges did the founder face. But David didn’t have any idea about how to develop an app. However, with no-code tools this is not a problem anymore. He discovered Bubble, a no-code web app tool that could connect with the OpenAI API.After, learning Bubble from YouTube tutorials and through trial and error and spending his nights studying the OpenAI API documentation, he launched the first version of the app in around three weeks. Strategies that made the project successful. David validated his idea by posting about ExcelFormulaBot on a Reddit Excel subreddit, receiving surprising attention with 10,000 upvotes. This encouraged him to offer the tool for free to gather feedback. Facing a hefty $4,999 API bill after the Reddit post, David quickly monetized his product with a subscription-based SaaS website. On launch day, 82 customers signed up, surpassing his expectations. A successful Product Hunt launch followed, generating $2.4k in sales within 24 hours, and a TikTok influencer with 4.5 million followers brought in thousands of new users overnight with a viral video. Marketing approach: -Paid ads: FormulaBot boosted website traffic with Paid Ads, notably on Google Ads, prioritizing Quality Score. This ensured ads aligned better with user searches, maximizing visibility and cost-efficiency, targeting those seeking Excel formula assistance. -SEO: a) Content/Keyword optimization: FormulaBot improved its SEO by making helpful pages about Excel formulas, like guides on topics such as "How to use SUMIFS." b) Site Speed Enhancement: David boosted FormulaBot's marketing site speed by moving it from Bubble to Framer, aiming to improve user experience and SEO performance. c) On-page optimization: David optimized FormulaBot's on-page elements by adjusting title tags, meta descriptions, and content to enhance SEO performance and align with search intent. These strategic refinements aimed to address ranking declines and emphasize FormulaBot's uniqueness, ultimately improving its visibility and competitiveness in search results. -Virality: FormulaBot went viral as users found it highly useful and cool. Influencers on platforms like TikTok and Twitter shared it with their followers because they found it valuable. Offering numerous free features further enhanced its appeal. Lessons: successes and mistakes. ✅ Leverage industry expertise: David identified a problem in analytics and used his experience to start an online business addressing it, turning an industry challenge into a profitable venture. ✅ Embrace learning new skills: Despite lacking initial technical know-how, David learned what he needed to develop the software himself, demonstrating a commitment to continuous learning and adaptability crucial for success. ❌ Minimize dependency on third parties: Relying solely on the ChatGPT API poses risks for FormulaBot. Any issues with the API could disrupt functionality and limit scalability. ⁉️ Caution with free tools: Offering a free tool can attract users and drive viral growth, but converting them to paying customers is challenging. Avoid relying solely on a 100% free model unless your revenue comes from non-user sources like ads. For businesses dependent on user subscriptions or purchases, balancing user attraction with conversion challenges is crucial. How could you replicate this idea step-by-step. To replicate the success of FormulaBot and similar AI wrapper startups, it's crucial to tread carefully in a competitive market. Avoid mere replication of existing solutions unless you can offer something distinct or superior. Consider these steps to effectively develop an AI Wrapper/ChatGPT wrapper product using Bubble as a no-code tool: Design the user interface: Utilize Bubble's drag-and-drop editor to create a user-friendly interface with input fields, buttons, and result displays. Set up workflows: Define workflows to connect the interface with the ChatGPT API, enabling seamless interaction between users and the AI. Integrate the ChatGPT API: Obtain the API key from OpenAI and integrate it into your app using Bubble's API connector feature. Test and gather feedback: Thoroughly test your app, soliciting feedback to refine functionality and usability. Refine and optimize: Continuously improve your app based on user input and testing results to enhance performance and user experience. The in-depth version of the case study was originally posted here. Feel free to comment if you have any questions, and let me know which similar ideas you'd like me to analyze.

Just reached 300 users in 3 months!!!

Just reached 300 users after 3 months live!!! My co-founder has been posting a bit here and always got some strong support and he suggested I share my side of things so here it is: How it started I co-founded AirMedia almost a year ago and we both didn’t know much about design/marketing/coding (just studied programming during my 6-month exchange period. The quickest way to get started seemed to get a no-code product that we could put in front of users and get feedback. My co-founder then started learning about bubble and we put together a basic platform to show users. I was working on a custom-code database in the meantime and decided after month 2 that we wanted to get something better I.e. AI would be interacting with the UI and had to do everything custom-code for it. We’re now month 3 and started from scratch again. While I was working on the code, we started talking to some potential users and selling lifetime deals to validate the idea (this is where I would start if I had to do it over again). Well I progressively found out it was more complicated than expected and we only released our first beta product last August (6 months later) Some challenges pre-launch: Getting the Meta/LinkedIn permissions for scheduling took around 1 month As the whole process took more time than expected, the waitlist of 300 that we managed to put together only converted by 10% (into free users). Please don’t make our mistakes and always keep your waitlist updated on what’s going on. Some challenges post-launch: Getting the right feedback and how to prioritise Getting users Monetising (yes - we’re bootstrapped) To get the best feedback we implemented some tracking (according to GDPR of course) on the platform and implemented Microsoft Clarity. The latter is a game-changer, if you have a SaaS and don’t use it you’re missing out. I wasn’t really into getting users as my co-founder handled that but it’s mainly manual and personalised LinkedIn outreach at the beginning and Reddit sharing about the progress, answering questions and getting some feedback at the same time. To monetise we realised we’re too common and there are 100+ other nice schedulers around so we’re now focusing on cracking the content creation side of AI (to be released next week 👀) as there’s much less competitors and it seems like that’s our users want. In the meantime of growing the company, we had to find a way to pay the bills as it’s two of us living together. So my co-founder started using the bubble skills gained and doing some freelance. He did around 7 platforms the last 6 months and we’re now just launching a bubble agency as a part of the main company to get your idea of a SaaS done in 30 days. That’s QuickMVP. It seemed like the right move to help other people (I met many non-technical founder looking for someone to bring their idea to life that didn’t cost $10k and was reliable) and include the AirMedia subscription in the package so let’s see how this next step plays out. Thanks for reading until here :)

Looking for a technical co-founder to build LinkedIn’s rival

How do you connect with likeminded people? You see the polished wins everywhere, but what about the messy drafts , the awkward pitches and the moments you’re not sure you’ve got it right? Problem: The whole idea of founding and starting a business can be super intimidating for some people, specially those who don’t know any founders personally, those who don’t have a large network, those who don’t have rich parents with large networks, those not inserted in an entrepreneurial culture like in the US for example (which is my case). Sometimes all you need is the right support network, and too see others do what you want, to know that it’s possible! Everyone has an “ultimate guide” to make 7 figures or build a business on YouTube but NO ONE shoes you the HOW, just the results… I’ve tried joining founder communities, LinkedIn ,Reddit … you name it. Most of these founder communities are inaccessible for regular people and often ask for you to have an already existing business with a min ARR… or their simply geography based and if you’re not in a certain area you can’t really participate… As of LinkedIn… full of empty AI generated posts about how some random dude raised $10m in 7 days. Okay Jonathan, but what about the HOW?? How did you write your first pitch? How many rejection calls did you get? What is an MVP? There simply isn’t a platform out there to document your founding journey and find inspiration within a community of people who are doing the same as you. What better way to feel motivated then to see someone actually document their process? Solution: I’m working on building a social media platform for aspiring/founders to connect through the RAW, UNFILTERED process of turning ideas into reality in REAL time. It’s all gonna be around the “building in public “ concept and content creation. Picture an instagram/tiktok profile where instead of seeing someone’s dog you see them documenting their founding process—from the moment they had the idea, to the moment they launched, you’re going to see the successes, the fails, the rejected calls, all documented through actual content and not some AI generated LinkedIn post. Imagine if you wanted to learn about how Steve Jobs started Apple , you could simply go through his profile on this app—exactly. To make sure all interactions are meaningful people would have to apply. It’s a truly curated community, with REAL people, building REAL things in REAL time, and not just tell us the story of how they did it… Audience: I’m targeting people who have a burning desire of building a business and early stage founders starting their founder journeys, that don’t have a support network and simply don’t know where to start. People who are tired of watching 30 min “ultimate guides “ on how to make it on YouTube from “business gurus” selling courses. People who haven’t reached the min ARR required to join an “exclusive “ founder a community. People who can’t simply just move to the US to get into the “exclusive” YC combinator. People who want to connect with real people building real things and not anonymous people on Reddit, or LinkedIn influencers again trying to promote their services. I believe in the idea because I’m also part of my audience. Have always wanted to start my own thing just never knew how to and where to find a community of likeminded people . I don’t know any founders myself, I come from a non-entrepreneurial society and I’d pay good money to access a community of REAL passionate founders building REAL things, in REAL time. This would be my first ever business, and I want to share my journey building it and hopefully inspire others to just start so I’ve created a mailing list to keep anyone interested in the project updated on my fails , learnings and successes. I’m not worried about “making it” but just “starting” and hopefully reach the right audience and inspire anyone to start whatever they have marinating in their thoughts. If you’re a founder struggling with staying consistent or an aspiring founder with an insane desire of starting and don’t know how to start, I’d love to get your feedback on what’s stopping you, your challenges starting out and what you’d find useful in such platform. And finally would this be something that interests you?? Feel free to subscribe to get new updates 🫶🏼 : https://mailchi.mp/037c56b89994/d-founder PS: casually looking for a technical co-founder

I built an AI Sales Copilot for Reps & Sales Engineers

I had this problem as a founder that it was really hard to transfer everything I knew about my product and industry to the reps & Sales Engineers I was hiring. This problem also exists for non-founders, say the SE manager or VP Sales ramping new teammates I solved this problem by building HeySam, the AI Sales Copilot that shadows your top reps and SEs on calls, learning the “tribal knowledge” around positioning, objection handling, and technical questions. Customize Sam with your documentation, Slack, and sales collateral to create your team's perfect sales copilot for: Sales calls with live help on objections and questions Call Intelligence to summarize meetings, identify competitive pressures, and update the CRM Meeting Prep with prospect briefs combining account research, past interactions, and competitive insights Contact Tracking to follow key relationships as people change roles. RFPs completed in minutes Slack responses to sales teams’ technical questions, freeing up SE and engineering time Docs and community for self-serve customer education You can start with any of the seven powerful use cases. One AI Agent. That’s Sam.

Side project: entrepreneurship app

Hey everyone, I’m building a side project: an app that helps aspiring entrepreneurs and small business owners with personalized lessons on topics like marketing, finance, and operations, powered by an AI assistant courses would be industry specific eventually maybe not first launch. The goal is to make entrepreneurship more accessible and inclusive through gamified learning, industry-specific lessons, and community tools like discussion posts and messaging for ongoing support. I have a working prototype, but now I need advice with marketing, pitching, and gathering interest. I’m also planning to start a podcast to gather insights from small business owners and entrepreneurs prior to launch. Looking for feedback on: Is this idea worth pursuing? How can I improve the concept or marketing? Would you be interested in listening to a podcast focused on entrepreneurship and small business? Any advice on how to engage users effectively through community tools like messaging and discussion posts?

How I went from $27 to $3K as a solopreneur still in a 9-5

My journey started back in November 2023. I was scrolling through Twitter and YouTube and saw a word that I had never come across before. Solopreneur. The word caught my eye. Mainly because I was pretty sure I knew what it meant even though it's not a word you'll find in the dictionary. I liked what it was describing. A solo entrepreneur. A one man business. It completely resonated with me. As a software engineer by trade I'm used to working alone, especially since the pandemic hit and we were forced to work remotely. See, I always wanted to ditch the 9-5 thing but thought that was too big and too scary for a single person to do. Surely you would need a lot of money to get started, right? Surely you would need investors? The whole concept seemed impossible to me. That was until I found all the success stories. I became obsessed with the concept of solopreneurship. As I went further down the rabbit hole I found people like Justin Welsh, Kieran Drew and Marc Louvion to name a few. All of whom have one person businesses making huge money every year. So I thought, if they can do it, why can't I? People like this have cleared the pathway for those looking to escape the 9-5 grind. I decided 2024 would be the year I try this out. My main goal for the year? Build a one man business, earn my first $ online and learn a sh\*t ton along the way. My main goal in general? Build my business to $100K per year, quit my 9-5 and live with freedom. From December 2023 to February 2024 I began brainstorming ideas. I was like a lost puppy looking for his ball. How on earth did people find good ideas? I began writing everything and anything that came to mind down in my notes app on my phone. By February I would have approximately 70 ideas. Each as weird and whacky as the other. I was skeptical though. If I went through all the trouble of building a product for one of these ideas how would I know if anyone would even be interested in using it? I got scared and took a break for a week. All these ideas seemed too big and the chance that they would take off into the atmosphere was slim (in my mind anyways). I was learning more and more about solopreneurship as the weeks went on so I decided to build a product centered around everything I was learning about. The idea was simple. Enter a business idea and use AI to give the user details about how to market it, who their target customers were, what to write on their landing page, etc. All for a measly $27 per use. I quickly built it and launched on March 3rd 2024. I posted about it on Indie Hackers, Reddit and Hacker News. I was so excited about the prospect of earning my first internet $! Surely everyone wanted to use my product! Nope...all I got was crickets. I was quickly brought back down to earth. That was until 5 days later. I looked at my phone and had a new Stripe notification! Cha-ching! My first internet $. What a feeling! That was goal number 1 complete. It would be another 6 days before I would get my second sale...and then another 15 days to get my third. It was an emotional rollercoaster. I went from feeling like quitting the 9-5 was actually possible to thinking that maybe the ups and downs aren't worth it. On one hand I had made my first internet dollar so I should my ecstatic, and don't get me wrong, I was but I wanted more. More validation that I could do this long term. By May I was starting to give up on the product. I had learned so much in the past few months about marketing, SEO, building an audience, etc. and I wanted to build something that I thought could have more success so I focused on one critical thing that I had learned about. What was it? Building a product that had SEO potential. A product that I knew hundreds of people were looking for. See this was my thinking - If I could find a keyword that people were searching for on Google hundreds/thousands of times every month and it was easy to rank high on search engines then I would go all in (in SEO land this equates to a Keyword that has a Keyword Difficulty of = 500). I began researching and found that the keyword "micro saas ideas" was being searched for around 600 times each month. Micro Saas was something that really interested me. It was perfect for solopreneurs. Small software products that 1 person could build. What's not to like if you're in the game of software and solopreneurship? Researching keywords like this became like a game for me. I was hooked. I was doing it every day, finding gems that were being searched for hundreds and thousands of times every month that still had potential. That's when I came up with my next product idea. I decided to create a database of Micro Saas Ideas all with this sort of SEO potential. See if you can build a product that you know people are looking for then that's all the validation you need. So I put this theory to the test. I created a database of Micro Saas Ideas with SEO Potential and launched it in June 2024. This time it was different. I made $700 in the first week of launching. A large contrast to my previous failed attempt at becoming the worlds greatest solopreneur. Since launch I have grown the product to $3K and I couldn't be happier. I know what you're saying, $3K isn't a lot. But it's validation. It's validation that I can earn $ online. Validation that I can grow a business and it gives me hope that one day I'll be able to quit that 9-5 grind. My plan is to keep growing the business. I expect there to be a few challenges up ahead but I'll tackle them as I go and learn from the failures and successes. I have a newsletter where I share Micro Saas Ideas with SEO potential every week which I'll leave below in the first comment. Feel free to come along for the ride. If not I hope this post brings you some value If you're thinking about starting as a solopreneur, stop thinking and start doing, you won't regret it.

I spent 6 months on a web app as a side project, and got 0 users. Here is my story.

Edit Thank you all so much for your time reading my story. Your support, feedback, criticism, and skepticism; all helped me a lot, and I couldn't appreciate it enough \^\_\^ I very rarely have stuff to post on Reddit, but I share how my project is going on, just random stuff, and memes on X. In case few might want to keep up 👀 TL;DR I spent 6 months on a tool that currently has 0 users. Below is what I learned during my journey, sharing because I believe most mistakes are easily avoidable. Do not overestimate your product and assume it will be an exception to fundamental principles. Principles are there for a reason. Always look for validation before you start. Avoid building products with a low money-to-effort ratio/in very competitive fields. Unless you have the means, you probably won't make it. Pick a problem space, pick your target audience, and talk to them before thinking about a solution. Identify and match their pain points. Only then should you think of a solution. If people are not overly excited or willing to pay in advance for a discounted price, it might be a sign to rethink. Sell one and only one feature at a time. Avoid everything else. If people don't pay for that one core feature, no secondary feature will change their mind. Always spend twice as much time marketing as you do building. You will not get users if they don't know it exists. Define success metrics ("1000 users in 3 months" or "$6000 in the account at the end of 6 months") before you start. If you don't meet them, strongly consider quitting the project. If you can't get enough users to keep going, nothing else matters. VALIDATION, VALIDATION, VALIDATION. Success is not random, but most of our first products will not make a success story. Know when to admit failure, and move on. Even if a product of yours doesn't succeed, what you learned during its journey will turn out to be invaluable for your future. My story So, this is the story of a product that I’ve been working on for the last 6 months. As it's the first product I’ve ever built, after watching you all from the sidelines, I have learned a lot, made many mistakes, and did only a few things right. Just sharing what I’ve learned and some insights from my journey so far. I hope that this post will help you avoid the mistakes I made — most of which I consider easily avoidable — while you enjoy reading it, and get to know me a little bit more 🤓. A slow start after many years Summ isn’t the first product I really wanted to build. Lacking enough dev skills to even get started was a huge blocker for so many years. In fact, the first product I would’ve LOVED to build was a smart personal shopping assistant. I had this idea 4 years ago; but with no GPT, no coding skills, no technical co-founder, I didn’t have the means to make it happen. I still do not know if such a tool exists and is good enough. All I wanted was a tool that could make data-based predictions about when to buy stuff (“buy a new toothpaste every three months”) and suggest physical products that I might need or be strongly interested in. AFAIK, Amazon famously still struggles with the second one. Fast-forward a few years, I learned the very basics of HTML, CSS, and Vanilla JS. Still was not there to build a product; but good enough to code my design portfolio from scratch. Yet, I couldn’t imagine myself building a product using Vanilla JS. I really hated it, I really sucked at it. So, back to tutorial hell, and to learn about this framework I just heard about: React.React introduced so many new concepts to me. “Thinking in React” is a phrase we heard a lot, and with quite good reasons. After some time, I was able to build very basic tutorial apps, both in React, and React Native; but I have to say that I really hated coding for mobile. At this point, I was already a fan of productivity apps, and had a concept for a time management assistant app in my design portfolio. So, why not build one? Surely, it must be easy, since every coding tutorial starts with a todo app. ❌ WRONG! Building a basic todo app is easy enough, but building one good enough for a place in the market was a challenge I took and failed. I wasted one month on that until I abandoned the project for good. Even if I continued working on it, as the productivity landscape is overly competitive, I wouldn’t be able to make enough money to cover costs, assuming I make any. Since I was (and still am) in between jobs, I decided to abandon the project. 👉 What I learned: Do not start projects with a low ratio of money to effort and time. Example: Even if I get 500 monthly users, 200 of which are paid users (unrealistically high number), assuming an average subscription fee of $5/m (such apps are quite cheap, mostly due to the high competition), it would make me around $1000 minus any occurring costs. Any founder with a product that has 500 active users should make more. Even if it was relatively successful, due to the high competition, I wouldn’t make any meaningful money. PS: I use Todoist today. Due to local pricing, I pay less than $2/m. There is no way I could beat this competitive pricing, let alone the app itself. But, somehow, with a project that wasn’t even functional — let alone being an MVP — I made my first Wi-Fi money: Someone decided that the domain I preemptively purchased is worth something. By this point, I had already abandoned the project, certainly wasn’t going to renew the domain, was looking for a FT job, and a new project that I could work on. And out of nowhere, someone hands me some free money — who am I not to take it? Of course, I took it. The domain is still unused, no idea why 🤔. Ngl, I still hate the fact that my first Wi-Fi money came from this. A new idea worth pursuing? Fast-forward some weeks now. Around March, I got this crazy idea of building an email productivity tool. We all use emails, yet we all hate them. So, this must be fixed. Everyone uses emails, in fact everyone HAS TO use emails. So, I just needed to build a tool and wait for people to come. This was all, really. After all, the problem space is huge, there is enough room for another product, everyone uses emails, no need for any further validation, right? ❌ WRONG ONCE AGAIN! We all hear from the greatest in the startup landscape that we must validate our ideas with real people, yet at least some of us (guilty here 🥸) think that our product will be hugely successful and prove them to be an exception. Few might, but most are not. I certainly wasn't. 👉 Lesson learned: Always validate your ideas with real people. Ask them how much they’d pay for such a tool (not if they would). Much better if they are willing to pay upfront for a discount, etc. But even this comes later, keep reading. I think the difference between “How much” and “If” is huge for two reasons: (1) By asking them for “How much”, you force them to think in a more realistic setting. (2) You will have a more realistic idea on your profit margins. Based on my competitive analysis, I already had a solution in my mind to improve our email usage standards and email productivity (huge mistake), but I did my best to learn about their problems regarding those without pushing the idea too hard. The idea is this: Generate concise email summaries with suggested actions, combine them into one email, and send it at their preferred times. Save as much as time the AI you end up with allows. After all, everyone loves to save time. So, what kind of validation did I seek for? Talked with only a few people around me about this crazy, internet-breaking idea. The responses I got were, now I see, mediocre; no one got excited about it, just said things along the lines of “Cool idea, OK”. So, any reasonable person in this situation would think “Okay, not might not be working”, right? Well, I did not. I assumed that they were the wrong audience for this product, and there was this magical land of user segments waiting eagerly for my product, yet unknowingly. To this day, I still have not reached this magical place. Perhaps, it didn’t exist in the first place. If I cannot find it, whether it exists or not doesn’t matter. I am certainly searching for it. 👉 What I should have done: Once I decide on a problem space (time management, email productivity, etc.), I should decide on my potential user segments, people who I plan to sell my product to. Then I should go talk to those people, ask them about their pains, then get to the problem-solving/ideation phase only later. ❗️ VALIDATION COMES FROM THE REALITY OUTSIDE. What validation looks like might change from product to product; but what invalidation looks like is more or less the same for every product. Nico Jeannen told me yesterday “validation = money in the account” on Twitter. This is the ultimate form of validation your product could get. If your product doesn’t make any money, then something is invalidated by reality: Your product, you, your idea, who knows? So, at this point, I knew a little bit of Python from spending some time in tutorial hell a few years ago, some HTML/CSS/JS, barely enough React to build a working app. React could work for this project, but I needed easy-to-implement server interactivity. Luckily, around this time, I got to know about this new gen of indie hackers, and learned (but didn’t truly understand) about their approach to indie hacking, and this library called Nextjs. How good Next.js still blows my mind. So, I was back to tutorial hell once again. But, this time, with a promise to myself: This is the last time I would visit tutorial hell. Time to start building this "ground-breaking idea" Learning the fundamentals of Next.js was easier than learning of React unsurprisingly. Yet, the first time I managed to run server actions on Next.js was one of the rarest moments that completely blew my mind. To this day, I reject the idea that it is something else than pure magic under its hood. Did I absolutely need Nextjs for this project though? I do not think so. Did it save me lots of time? Absolutely. Furthermore, learning Nextjs will certainly be quite helpful for other projects that I will be tackling in the future. Already got a few ideas that might be worth pursuing in the head in case I decide to abandon Summ in the future. Fast-forward few weeks again: So, at this stage, I had a barely working MVP-like product. Since the very beginning, I spent every free hour (and more) on this project as speed is essential. But, I am not so sure it was worth it to overwork in retrospect. Yet, I know I couldn’t help myself. Everything is going kinda smooth, so what’s the worst thing that could ever happen? Well, both Apple and Google announced their AIs (Apple Intelligence and Google Gemini, respectively) will have email summarization features for their products. Summarizing singular emails is no big deal, after all there were already so many similar products in the market. I still think that what truly matters is a frictionless user experience, and this is why I built this product in a certain way: You spend less than a few minutes setting up your account, and you get to enjoy your email summaries, without ever visiting its website again. This is still a very cool concept I really like a lot. So, at this point: I had no other idea that could be pursued, already spent too much time on this project. Do I quit or not? This was the question. Of course not. I just have to launch this product as quickly as possible. So, I did something right, a quite rare occurrence I might say: Re-planned my product, dropped everything secondary to the core feature immediately (save time on reading emails), tried launching it asap. 👉 Insight: Sell only one core feature at one time. Drop anything secondary to this core feature. Well, my primary occupation is product design. So one would expect that a product I build must have stellar design. I considered any considerable time spent on design at this stage would be simply wasted. I still think this is both true and wrong: True, because if your product’s core benefits suck, no one will care about your design. False, because if your design looks amateurish, no one will trust you and your product. So, I always targeted an average level design with it and the way this tool works made it quite easy as I had to design only 2 primary pages: Landing page and user portal (which has only settings and analytics pages). However, even though I knew spending time on design was not worth much of my time, I got a bit “greedy”: In fact, I redesigned those pages three times, and still ended up with a so-so design that I am not proud of. 👉 What I would do differently: Unless absolutely necessary, only one iteration per stage as long as it works. This, in my mind, applies to everything. If your product’s A feature works, then no need to rewrite it from scratch for any reason, or even refactor it. When your product becomes a success, and you absolutely need that part of your codebase to be written, do so, but only then. Ready to launch, now is th etime for some marketing, right? By July 26, I already had a “launchable” product that barely works (I marked this date on a Notion docs, this is how I know). Yet, I had spent almost no time on marketing, sales, whatever. After all, “You build and they will come”. Did I know that I needed marketing? Of course I did, but knowingly didn’t. Why, you might ask. Well, from my perspective, it had to be a dev-heavy product; meaning that you spend most of your time on developing it, mostly coding skills. But, this is simply wrong. As a rule of thumb, as noted by one of the greatests, Marc Louvion, you should spend at least twice of the building time on marketing. ❗️ Time spent on building \* 2 people don’t know your product > they don’t use your product > you don’t get users > you don’t make money Easy as that. Following the same reasoning, a slightly different approach to planning a project is possible. Determine an approximate time to complete the project with a high level project plan. Let’s say 6 months. By the reasoning above, 2 months should go into building, and 4 into marketing. If you need 4 months for building instead of 2, then you need 8 months of marketing, which makes the time to complete the project 12 months. If you don’t have that much time, then quit the project. When does a project count as completed? Well, in reality, never. But, I think we have to define success conditions even before we start for indie projects and startups; so we know when to quit when they are not met. A success condition could look like “Make $6000 in 12 months” or “Have 3000 users in 6 months”. It all depends on the project. But, once you set it, it should be set in stone: You don’t change it unless absolutely necessary. I suspect there are few principles that make a solopreneur successful; and knowing when to quit and when to continue is definitely one of them. Marc Louvion is famously known for his success, but he got there after failing so many projects. To my knowledge, the same applies to Nico Jeannen, Pieter Levels, or almost everyone as well. ❗️ Determining when to continue even before you start will definitely help in the long run. A half-aed launch Time-leap again. Around mid August, I “soft launched” my product. By soft launch, I mean lazy marketing. Just tweeting about it, posting it on free directories. Did I get any traffic? Surely I did. Did I get any users? Nope. Only after this time, it hit me: “Either something is wrong with me, or with this product” Marketing might be a much bigger factor for a project’s success after all. Even though I get some traffic, not convincing enough for people to sign up even for a free trial. The product was still perfect in my eyes at the time (well, still is ^(\_),) so the right people are not finding my product, I thought. Then, a question that I should have been asking at the very first place, one that could prevent all these, comes to my mind: “How do even people search for such tools?” If we are to consider this whole journey of me and my so-far-failed product to be an already destined failure, one metric suffices to show why. Search volume: 30. Even if people have such a pain point, they are not looking for email summaries. So, almost no organic traffic coming from Google. But, as a person who did zero marketing on this or any product, who has zero marketing knowledge, who doesn’t have an audience on social media, there is not much I could do. Finally, it was time to give up. Or not… In my eyes, the most important element that makes a founder (solo or not) successful (this, I am not by any means) is to solve problems. ❗️ So, the problem was this: “People are not finding my product by organic search” How do I make sure I get some organic traffic and gets more visibility? Learn digital marketing and SEO as much as I can within very limited time. Thankfully, without spending much time, I came across Neil Patel's YT channel, and as I said many times, it is an absolute gold mine. I learned a lot, especially about the fundamentals, and surely it will be fruitful; but there is no magic trick that could make people visit your website. SEO certainly helps, but only when people are looking for your keywords. However, it is truly a magical solution to get in touch with REAL people that are in your user segments: 👉 Understand your pains, understand their problems, help them to solve them via building products. I did not do this so far, have to admit. But, in case you would like to have a chat about your email usage, and email productivity, just get in touch; I’d be delighted to hear about them. Getting ready for a ProductHunt launch The date was Sept 1. And I unlocked an impossible achievement: Running out of Supabase’s free plan’s Egres limit while having zero users. I was already considering moving out of their Cloud server and managing a Supabase CLI service on my Hetzner VPS for some time; but never ever suspected that I would have to do this quickly. The cheapest plan Supabase offers is $25/month; yet, at that point, I am in between jobs for such a long time, basically broke, and could barely afford that price. One or two months could be okay, but why pay for it if I will eventually move out of their Cloud service? So, instead of paying $25, I spent two days migrating out of Supabase Cloud. Worth my time? Definitely not. But, when you are broke, you gotta do stupid things. This was the first time that I felt lucky to have zero users: I have no idea how I would manage this migration if I had any. I think this is one of the core tenets of an indie hacker: Controlling their own environment. I can’t remember whose quote this is, but I suspect it was Naval: Entrepreneurs have an almost pathological need to control their own fate. They will take any suffering if they can be in charge of their destiny, and not have it in somebody else’s hands. What’s truly scary is, at least in my case, we make people around us suffer at the expense of our attempting to control our own fates. I know this period has been quite hard on my wife as well, as I neglected her quite a bit, but sadly, I know that this will happen again. It is something that I can barely help with. Still, so sorry. After working the last two weeks on a ProductHunt Launch, I finally launched it this Tuesday. Zero ranking, zero new users, but 36 kind people upvoted my product, and many commented and provided invaluable feedback. I couldn't be more grateful for each one of them 🙏. Considering all these, what lies in the future of Summ though? I have no idea, to be honest. On one hand, I have zero users, have no job, no income. So, I need a way to make money asap. On the other hand, the whole idea of it revolves around one core premise (not an assumption) that I am not so willing to share; and I couldn’t have more trust in it. This might not be the best iteration of it, however I certainly believe that email usage is one of the best problem spaces one could work on. 👉 But, one thing is for certain: I need to get in touch with people, and talk with them about this product I built so far. In fact, this is the only item on my agenda. Nothing else will save my brainchild <3. Below are some other insights and notes that I got during my journey; as they do not 100% fit into this story, I think it is more suitable to list them here. I hope you enjoyed reading this. Give Summ a try, it comes with a generous free trial, no credit card required. Some additional notes and insights: Project planning is one of the most underestimated skills for solopreneurs. It saves you enormous time, and helps you to keep your focus up. Building B2B products beats building B2C products. Businesses are very willing to pay big bucks if your product helps them. On the other hand, spending a few hours per user who would pay $5/m probably is not worth your time. It doesn’t matter how brilliant your product is if no one uses it. If you cannot sell a product in a certain category/niche (or do not know how to sell it), it might be a good idea not to start a project in it. Going after new ideas and ventures is quite risky, especially if you don’t know how to market it. On the other hand, an already established category means that there is already demand. Whether this demand is sufficient or not is another issue. As long as there is enough demand for your product to fit in, any category/niche is good. Some might be better, some might be worse. Unless you are going hardcore B2B, you will need people to find your product by means of organic search. Always conduct thorough keyword research as soon as possible.

How me and my team made 15+ apps and not made a single sale in 2023

Hey, my name is Michael, I am in Auckland NZ. This year was the official beginning of my adult life. I graduated from university and started a full-time job. I’ve also really dug into indiehacking/bootstrapping and started 15 projects (and it will be at least 17 before the year ends). I think I’ve learned a lot but I consciously repeated mistakes. Upto (Nov) Discord Statuses + Your Location + Facebook Poke https://preview.redd.it/4nqt7tp2tf5c1.png?width=572&format=png&auto=webp&s=b0223484bc54b45b5c65e0b1afd0dc52f9c02ad1 This was the end of uni, I often messaged (and got messaged) requests of status and location to (and from my) friends. I thought, what if we make a social app that’s super basic and all it does is show you where your friends are? To differentiate from snap maps and others we wanted something with more privacy where you select the location. However, never finished the codebase or launched it. This is because I slowly started to realize that B2C (especially social networks) are way too hard to make into an actual business and the story with Fistbump would repeat itself. However, this decision not to launch it almost launched a curse on our team. From that point, we permitted ourselves to abandon projects even before launching. Lessons: Don’t do social networks if your goal is 10k MRR ASAP. If you build something to 90% competition ship it or you will think it’s okay to abandon projects Insight Bites (Nov) Youtube Summarizer Extension &#x200B; https://preview.redd.it/h6drqej4tf5c1.jpg?width=800&format=pjpg&auto=webp&s=0f211456c390ac06f4fcb54aa51f9d50b0826658 Right after Upto, we started ideating and conveniently the biggest revolution in the recent history of tech was released → GPT. We instantly began ideating. The first problem we chose to use AI for is to summarize YouTube videos. Comical. Nevertheless, I am convinced we have had the best UX because you could right-click on a video to get a slideshow of insights instead of how everyone else did it. We dropped it because there was too much competition and unit economics didn’t work out (and it was a B2C). PodPigeon (Dec) Podcast → Tweet Threads https://preview.redd.it/0ukge245tf5c1.png?width=2498&format=png&auto=webp&s=23303e1cab330578a3d25cd688fa67aa3b97fb60 Then we thought, to make unit economics work we need to make this worthwhile for podcasters. This is when I got into Twitter and started seeing people summarize podcasts. Then I thought, what if we make something that converts a podcast into tweets? This was probably one of the most important projects because it connected me with Jason and Jonaed, both of whom I regularly stay in contact with and are my go-to experts on ideas related to content creation. Jonaed was even willing to buy Podpigeon and was using it on his own time. However, the unit economics still didn’t work out (and we got excited about other things). Furthermore, we got scared of the competition because I found 1 - 2 other people who did similar things poorly. This was probably the biggest mistake we’ve made. Very similar projects made 10k MRR and more, launching later than we did. We didn’t have a coherent product vision, we didn’t understand the customer well enough, and we had a bad outlook on competition and a myriad of other things. Lessons: I already made another post about the importance of outlook on competition. Do not quit just because there are competitors or just because you can’t be 10x better. Indiehackers and Bootstrappers (or even startups) need to differentiate in the market, which can be via product (UX/UI), distribution, or both. Asking Ace Intro.co + Crowdsharing &#x200B; https://preview.redd.it/0hu2tt16tf5c1.jpg?width=1456&format=pjpg&auto=webp&s=3d397568ef2331e78198d64fafc1a701a3e75999 As I got into Twitter, I wanted to chat with some people I saw there. However, they were really expensive. I thought, what if we made some kind of crowdfunding service for other entrepreneurs to get a private lecture from their idols? It seemed to make a lot of sense on paper. It was solving a problem (validated via the fact that Intro.co is a thing and making things cheaper and accessible is a solid ground to stand on), we understood the market (or so we thought), and it could monetize relatively quickly. However, after 1-2 posts on Reddit and Indiehackers, we quickly learned three things. Firstly, no one cares. Secondly, even if they do, they think they can get the same information for free online. Thirdly, the reasons before are bad because for the first point → we barely talked to people, and for the second people → we barely talked to the wrong people. However, at least we didn’t code anything this time and tried to validate via a landing page. Lessons Don’t give up after 1 Redditor says “I don’t need this” Don’t be scared to choose successful people as your audience. Clarito Journaling with AI analyzer https://preview.redd.it/8ria2wq6tf5c1.jpg?width=1108&format=pjpg&auto=webp&s=586ec28ae75003d9f71b4af2520b748d53dd2854 Clarito is a classic problem all amateur entrepreneurs have. It’s where you lie to yourself that you have a real problem and therefore is validated but when your team asks you how much you would pay you say I guess you will pay, maybe, like 5 bucks a month…? Turns out, you’d have to pay me to use our own product lol. We sent it off to a few friends and posted on some forums, but never really got anything tangible and decided to move away. Honestly, a lot of it is us in our own heads. We say the market is too saturated, it’ll be hard to monetize, it’s B2C, etc. Lessons: You use the Mom Test on other people. You have to do it yourself as well. However, recognizing that the Mom Test requires a lot of creativity in its investigation because knowing what questions to ask can determine the outcome of the validation. I asked myself “Do I journal” but I didn’t ask myself “How often do I want GPT to chyme in on my reflections”. Which was practically never. That being said I think with the right audience and distribution, this product can work. I just don’t know (let alone care) about the audience that much (and I thought I was one of them)/ Horns & Claw Scrapes financial news texts you whether you should buy/sell the stock (news sentiment analysis) &#x200B; https://preview.redd.it/gvfxdgc7tf5c1.jpg?width=1287&format=pjpg&auto=webp&s=63977bbc33fe74147b1f72913cefee4a9ebec9c2 This one we didn’t even bother launching. Probably something internal in the team and also seemed too good to be true (because if this works, doesn’t that just make us ultra-rich fast?). I saw a similar tool making 10k MRR so I guess I was wrong. Lessons: This one was pretty much just us getting into our heads. I declared that without an audience it would be impossible to ship this product and we needed to start a YouTube channel. Lol, and we did. And we couldn’t even film for 1 minute. I made bold statements like “We will commit to this for at least 1 year no matter what”. Learnery Make courses about any subject https://preview.redd.it/1nw6z448tf5c1.jpg?width=1112&format=pjpg&auto=webp&s=f2c73e8af23b0a6c3747a81e785960d4004feb48 This is probably the most “successful” project we’ve made. It grew from a couple of dozen to a couple of hundred users. It has 11 buy events for $9.99 LTD (we couldn’t be bothered connecting Stripe because we thought no one would buy it anyway). However what got us discouraged from seriously pursuing it more is, that this has very low defensibility, “Why wouldn’t someone just use chatGPT?” and it’s B2C so it’s hard to monetize. I used it myself for a month or so but then stopped. I don’t think it’s the app, I think the act of learning a concept from scratch isn’t something you do constantly in the way Learnery delivers it (ie course). I saw a bunch of similar apps that look like Ass make like 10k MRR. Lessons: Don’t do B2C, or if you do, do it properly Don’t just Mixpanel the buy button, connect your Stripe otherwise, it doesn’t feel real and you won’t get momentum. I doubt anyone (even me) will make this mistake again. I live in my GPT bubble where I make assumptions that everyone uses GPT the same way and as much as I do. In reality, the argument that this has low defensibility against GPT is invalid. Platforms that deliver a differentiated UX from ChatGPT to audiences who are not tightly integrated into the habit of using ChatGPT (which is like - everyone except for SOME tech evangelists). CuriosityFM Make podcasts about any subject https://preview.redd.it/zmosrcp8tf5c1.jpg?width=638&format=pjpg&auto=webp&s=d04ddffabef9050050b0d87939273cc96a8637dc This was our attempt at making Learnery more unique and more differentiated from chatGPT. We never really launched it. The unit economics didn’t work out and it was actually pretty boring to listen to, I don’t think I even fully listened to one 15-minute episode. I think this wasn’t that bad, it taught us more about ElevenLabs and voice AI. It took us maybe only 2-3 days to build so I think building to learn a new groundbreaking technology is fine. SleepyTale Make children’s bedtime stories https://preview.redd.it/14ue9nm9tf5c1.jpg?width=807&format=pjpg&auto=webp&s=267e18ec6f9270e6d1d11564b38136fa524966a1 My 8-year-old sister gave me that idea. She was too scared of making tea and I was curious about how she’d react if she heard a bedtime story about that exact scenario with the moral that I wanted her to absorb (which is that you shouldn’t be scared to try new things ie stop asking me to make your tea and do it yourself, it’s not that hard. You could say I went full Goebbels on her). Zane messaged a bunch of parents on Facebook but no one really cared. We showed this to one Lady at the place we worked from at Uni and she was impressed and wanted to show it to her kids but we already turned off our ElevenLabs subscription. Lessons: However, the truth behind this is beyond just “you need to be able to distribute”. It’s that you have to care about the audience. I don’t particularly want to build products for kids and parents. I am far away from that audience because I am neither a kid anymore nor going to be a parent anytime soon, and my sister still asked me to make her tea so the story didn’t work. I think it’s important to ask yourself whether you care about the audience. The way you answer that even when you are in full bias mode is, do you engage with them? Are you interested in what’s happening in their communities? Are you friends with them? Etc. User Survey Analyzer Big User Survey → GPT → Insights Report Me and my coworker were chatting about AI when he asked me to help him analyze a massive survey for him. I thought that was some pretty decent validation. Someone in an actual company asking for help. Lessons Market research is important but moving fast is also important. Ie building momentum. Also don’t revolve around 1 user. This has been a problem in multiple projects. Finding as many users as possible in the beginning to talk to is key. Otherwise, you are just waiting for 1 person to get back to you. AutoI18N Automated Internationalization of the codebase for webapps This one I might still do. It’s hard to find a solid distribution strategy. However, the idea came from me having to do it at my day job. It seems a solid problem. I’d say it’s validated and has some good players already. The key will be differentiation via the simplicity of UX and distribution (which means a slightly different audience). In the backlog for now because I don’t care about the problem or the audience that much. Documate - Part 1 Converts complex PDFs into Excel https://preview.redd.it/8b45k9katf5c1.jpg?width=1344&format=pjpg&auto=webp&s=57324b8720eb22782e28794d2db674b073193995 My mom needed to convert a catalog of furniture into an inventory which took her 3 full days of data entry. I automated it for her and thought this could have a big impact but there was no distribution because there was no ICP. We tried to find the ideal customers by talking to a bunch of different demographics but I flew to Kazakhstan for a holiday and so this kind of fizzled out. I am not writing this blog post linearity, this is my 2nd hour and I am tired and don’t want to finish this later so I don’t even know what lessons I learned. Figmatic Marketplace of high-quality Figma mockups of real apps https://preview.redd.it/h13yv45btf5c1.jpg?width=873&format=pjpg&auto=webp&s=aaa2896aeac2f22e9b7d9eed98c28bb8a2d2cdf1 This was a collab between me and my friend Alex. It was the classic Clarito where we both thought we had this problem and would pay to fix it. In reality, this is a vitamin. Neither I, nor I doubt Alex have thought of this as soon as we bought the domain. We posted it on Gumroad, sent it to a bunch of forums, and called it a day. Same issue as almost all the other ones. No distribution strategy. However, apps like Mobin show us that this concept is indeed profitable but it takes time. It needs SEO. It needs a community. None of those things, me and Alex had or was interested in. However shortly after HTML → Figma came out and it’s the best plugin. Maybe that should’ve been the idea. Podcast → Course Turns Podcaster’s episodes into a course This one I got baited by Jason :P I described to him the idea of repurposing his content for a course. He told me this was epic and he would pay. Then after I sent him the demo, he never checked it out. Anyhow during the development, we realized that doesn’t actually work because A podcast doesn’t have the correct format for the course, the most you can extract are concepts and ideas, seldom explanations. Most creators want video-based courses to be hosted on Kajabi or Udemy Another lesson is that when you pitch something to a user, what you articulate is a platform or a process, they imagine an outcome. However, the end result of your platform can be a very different outcome to what they had in mind and there is even a chance that what they want is not possible. You need to understand really well what the outcome looks like before you design the process. This is a classic problem where we thought of the solution before the problem. Yes, the problem exists. Podcasters want to make courses. However, if you really understand what they want, you can see how repurposing a podcast isn’t the best way to get there. However I only really spoke to 1-2 podcasters about this so making conclusions is dangerous for this can just be another asking ace mistake with the Redditor. Documate Part 2 Same concept as before but now I want to run some ads. We’ll see what happens. https://preview.redd.it/xb3npj0ctf5c1.jpg?width=1456&format=pjpg&auto=webp&s=3cd4884a29fd11d870d010a2677b585551c49193 In conclusion https://preview.redd.it/2zrldc9dtf5c1.jpg?width=1840&format=pjpg&auto=webp&s=2b3105073e752ad41c23f205dbd1ea046c1da7ff It doesn’t actually matter that much whether you choose to do a B2C, or a social network or focus on growing your audience. All of these can make you successful. What’s important is that you choose. If I had to summarize my 2023 in one word it’s indecision. Most of these projects succeeded for other people, nothing was as fundamentally wrong about them as I proclaimed. In reality that itself was an excuse. New ideas seduce, and it is a form of discipline to commit to a single project for a respectful amount of time. https://preview.redd.it/zy9a2vzdtf5c1.jpg?width=1456&format=pjpg&auto=webp&s=901c621227bba0feb4efdb39142f66ab2ebb86fe Distribution is not just posting on Indiehackers and Reddit. It’s an actual strategy and you should think of it as soon as you think of the idea, even before the Figma designs. I like how Denis Shatalin taught me. You have to build a pipeline. That means a reliable way to get leads, launch campaigns at them, close deals, learn from them, and optimize. Whenever I get an idea now I always try to ask myself “Where can I find 1000s leads in one day?” If there is no good answer, this is not a good project to do now. &#x200B; https://preview.redd.it/2boh3fpetf5c1.jpg?width=1456&format=pjpg&auto=webp&s=1c0d5d7b000716fcbbb00cbad495e8b61e25be66 Talk to users before doing anything. Jumping on designing and coding to make your idea a reality is a satisfying activity in the short term. Especially for me, I like to create for the sake of creation. However, it is so important to understand the market, understand the audience, understand the distribution. There are a lot of things to understand before coding. https://preview.redd.it/lv8tt96ftf5c1.jpg?width=1456&format=pjpg&auto=webp&s=6c8735aa6ad795f216ff9ddfa2341712e8277724 Get out of your own head. The real reason we dropped so many projects is that we got into our own heads. We let the negative thoughts creep in and kill all the optimism. I am really good at coming up with excuses to start a project. However, I am equally as good at coming up with reasons to kill a project. And so you have this yin and yang of starting and stopping. Building momentum and not burning out. I can say with certainty my team ran out of juice this year. We lost momentum so many times we got burnt out towards the end. Realizing that the project itself has momentum is important. User feedback and sales bring momentum. Building also creates momentum but unless it is matched with an equal force of impact, it can stomp the project down. That is why so many of our projects died quickly after we launched. The smarter approach is to do things that have a low investment of momentum (like talking to users) but result in high impact (sales or feedback). Yes, that means the project can get invalidated which makes it more short-lived than if we built it first, but it preserves team life energy. At the end of 2023 here is a single sentence I am making about how I think one becomes a successful indiehacker. One becomes a successful Indiehacker when one starts to solve pain-killer problems in the market they understand, for an audience they care about and consistently engage with for a long enough timeframe. Therefore an unsuccessful Indiehacker in a single sentence is An unsuccessful Indiehacker constantly enters new markets they don’t understand to build solutions for people whose problems they don’t care about, in a timeframe that is shorter than than the time they spent thinking about distribution. However, an important note to be made. Life is not just about indiehacking. It’s about learning and having fun. In the human world, the best journey isn’t the one that gets you the fastest to your goals but the one you enjoy the most. I enjoyed making those silly little projects and although I do not regret them, I will not repeat the same mistakes in 2024. But while it’s still 2023, I have 2 more projects I want to do :) EDIT: For Devs, frontend is always react with vite (ts) and backend is either node with express (ts) or python. For DB either Postgres or mongo (usually Prisma for ORM). For deployment all of it is on AWS (S3, EC2). In terms of libraries/APIs Whisper.cpp is best open source for transcription Obviously the gpt apis Eleven labs for voice related stuff And other random stuff here and there

I built an app to find who’s interested in your app by monitoring social media

Hi everyone! I hope you’re all doing great folks! I’d love to know your thoughts about what I’ve been working on recently! 🙏 If you’re busy or wanna see the app scroll to the bottom to see the video demo, otherwise, continue reading. Very brief presentation of myself first: I’m Marvin, and I live in Florence, Italy, 👋 This year I decided to go all-in on solopreneurship, I’ve been in tech as Software Engineer first, and then in Engineering Leadership for 10+ years, I’ve always worked in startups, except for last year, when I was the Director of Engineering at the Linux Foundation. Follow me on X or subscribe to my newsletter if you’re curious about this journey. The vision Most founders start building digital startups because they love crafting and being impactful by helping other people or companies. First-time founders then face reality when they realize that nailing distribution is key. All other founders already learned this, most likely the hard way. The outcome is the same: a great product will unlikely succeed without great distribution. Letting people know about your product should be easier and not an unfair advantage. The following meme is so true, but also quite sad. I wanna help this to change by easing the marketing and distribution part. https://preview.redd.it/g52pz46upqtd1.png?width=679&format=png&auto=webp&s=cf8398a3592f25c05c396bb2ff5d028331a36315 The story behind Distribution is a huge space: lead generation, demand generation, content marketing, social media marketing, cold outreach, etc. I cannot solve everything altogether. A few months ago I was checking the traffic to a job board I own (NextCommit). That's when I noticed that the “baseline” traffic increased by almost 10x. 🤯 I started investigating why. I realized that the monthly traffic from Reddit increased from 10-ish to 350+. Yeah, the job board doesn’t get much traffic in total, but this was an interesting finding. After digging more, it seems that all that increase came from a single Reddit comment: https://www.reddit.com/r/remotework/comments/1crwcei/comment/l5fb1yy/ This is the moment when I realized two things: It’s cool that someone quoted it! Engaging with people on Reddit, even just through comments, can be VERY powerful. And this was just one single comment! https://preview.redd.it/nhxcv4h2qqtd1.png?width=1192&format=png&auto=webp&s=d31905f56ae59426108ddbb61f2d6b668eedf27a Some weeks later I started noticing a few apps like ReplyGuy. These were automatically engaging with Reddit posts identified through keywords. I decided to sign up for the free plan of ReplyGuy to know more, but many things didn’t convince me: One of the keywords I used for my job board was “remote” and that caused a lot of false positives, The generated replies were good as a kickstart, but most of the time they needed to be tuned to sound more like me. The latter is expected. In the end, the platform doesn’t know me, doesn’t know my opinions, doesn’t know my story, etc.. The only valuable feature left for me was identifying the posts, but that also didn’t work well for me due to false positives. I ended up using it after only 15 minutes. I’m not saying they did a poor job, but it was not working well for me. In the end, the product got quite some traction, so it helped confirm there’s interest in that kind of tool. What bothered me was the combination of auto-replies that felt non-authentic. It’s not that I’m against bots, automation is becoming more common, and people are getting used to it. But in this context, I believe bots should act as an extension of ourselves, enhancing our interactions rather than just generating generic responses (like tools such as HeyGen, Synthesia, PhotoAI). I’m not there yet with my app, but a lot can be done. I'd love to reach the point where a user feels confident to automate the replies because they sound as written by themselves. I then decided to start from the same space, helping engage with Reddit posts, for these reasons: I experienced myself that it can be impactful, It aligns with my vision to ease distribution, Some competitors validated that there’s interest in this specific feature and I could use it as a starting point, I’m confident I can provide a better experience even with what I already have. The current state The product currently enables you to: Create multiple projects and assign keywords, Find the posts that are relevant for engagement using a fuzzy match of keywords and post-filtered using AI to avoid false positives, Provide an analysis of each post to assess the best way to engage, Generate a helpful reply that you’d need to review and post. So currently the product is more on the demand gen side, but this is just the beginning. I’m speaking with people from Marketing, Sales, RevOps, and Growth agencies to better understand their lives, struggles, and pain points. This will help me ensure that I build a product that enables them to help users find the products they need. I’m currently looking for up to 10 people to join the closed beta for free. If you’re interested in joining or to get notified once generally available you can do it here! https://tally.so/r/3XYbj4 After the closed beta, I will start onboarding people in batches. This will let me gather feedback, iterate, and provide a great experience to everyone aligned with my vision. I’m not going to add auto-reply unless the conditions I explained above are met or someone convinces me there’s a good reason for doing so. Each batch will probably get bigger with an increasing price until I’m confident about making it generally available. The next steps The next steps will depend on the feedback I get from the customers and the learnings from the discovery calls I’m having. I will talk about future developments in another update, but I have some ideas already. Check out the demo video below, and I'd love to hear your thoughts! ❤️ Oh and BTW, the app is called HaveYouHeard! https://reddit.com/link/1fzsnrd/video/34lat9snpqtd1/player This is the link to Loom in case the upload doesn't work: https://www.loom.com/share/460c4033b1f94e3bb5e1d081a05eedfd

How I Automated Amazon Affiliate Marketing: A Developer's Journey

From Manual Labor to 1000x Efficiency As a developer who ventured into affiliate marketing, I discovered a significant gap between technical possibilities and current practices. This revelation led me to create AutoPin, a tool that's now helping hundreds of affiliate marketers reclaim their time. The Problem: A Time-Consuming Reality Every affiliate marketer knows this scenario: you spend hours copying and pasting links, checking prices, and updating product information. I found myself dedicating 4-6 hours daily to these repetitive tasks. As a programmer, this felt fundamentally wrong. The typical affiliate marketing workflow looked like this: Find promising products Generate affiliate links one by one Monitor price changes manually Check product availability regularly Update content when things change Repeat this process daily This manual process had several critical issues: Time Waste: 20-30 hours weekly on repetitive tasks Missed Opportunities: Unable to scale beyond 100 products Human Error: Inevitable mistakes in manual updates Delayed Updates: Lost commissions due to outdated information The Solution: Building AutoPin After three months of development and six months of testing, I created a system that could: Generate hundreds of affiliate links in minutes Monitor price changes automatically Update product availability in real-time Export data in multiple formats Scale infinitely without additional effort Real Results, Real Impact The impact was immediate and significant: 📊 Efficiency Metrics: Link generation: From 2 minutes per link to 0.1 seconds Monitoring capacity: From 50 to 5000+ products Update frequency: From daily to real-time Error rate: Reduced by 99.9% 💡 User Success Stories: "Increased my product portfolio by 10x without adding work hours" "Revenue grew 300% in the first month" "Finally able to focus on content creation instead of link management" Technical Insights The system architecture focuses on three core components: Data Extraction Engine Efficient web scraping Rate limiting and proxy management Data validation and cleaning Real-time Monitoring System Websocket connections for instant updates Queue management for large-scale monitoring Smart scheduling based on price volatility Export Framework Multiple format support (CSV, HTML, Markdown) Custom templating engine Batch processing capabilities The Future of Affiliate Marketing Automation We're currently developing AI capabilities to: Generate product descriptions automatically Optimize link placement for conversion Predict price trends and best promotion times Create content variations for different platforms Key Learnings Automation is Essential The future of affiliate marketing lies in automation. Manual processes simply can't compete with automated systems in terms of efficiency and accuracy. Focus on Value Creation When marketers spend less time on repetitive tasks, they can focus on strategy and content quality. Scale Matters With automation, the difference between managing 10 products and 1000 products becomes minimal. Getting Started If you're an affiliate marketer spending hours on manual tasks, it's time to automate. Here's what you can do: Analyze your current workflow Identify repetitive tasks Start with basic automation Scale gradually Monitor and optimize Conclusion The transformation from manual to automated affiliate marketing isn't just about saving time—it's about unlocking potential. When you remove the tedious aspects of affiliate marketing, you create space for creativity, strategy, and growth. Want to experience the difference? Visit AutoPin at autopin.pro and join the automation revolution. Remember: The best time to automate was yesterday. The second best time is now. About the Author: A developer turned affiliate marketer who believes in the power of automation to transform digital marketing. #AffiliateMarketing #Automation #Programming #DigitalMarketing #SaaS #ProductivityTools

How to get your first 10 customers with cold email

Cold email is an insane channel for growth, especially for bootstrapped startups as it's very low cost but completely scalable. Yet there's a huge difference between blind cold emailing and crafting personalized outreach for select individuals. The latter is a legit channel which makes many businesses scale in short amounts of time (i.e. see Alex Hormozi’s ‘$100 Million Dollar Offer’). My goal here is to help other founders do what I did but quicker. So you can learn faster. And then teach me something new too. These are the step-by-step lessons I've learnt as a bootstrapped founder, showing you how to use cold email to get your first customers: Find your leads Write engaging email copy Personalize your outreach Send emails Scale up Find your leads This is a key step. Once you figure out exactly who you want to target and where to find them, you'll be printing money. There's a few different ways to go about finding valuable leads. The secret? Keep testing different approaches until you strike gold. First, dedicate some time every day to find and organise leads. Then, keep an eye on your numbers and bounce rates. If something's not working, switch it up. Stick with what's bringing in results and ditch what's not. It's all about staying flexible and learning as you go. Apollo.io is a great starting point as an effective lead source. Their tool allows you to specify filters including job titles, location, company size, industry, keywords, technologies, and revenue. Get specific with your searches to find your ideal customers. Once you have some results you can save and export them, you'll get a list of contact information including name, email, company, LinkedIn, ready to be verified and used. LinkedIn Sales Navigator is another good source. You can either do manual searches or use a scraper to automate the process. The scrapers I'd recommend checking out are FindyMail and Evaboot. As with Apollo, it's best to get very specific with your targeting so you know the prospect will be interested in your offer. BuiltWith is more expensive but ideal if you're targeting competitors. With BuiltWith you can build lists based on what technologies companies are using. For example if you're selling a Shopify app, you'd want to know websites or stores using Shopify, and reach out to them. The best lead sources will always be those that haven't been contacted a lot in the past. If you are able to find places where your target audience uniquely hangs out, and you can get their company website domains, they have the potential to be scrapped, and you have a way to personalize like "I spotted your comment on XYZ website". Once you've got your leads, keep them organized. Set up folders for different niches, countries, company sizes, so you can review what works and what doesn't. One more thing – before you start firing off emails, make sure those addresses are verified. Always use an email verifier to clean up your list and avoid bounces that may affect your sending reputation, and land you in the spam folder. I use Neverbounce for this but there are other tools available. Write engaging email copy Writing a good copy that gets replies is difficult, it changes depending on your offer/audience and nobody knows what's going to work. The best approach is to keep testing different targeting and messaging until you find what works. However, there are some key rules to stick to that I've outlined. For the subject line, keep it short and personalized. Try to write something that sparks interest, and mention the recipients name: Thought you’d like this {{first name}} {{firstName}} - quick question For the email body it's best to use a framework of personalization, offer, then call to action. Personalization is an entire subject in its own right, which I've covered below. In short, a personalized email opener is the best way to grab their attention, and let them know the email is relevant to them and to keep reading. Take it from Alex Hormozi and his $100M Offers playbook – your offer is very important to get right. Make sure your offer hits the mark for your target audience, and get as specific as possible. For example: I built a SaaS shopify app for small ecommerce businesses selling apparel that doubles your revenue in 60-days or your money back. We developed a cold email personalization tool for lead generation agencies that saves hundreds of hours, and can 3x your reply rate. Lastly, the CTA. The goal here isn't to get sign-ups directly from your first email. It's better to ask a brief question about whether the prospect would be interested in learning more. Something very low friction, that warrants a response. Some examples might include: Would you be interested in learning more about this? Can we connect a bit more on this? Mind if I send over a loom I recorded for you? Never send any links in the first email. You've reached out to this person because you have good reason to believe they'd find real value in your offer, and you want to verify if that's the case. After you get one reply, this is a great positive signal and from there you can send a link, book a call, provide a free resource, whatever makes sense based on their response. Personalize your outreach Personalization is one of the most important parts of the process to get right. Your recipient probably receives a multitude of emails every day, how can you make yours stand out, letting them know you've done your research, and that your email is relevant to them? Personalizing each email ensures you get more positive replies, and avoid spam filters, as your email is unique and hasn't been copied and pasted a million times over. The goal is to spark the recipient's interest, and let them know that you're contacting them for good reason. You might mention a recent achievement, blog post or product release that led you to reach out to the prospect specifically. For example: Your post on "Doing Nothing" gave me a good chuckle. Savvy marketing on Cadbury's part. Saw that you've been at Google for just under a year now as a new VP of sales. Spotted that you've got over 7 years of experience in the digital marketing space. Ideally you'll mention something specifically about the prospect or their company that relates to your offer. The downside to personalization is that it's hard to get right, and very time consuming at scale, but totally worth it. Full disclosure, me and my partner Igor just launched our new startup ColdClicks which uses AI to generate hyper-personalized email openers at scale. We built the tool as we were sending hundreds of emails a day, and personalizing every individual email took hours out of our day. ColdClicks automates this process, saving you time and getting you 2-3x more replies. Send emails At this stage you've decided on who you're targeting, you've mined some leads, and written copy. Now it's time to get sending. You can do this manually by copy and pasting each message, but one of the reasons cold email is so powerful is that it's scalable. When you build a process that gets customers, you'll want to send as many emails as you can to your target market. To get started quickly, you can use a mail-merge gmail tool, the best I've used is Maileteor. With Maileteor you upload your lead data to Google sheets, set-up an email template and Mailmetor will send out emails every day automatically. In your template you can define variables including name, company, and personalization to ensure your email is unique for each recipient. Alternatively, you may opt for a more comprehensive tool such as Instantly. Instantly includes unlimited email sending and accounts. There's more initial setup involved as you'll need to set-up Google workspace, buy sending domains, and warm up your email accounts, but when you become familiar with the process you can build a powerful lead generation / customer acquisition machine. Some key points to note, it's very important to warm up any new email accounts you set up. Warmup is the process of gradually establishing a positive reputation with email service providers like Gmail or Yahoo. Make sure to set up DKIM and DMARC on those new email accounts too, to maximise your chances of landing in the inbox. Scale up Once you've found a process that works, good things happen, and it becomes a numbers game. As you get replies and start to see new users signing up, you'll want to scale the process and send more emails. It's straightforward to add new sending accounts in a sending tool like Instantly, and you'll want to broaden your targeting when mining to test new markets. Unfortunately, sending more emails usually comes with a drop in reply rate as you have less time to personalize your messaging for each recipient. This is where ColdClicks shines. The tool allows you to upload thousands of leads and generate perfectly relevant email personalizations for every lead in your list, then export to your favorite sending tool. The examples I listed above in the personalization section were all generated by ColdClicks. Wrapping it up Cold email is an amazing way to validate your product and get new customers. The channel gets a bad rap, but there's a huge difference between blind cold emailing and crafting personalized outreach for individuals who will find value in your product. It's perfect for bootstrapped founders due to its affordability and scalability, and it's the driver of growth for many SaaS businesses. Time to get your first 10 customers! As you start sending, make it a habit to regularly check for new leads. Always experiment with market/messaging, track every campaign so you can learn what's working and iterate, and when you do get positive responses, reply as soon as you can!

Built a side project to help validate... side projects 🤔

Hey builders! Long-time lurker, first-time poster. Wanted to share something I've been working on after hours. The Problem Like many of you, I was building side projects at night while working full-time. My pattern was painfully consistent: \- Get excited about an idea \- Spend precious evening hours coding \- Launch on Reddit/Twitter \- \crickets\ \- Realize I should've validated first \- Repeat 🥲 The worst part? I was trying to do validation on Reddit, but with limited time after work, I couldn't: \- Properly research different communities \- Keep track of all the responses \- Find people actually interested in what I was building \- Or figure out what features to prioritize in my limited dev time The Solution So I built RediScope (yes, another side project 😅). It automates the Reddit validation process: Quick Loom demo How it works: Tell it what you're trying to validate AI helps write natural-sounding questions for each community Get instant analysis of responses Automatically spot potential early users The goal? Instead of spending your limited free time scrolling through Reddit, get clear validation and potential users in 48 hours. Tech Stack (since we all love this part): \- Frontend: React + Tailwind \- Backend: Node.js \- AI: OpenAI for the smart bits \- DB: PostgreSQL \- Hosting: Digital Ocean Current Status: \- ✅ Core validation engine working \- ✅ Community analysis \- ✅ Response analytics \- ✅ User dashboard \- 🔎 Lead Generator (in progress) \- 📋 API (planned) This is very much a nights-and-weekends project (like everything else we build 😄). Would love feedback from fellow side project builders: \- How do you validate your ideas currently? \- What would make this useful for your next project? \- Any features you'd want to see? Drop your thoughts below! If you want to try it when it launches: https://www.rediscope.app Also huge shoutout to this community - been learning so much from everyone's posts here 🙏

I’ve built a gaming recommendation and exploration platform called Which Game Next

Hello there! Me and a few of my best friends are software engineers, and we’ve been working part-time on developing a side project for the past 12 months. It’s called www.whichgamenext.com, and we’ve recently launched into open beta for everyone to check out. Your feedback would be invaluable to us! Our aim has been to build a gaming recommendation engine, alongside providing market oversight for where you can legally and officially purchase or obtain modern games from multiple stores and/or subscriptions. It’s often difficult to figure out what you have access to if you only have a single specific subscription, like Game Pass PC, or if you’re only interested in games on GOG/Nintendo (what a mix!). We started by identifying the available digital stores and subscriptions and slowly compiling our database using multiple automated services to gather data on these games. Think JustWatch, but for games! One major service we’ve partnered with is IGDB, which has been supplying us with JSON data dumps that served as the initial seed for our game data. A massive thank you to them for their continued support! With the data in place, we’ve been focusing on exploring new features. So far, this has included private and public user-generated lists, personal backlog tracking, and the ability to like or dislike games. We’re now improving our recommendation engine, tackling the complexities that come with it, and having a lot of fun along the way. We’re utilising modern AI strategies and solving fascinating problems related to large-scale data aggregation. We truly can’t wait to share this fantastic work! In addition to this, you can soon expect curated collections, articles about games, and supporting links to help you make informed, unbiased purchasing decisions. Your shared data will drive the recommendations. But it doesn’t stop there—we have plenty of other features on our radar, such as importing games from your favourite stores, syncing your gameplay time, surfacing data like “How Long to Beat,” and creating new and exciting ways to interact with this growing community! This is a passion project created by a group of gamers who want to spend their time and money wisely, without purchasing biases. Since it’s a side project, we mostly work on it at night, but we’re excited to grow the community, share our vision, and, who knows, maybe one day make it our full-time job! Let’s dive into the technical details: • Monorepo architecture: This speeds up development by sharing libraries, living style guides, configs, etc. Nx.js has been brilliant, enabling us to create a dependency graph of changes and only build/deploy what’s modified in a PR. • AWS: We’re using the free tier (with a few exceptions where we pay for smaller services). Achieving self-sufficiency is critical for us. Additionally, we applied to the AWS Startup Foundation programme and received $1,000 in AWS credits, which has been incredibly helpful! • Infrastructure: Fully deployed as code with Terraform. • Backends: Built using Express and Nest.js, split into around 40 projects and counting! Each project plays a unique role in gathering and syncing game data. • Scalability: Designed from the ground up, utilising AWS Lambdas with auto-scaling and load balancing. • Databases: We use Postgres with RDS and DynamoDB for storing various data. • Frontend stack: Built with React, Next.js, Tailwind, Zustand, TanStack Query, Jest, and Storybook. • CI/CD: Managed with GitHub Actions and Amplify hooks for deploying the frontends. • Admin portal: We’ve built a bespoke CMS to control the main website. It synchronises with external services, tracks game data changes, and allows us to selectively apply ‘patches’ from sites like IGDB. The system also includes data override and rollback capabilities, ensuring we maintain control over game data. • Automation: Partially automated, so manual intervention is rarely needed. • Scraping tools: Fully integrated into the admin portal with log trail capabilities. • Cloudflare: Used for on-the-fly image transformations; we’re considering moving to it full-time as our CDN for free WebP conversions. • Authentication: Handled by Cognito, with a custom frontend built from scratch. Key learnings so far: • AWS cold starts: Not ideal! While the platform is still new, we ping endpoints to keep them responsive. This won’t be an issue once traffic increases. • Lambda memory matters: We learned the hard way that low-memory configurations can delay responses by 2-3 seconds. • DynamoDB partition keys: If not designed correctly from the start, you might have to start over (yes, we’ve been there!). • GitHub Actions: Setting up node\_modules cache reuse takes time, but it’s worth it—don’t give up! We don’t know where this project will take us yet, but it’s been a fantastic journey so far. We’ve learned a lot, explored technologies we don’t typically use in our day jobs, and built something we’re genuinely passionate about. Your feedback would mean the world to us. What do you think of what we’ve done so far? What would you like to see added? Is this a service you’d use? Do you see the value in it as we do? Thanks for reading, and we hope to see you in the comments! (or our newly created /r/whichgamenext

0-20+ faceless AI automated YouTube channels in 1 year - my process and tools

First of all before diving deep into this process (scroll a bit below) I have to say something that everyone keeps asking me, is it profitable? Yes. It's by far my most profitable venture outside of my regular 9-5... But it took a lot of work, delegation and building processes to get here. So the one thing I would love to get out of this post - if you have any insights, feedback or tools I might be missing out post them below and let's help each other out. Now, how you can get started with (AI) YouTube automation: Pick a topic that is BOTH: a) in demand b) interesting to you & you have knowledge about Do everything yourself at first - delegate later No one cares about the videos as much as you do, so make sure to nail the ideation, scripts, editing, format and packaging yourself first. Now that we got that out of the way: Use this workflow: VidIQ - outliers sections is pure gold, I use it all the time to find trending video packaging, topics, etc. ChatGPT or Claude - high level video ideas at scale and your assistant (I use projects inside ChatGPT and its really good at managing and prioritizing). If you are using it for scripts please for the love of god, make final edits yourself by hand. Add character, personal insights, ideas, etc. Katalist AI - all in one video generator tool I use to quickly go from video idea to script, storyboard, AI voiceover and then final visuals. It's surprisingly good and to make a decent video it only takes about 1-2 hours in TOTAL. Once you understand how it works and have a process, delegate to tech savvy VAs / content creators for $5-$15/hour and you have final, good quality videos for less than $30. Pikzels / Krea AI - your AI thumbnail generator, I dont remember the last time we used Photoshop outside of quick text or image edits. Its basically AI image manipulation at scale and it costs 10-30x less than a human thumbnail designer and the thumbnails are really good. VidIQ+TubeBuddy - titles & optimization, but you have to know that most of the views come usually from recommended, so dont over obsess and add 392x keywords in your title and description. Its all about the packaging. Now whats left is track performance & iterate - it's practically impossible to nail it the first few times, but each video you make look at the data (not just in YT studio) and UNDERSTAND why it did not perform as well as you thought it would. Regarding monetization, adsense sucks - sell digital products. If I was relying on adsense alone I would never ever be profitable, but selling mini digital products and mentioning CTAs in the actual video not just in the description makes this super profitable and scaleable, especially since video production is so cheap. Final thoughts: (AI) YouTube automation absolutely works, but it’s not an overnight success or a total hands-off cashcow machine. It’s a real business and you need systems, consistent effort, iteration, failing and learning along the way. If you’ve got any tips, hidden gems or tools I might be missing, drop them below & let’s help each other out.

PlumbingJobs.com - I launched a niche job board with hand-curated jobs for plumbers. Here's the summary of how it's going after the 3rd month

On October 12th 2024, I launched PlumbingJobs.com, and this is my first update (January 2025) in what I hope will be a long journey. To stay accountable and track progress, I’ll be sharing monthly updates about the site's stats, achievements, challenges, and my plans moving forward. While these posts are mostly to document the journey, I hope they’ll also be helpful to others, especially members of r/SideProject who might be working on their own first online projects. If this post isn’t a good fit for this subreddit, I’m happy to remove it or move updates elsewhere. The goal for PlumbingJobs.com is clear: to become the #1 job board for plumber jobs, featuring hand-picked opportunities the plumbing industry. Let’s dive right in: Statistics update ~ 4th Quarter of 2024 |\-|October|November|December| |:-|:-|:-|:-| |Jobs Posted:|2|16|43| |Paid Post:|0|2|2| |Free Post:|0|1|2| |Visitors:|72|138|1,164| |Avg. Time Per Visit:|1 min. 24 sec|2 min. 15 sec|3 min. 41 sec| |Pageviews:|196|308|2,590| |Avg. Actions:|1.1|2.3|2.3| |Bounce Rate:|87%|73%|40%| I'm not a very technical guy and I don't know how to code. So the best way for me was learning to build it using Wordpress through YouTube. Also, I believe in the power of a great .COM domain name, and the stats from the first three months have only reinforced that belief: 49.2% of traffic comes directly from users typing the URL into their browsers. 48% of traffic is from search engines like Google and Bing. The remaining 1.8% comes from social media and other backlinks. Pricing Tiers and Early Wins I offer three pricing tiers for job listings: Free Listing: Basic exposure for job openings. Silver Listing ($45): Greater visibility and placement on the site. Gold Listing ($95): Premium visibility and enhanced promotion. To my surprise, my very first sale in October was a Gold Listing! That initial $95 sale was the motivation I needed to keep building. Later that month, I sold a Silver Listing, bringing my total revenue for October to $140. The same revenue was generated in December 2024, showing consistent early interest. Steps Taken in December To boost SEO and add value to the site, I created a Plumbing Directory, featuring: Plumbing companies across the U.S. Their stories, contact information, logos, addresses, business hours, and more. This directory serves as free marketing for these businesses and increases the likelihood they’ll discover my site and support it by posting job openings. Plans Moving Forward Social Media Marketing: I plan to automate posts using AI to expand reach and drive more traffic to the site. Consistency in Job Postings: I’m committed to posting 2–3 plumbing jobs daily to keep the site fresh and useful for plumbers seeking work. Looking forward to grow this niche job board slowly but surely this 2025. If you have any questions, concerns, come across glitches - feel free to reach out, happy to chat. Thank you all again, and see you in a month. Romel@plumbingjobs.com

How me and my team made 15+ apps and not made a single sale in 2023

Hey, my name is Michael, I am in Auckland NZ. This year was the official beginning of my adult life. I graduated from university and started a full-time job. I’ve also really dug into indiehacking/bootstrapping and started 15 projects (and it will be at least 17 before the year ends). I think I’ve learned a lot but I consciously repeated mistakes. Upto (Nov) Discord Statuses + Your Location + Facebook Poke https://preview.redd.it/4nqt7tp2tf5c1.png?width=572&format=png&auto=webp&s=b0223484bc54b45b5c65e0b1afd0dc52f9c02ad1 This was the end of uni, I often messaged (and got messaged) requests of status and location to (and from my) friends. I thought, what if we make a social app that’s super basic and all it does is show you where your friends are? To differentiate from snap maps and others we wanted something with more privacy where you select the location. However, never finished the codebase or launched it. This is because I slowly started to realize that B2C (especially social networks) are way too hard to make into an actual business and the story with Fistbump would repeat itself. However, this decision not to launch it almost launched a curse on our team. From that point, we permitted ourselves to abandon projects even before launching. Lessons: Don’t do social networks if your goal is 10k MRR ASAP. If you build something to 90% competition ship it or you will think it’s okay to abandon projects Insight Bites (Nov) Youtube Summarizer Extension &#x200B; https://preview.redd.it/h6drqej4tf5c1.jpg?width=800&format=pjpg&auto=webp&s=0f211456c390ac06f4fcb54aa51f9d50b0826658 Right after Upto, we started ideating and conveniently the biggest revolution in the recent history of tech was released → GPT. We instantly began ideating. The first problem we chose to use AI for is to summarize YouTube videos. Comical. Nevertheless, I am convinced we have had the best UX because you could right-click on a video to get a slideshow of insights instead of how everyone else did it. We dropped it because there was too much competition and unit economics didn’t work out (and it was a B2C). PodPigeon (Dec) Podcast → Tweet Threads https://preview.redd.it/0ukge245tf5c1.png?width=2498&format=png&auto=webp&s=23303e1cab330578a3d25cd688fa67aa3b97fb60 Then we thought, to make unit economics work we need to make this worthwhile for podcasters. This is when I got into Twitter and started seeing people summarize podcasts. Then I thought, what if we make something that converts a podcast into tweets? This was probably one of the most important projects because it connected me with Jason and Jonaed, both of whom I regularly stay in contact with and are my go-to experts on ideas related to content creation. Jonaed was even willing to buy Podpigeon and was using it on his own time. However, the unit economics still didn’t work out (and we got excited about other things). Furthermore, we got scared of the competition because I found 1 - 2 other people who did similar things poorly. This was probably the biggest mistake we’ve made. Very similar projects made 10k MRR and more, launching later than we did. We didn’t have a coherent product vision, we didn’t understand the customer well enough, and we had a bad outlook on competition and a myriad of other things. Lessons: I already made another post about the importance of outlook on competition. Do not quit just because there are competitors or just because you can’t be 10x better. Indiehackers and Bootstrappers (or even startups) need to differentiate in the market, which can be via product (UX/UI), distribution, or both. Asking Ace Intro.co + Crowdsharing &#x200B; https://preview.redd.it/0hu2tt16tf5c1.jpg?width=1456&format=pjpg&auto=webp&s=3d397568ef2331e78198d64fafc1a701a3e75999 As I got into Twitter, I wanted to chat with some people I saw there. However, they were really expensive. I thought, what if we made some kind of crowdfunding service for other entrepreneurs to get a private lecture from their idols? It seemed to make a lot of sense on paper. It was solving a problem (validated via the fact that Intro.co is a thing and making things cheaper and accessible is a solid ground to stand on), we understood the market (or so we thought), and it could monetize relatively quickly. However, after 1-2 posts on Reddit and Indiehackers, we quickly learned three things. Firstly, no one cares. Secondly, even if they do, they think they can get the same information for free online. Thirdly, the reasons before are bad because for the first point → we barely talked to people, and for the second people → we barely talked to the wrong people. However, at least we didn’t code anything this time and tried to validate via a landing page. Lessons Don’t give up after 1 Redditor says “I don’t need this” Don’t be scared to choose successful people as your audience. Clarito Journaling with AI analyzer https://preview.redd.it/8ria2wq6tf5c1.jpg?width=1108&format=pjpg&auto=webp&s=586ec28ae75003d9f71b4af2520b748d53dd2854 Clarito is a classic problem all amateur entrepreneurs have. It’s where you lie to yourself that you have a real problem and therefore is validated but when your team asks you how much you would pay you say I guess you will pay, maybe, like 5 bucks a month…? Turns out, you’d have to pay me to use our own product lol. We sent it off to a few friends and posted on some forums, but never really got anything tangible and decided to move away. Honestly, a lot of it is us in our own heads. We say the market is too saturated, it’ll be hard to monetize, it’s B2C, etc. Lessons: You use the Mom Test on other people. You have to do it yourself as well. However, recognizing that the Mom Test requires a lot of creativity in its investigation because knowing what questions to ask can determine the outcome of the validation. I asked myself “Do I journal” but I didn’t ask myself “How often do I want GPT to chyme in on my reflections”. Which was practically never. That being said I think with the right audience and distribution, this product can work. I just don’t know (let alone care) about the audience that much (and I thought I was one of them)/ Horns & Claw Scrapes financial news texts you whether you should buy/sell the stock (news sentiment analysis) &#x200B; https://preview.redd.it/gvfxdgc7tf5c1.jpg?width=1287&format=pjpg&auto=webp&s=63977bbc33fe74147b1f72913cefee4a9ebec9c2 This one we didn’t even bother launching. Probably something internal in the team and also seemed too good to be true (because if this works, doesn’t that just make us ultra-rich fast?). I saw a similar tool making 10k MRR so I guess I was wrong. Lessons: This one was pretty much just us getting into our heads. I declared that without an audience it would be impossible to ship this product and we needed to start a YouTube channel. Lol, and we did. And we couldn’t even film for 1 minute. I made bold statements like “We will commit to this for at least 1 year no matter what”. Learnery Make courses about any subject https://preview.redd.it/1nw6z448tf5c1.jpg?width=1112&format=pjpg&auto=webp&s=f2c73e8af23b0a6c3747a81e785960d4004feb48 This is probably the most “successful” project we’ve made. It grew from a couple of dozen to a couple of hundred users. It has 11 buy events for $9.99 LTD (we couldn’t be bothered connecting Stripe because we thought no one would buy it anyway). However what got us discouraged from seriously pursuing it more is, that this has very low defensibility, “Why wouldn’t someone just use chatGPT?” and it’s B2C so it’s hard to monetize. I used it myself for a month or so but then stopped. I don’t think it’s the app, I think the act of learning a concept from scratch isn’t something you do constantly in the way Learnery delivers it (ie course). I saw a bunch of similar apps that look like Ass make like 10k MRR. Lessons: Don’t do B2C, or if you do, do it properly Don’t just Mixpanel the buy button, connect your Stripe otherwise, it doesn’t feel real and you won’t get momentum. I doubt anyone (even me) will make this mistake again. I live in my GPT bubble where I make assumptions that everyone uses GPT the same way and as much as I do. In reality, the argument that this has low defensibility against GPT is invalid. Platforms that deliver a differentiated UX from ChatGPT to audiences who are not tightly integrated into the habit of using ChatGPT (which is like - everyone except for SOME tech evangelists). CuriosityFM Make podcasts about any subject https://preview.redd.it/zmosrcp8tf5c1.jpg?width=638&format=pjpg&auto=webp&s=d04ddffabef9050050b0d87939273cc96a8637dc This was our attempt at making Learnery more unique and more differentiated from chatGPT. We never really launched it. The unit economics didn’t work out and it was actually pretty boring to listen to, I don’t think I even fully listened to one 15-minute episode. I think this wasn’t that bad, it taught us more about ElevenLabs and voice AI. It took us maybe only 2-3 days to build so I think building to learn a new groundbreaking technology is fine. SleepyTale Make children’s bedtime stories https://preview.redd.it/14ue9nm9tf5c1.jpg?width=807&format=pjpg&auto=webp&s=267e18ec6f9270e6d1d11564b38136fa524966a1 My 8-year-old sister gave me that idea. She was too scared of making tea and I was curious about how she’d react if she heard a bedtime story about that exact scenario with the moral that I wanted her to absorb (which is that you shouldn’t be scared to try new things ie stop asking me to make your tea and do it yourself, it’s not that hard. You could say I went full Goebbels on her). Zane messaged a bunch of parents on Facebook but no one really cared. We showed this to one Lady at the place we worked from at Uni and she was impressed and wanted to show it to her kids but we already turned off our ElevenLabs subscription. Lessons: However, the truth behind this is beyond just “you need to be able to distribute”. It’s that you have to care about the audience. I don’t particularly want to build products for kids and parents. I am far away from that audience because I am neither a kid anymore nor going to be a parent anytime soon, and my sister still asked me to make her tea so the story didn’t work. I think it’s important to ask yourself whether you care about the audience. The way you answer that even when you are in full bias mode is, do you engage with them? Are you interested in what’s happening in their communities? Are you friends with them? Etc. User Survey Analyzer Big User Survey → GPT → Insights Report Me and my coworker were chatting about AI when he asked me to help him analyze a massive survey for him. I thought that was some pretty decent validation. Someone in an actual company asking for help. Lessons Market research is important but moving fast is also important. Ie building momentum. Also don’t revolve around 1 user. This has been a problem in multiple projects. Finding as many users as possible in the beginning to talk to is key. Otherwise, you are just waiting for 1 person to get back to you. AutoI18N Automated Internationalization of the codebase for webapps This one I might still do. It’s hard to find a solid distribution strategy. However, the idea came from me having to do it at my day job. It seems a solid problem. I’d say it’s validated and has some good players already. The key will be differentiation via the simplicity of UX and distribution (which means a slightly different audience). In the backlog for now because I don’t care about the problem or the audience that much. Documate - Part 1 Converts complex PDFs into Excel https://preview.redd.it/8b45k9katf5c1.jpg?width=1344&format=pjpg&auto=webp&s=57324b8720eb22782e28794d2db674b073193995 My mom needed to convert a catalog of furniture into an inventory which took her 3 full days of data entry. I automated it for her and thought this could have a big impact but there was no distribution because there was no ICP. We tried to find the ideal customers by talking to a bunch of different demographics but I flew to Kazakhstan for a holiday and so this kind of fizzled out. I am not writing this blog post linearity, this is my 2nd hour and I am tired and don’t want to finish this later so I don’t even know what lessons I learned. Figmatic Marketplace of high-quality Figma mockups of real apps https://preview.redd.it/h13yv45btf5c1.jpg?width=873&format=pjpg&auto=webp&s=aaa2896aeac2f22e9b7d9eed98c28bb8a2d2cdf1 This was a collab between me and my friend Alex. It was the classic Clarito where we both thought we had this problem and would pay to fix it. In reality, this is a vitamin. Neither I, nor I doubt Alex have thought of this as soon as we bought the domain. We posted it on Gumroad, sent it to a bunch of forums, and called it a day. Same issue as almost all the other ones. No distribution strategy. However, apps like Mobin show us that this concept is indeed profitable but it takes time. It needs SEO. It needs a community. None of those things, me and Alex had or was interested in. However shortly after HTML → Figma came out and it’s the best plugin. Maybe that should’ve been the idea. Podcast → Course Turns Podcaster’s episodes into a course This one I got baited by Jason :P I described to him the idea of repurposing his content for a course. He told me this was epic and he would pay. Then after I sent him the demo, he never checked it out. Anyhow during the development, we realized that doesn’t actually work because A podcast doesn’t have the correct format for the course, the most you can extract are concepts and ideas, seldom explanations. Most creators want video-based courses to be hosted on Kajabi or Udemy Another lesson is that when you pitch something to a user, what you articulate is a platform or a process, they imagine an outcome. However, the end result of your platform can be a very different outcome to what they had in mind and there is even a chance that what they want is not possible. You need to understand really well what the outcome looks like before you design the process. This is a classic problem where we thought of the solution before the problem. Yes, the problem exists. Podcasters want to make courses. However, if you really understand what they want, you can see how repurposing a podcast isn’t the best way to get there. However I only really spoke to 1-2 podcasters about this so making conclusions is dangerous for this can just be another asking ace mistake with the Redditor. Documate Part 2 Same concept as before but now I want to run some ads. We’ll see what happens. https://preview.redd.it/xb3npj0ctf5c1.jpg?width=1456&format=pjpg&auto=webp&s=3cd4884a29fd11d870d010a2677b585551c49193 In conclusion https://preview.redd.it/2zrldc9dtf5c1.jpg?width=1840&format=pjpg&auto=webp&s=2b3105073e752ad41c23f205dbd1ea046c1da7ff It doesn’t actually matter that much whether you choose to do a B2C, or a social network or focus on growing your audience. All of these can make you successful. What’s important is that you choose. If I had to summarize my 2023 in one word it’s indecision. Most of these projects succeeded for other people, nothing was as fundamentally wrong about them as I proclaimed. In reality that itself was an excuse. New ideas seduce, and it is a form of discipline to commit to a single project for a respectful amount of time. https://preview.redd.it/zy9a2vzdtf5c1.jpg?width=1456&format=pjpg&auto=webp&s=901c621227bba0feb4efdb39142f66ab2ebb86fe Distribution is not just posting on Indiehackers and Reddit. It’s an actual strategy and you should think of it as soon as you think of the idea, even before the Figma designs. I like how Denis Shatalin taught me. You have to build a pipeline. That means a reliable way to get leads, launch campaigns at them, close deals, learn from them, and optimize. Whenever I get an idea now I always try to ask myself “Where can I find 1000s leads in one day?” If there is no good answer, this is not a good project to do now. &#x200B; https://preview.redd.it/2boh3fpetf5c1.jpg?width=1456&format=pjpg&auto=webp&s=1c0d5d7b000716fcbbb00cbad495e8b61e25be66 Talk to users before doing anything. Jumping on designing and coding to make your idea a reality is a satisfying activity in the short term. Especially for me, I like to create for the sake of creation. However, it is so important to understand the market, understand the audience, understand the distribution. There are a lot of things to understand before coding. https://preview.redd.it/lv8tt96ftf5c1.jpg?width=1456&format=pjpg&auto=webp&s=6c8735aa6ad795f216ff9ddfa2341712e8277724 Get out of your own head. The real reason we dropped so many projects is that we got into our own heads. We let the negative thoughts creep in and kill all the optimism. I am really good at coming up with excuses to start a project. However, I am equally as good at coming up with reasons to kill a project. And so you have this yin and yang of starting and stopping. Building momentum and not burning out. I can say with certainty my team ran out of juice this year. We lost momentum so many times we got burnt out towards the end. Realizing that the project itself has momentum is important. User feedback and sales bring momentum. Building also creates momentum but unless it is matched with an equal force of impact, it can stomp the project down. That is why so many of our projects died quickly after we launched. The smarter approach is to do things that have a low investment of momentum (like talking to users) but result in high impact (sales or feedback). Yes, that means the project can get invalidated which makes it more short-lived than if we built it first, but it preserves team life energy. At the end of 2023 here is a single sentence I am making about how I think one becomes a successful indiehacker. One becomes a successful Indiehacker when one starts to solve pain-killer problems in the market they understand, for an audience they care about and consistently engage with for a long enough timeframe. Therefore an unsuccessful Indiehacker in a single sentence is An unsuccessful Indiehacker constantly enters new markets they don’t understand to build solutions for people whose problems they don’t care about, in a timeframe that is shorter than than the time they spent thinking about distribution. However, an important note to be made. Life is not just about indiehacking. It’s about learning and having fun. In the human world, the best journey isn’t the one that gets you the fastest to your goals but the one you enjoy the most. I enjoyed making those silly little projects and although I do not regret them, I will not repeat the same mistakes in 2024. But while it’s still 2023, I have 2 more projects I want to do :) EDIT: For Devs, frontend is always react with vite (ts) and backend is either node with express (ts) or python. For DB either Postgres or mongo (usually Prisma for ORM). For deployment all of it is on AWS (S3, EC2). In terms of libraries/APIs Whisper.cpp is best open source for transcription Obviously the gpt apis Eleven labs for voice related stuff And other random stuff here and there

I retired at 32 from my side project. Here's the path I took.

EDIT 2: Thanks for the award kind stranger! I've stopped responding to reddit comments for this post. I'm adding an FAQ to the original post based on the most common high quality questions. If you have a question that you're dying to know the answer to and that only I can help you with (vs. Google, ChatGPT, etc.), DM me. EDIT: I love how controversial this post has become (50% upvote rate), and only in this subreddit (vs. other subreddits that I posted the same content in). I trust that the open-minded half of you will find something useful in this post and my other posts and comments. I retired at 32 years old, in large part thanks to a B2C SaaS app that I developed on my own. Now, I don't have to work in order to cover my living expenses, and wouldn't have to work for quite a while. In other words, I can finally sip mai tais at the beach. I've condensed how I got there into this post. First, a super simplified timeline of events, followed by some critical details. Timeline 2013 Graduated college in the US 2013 Started first corporate job 2013 Started side project (B2C app) that would eventually lead to my retirement 2020 Started charging for use of my B2C app (was free, became freemium) 2021 Quit my last corporate job 2022 Retired: time freedom attained Details First, some summary statistics of my path to retirement: 9 years: time between graduating college and my retirement. 8 years: total length of my career where I worked at some corporate day job. 7 years: time it took my B2C app to make its first revenue dollar 2 years: time between my first dollar of SaaS revenue and my retirement. "Something something overnight success a decade in the making". I got extremely lucky on my path to retirement, both in terms of the business environment I was in and who I am as a person. I'd also like to think that some of the conscious decisions I made along the way contributed to my early retirement. Lucky Breaks Was born in the US middle class. Had a natural affinity for computer programming and entrepreneurial mindset (initiative, resourcefulness, pragmatism, courage, growth mindset). Had opportunities to develop these mindsets throughout life. Got into a good college which gave me the credentials to get high paying corporate jobs. Was early to a platform that saw large adoption (see "barnacle on whale" strategy). Business niche is shareworthy: my SaaS received free media. Business niche is relatively stable, and small enough to not be competitive. "Skillful" Decisions I decided to spend the nights and weekends of my early career working on side projects in the hopes that one would hit. I also worked a day job to support myself and build my savings. My launch funnel over roughly 7 years of working on side projects: Countless side projects prototyped. 5 side projects publically launched. 2 side projects made > $0. 1 side project ended up becoming the SaaS that would help me retire. At my corporate day jobs, I optimized for learning and work-life balance. My learning usually stalled after a year or two at one company, so I’d quit and find another job. I invested (and continute to do so) in physical and mental wellbeing via regular workouts, meditation, journaling, traveling, and good food. My fulfilling non-work-life re-energized me for my work-life, and my work-life supported my non-work-life: a virtuous cycle. I automated the most time-consuming aspects of my business (outside of product development). Nowadays, I take long vacations and work at most 20 hours a week / a three-day work week . I decided to keep my business entirely owned and operated by me. It's the best fit for my work-style (high autonomy, deep focus, fast decision-making) and need to have full creative freedom and control. I dated and married a very supportive and inspiring partner. I try not to succumb to outrageous lifestyle creep, which keeps my living expenses low and drastically extends my burn-rate. Prescription To share some aphorisms I’ve leaned with the wantrepreneurs or those who want to follow a similar path: Maximize your at bats, because you only need one hit. Bias towards action. Launch quickly. Get your ideas out into the real world for feedback. Perfect is the enemy of good. If you keep swinging and improving, you'll hit the ball eventually. Keep the big picture in mind. You don't necessarily need a home-run to be happy: a base hit will often do the job. Think about what matters most to you in life: is it a lot of money or status? Or is it something more satisfying, and often just as if not more attainable, like freedom, loving relationships, or fulfillment? Is what you’re doing now a good way to get what you want? Or is there a better way? At more of a micro-level of "keep the big picture in mind", I often see talented wantrepreneurs get stuck in the weeds of lower-level optimizations, usually around technical design choices. They forget (or maybe subconsciously avoid) the higher-level and more important questions of customer development, user experience, and distribution. For example: “Are you solving a real problem?” or “Did you launch an MVP and what did your users think?” Adopt a growth mindset. Believe that you are capable of learning whatever you need to learn in order to do what you want to do. The pain of regret is worse than the pain of failure. I’ve noticed that fear of failure is the greatest thing holding people back from taking action towards their dreams. Unless failure means death in your case, a debilitating fear of failure is a surmountable mental block. You miss 100% of the shots you don't take. When all is said and done, we often regret the things we didn't do in life than the things we did. There’s more to life than just work. Blasphemous (at least among my social circle)! But the reality is that many of the dying regret having worked too much in their lives. As Miss Frizzle from The Magic Schoolbus says: "Take chances, make mistakes, get messy!" Original post

I recreated an AI Phone Agent that saved $20,000 in lost revenue in 30 days for a business

I've been intrigued by AI and its ability to help businesses streamline time-consuming tasks. Recently, I discovered a case study where a voice agent was able to earn a business $20,000 in booked calls in a month. Below, I've shared the case study and a demo number for a voice agent I developed. This technology is advancing rapidly, and I want to explore its potential further. Case Study A family-owned HVAC company struggled with managing a high volume of customer calls, including after-hours and weekend inquiries, resulting in missed opportunities and unmanaged leads. Hiring a dedicated call support team was not cost-effective. Solution The company implemented an AI system to handle calls autonomously, gather customer information, and notify service technicians via SMS, with options for live call transfers. Details The AI integration featured custom capabilities such as Service Titan integration, live call transfers, SMS/email alerts, calendar and CRM integration, and Zapier automation. Results In the first week, the company experienced a 20% increase in bookings and conversions. The system efficiently captured leads and managed tasks, enabling staff to handle more inquiries and outsource overflow. Within 30 days, the company saved $20,000 in lost revenue due to the elimination of calls that went to voicemail, or lost leads. The voice agent's ability to answer calls 24/7 led to significant revenue growth, time savings, and reduced churn. Here's the demo number for the voice agent I created: +1 (651) 372 2045 I believe this tech has strong use cases in a variety of industries, from home service, to dental clinics, to wedding photographers. This article studied the effect of missed calls in different businesses, if you're interested in learning more. I'd love to hear your thoughts and industries you think this could be the most beneficial for. Thank you!

I recreated an AI Phone Agent that saved $20,000 in lost revenue in 30 days for a business

I've been intrigued by AI and its ability to help businesses streamline time-consuming tasks. Recently, I discovered a case study where a voice agent was able to earn a business $20,000 in booked calls in a month. Below, I've shared the case study and a demo number for a voice agent I developed. This technology is advancing rapidly, and I want to explore its potential further. Case Study A family-owned HVAC company struggled with managing a high volume of customer calls, including after-hours and weekend inquiries, resulting in missed opportunities and unmanaged leads. Hiring a dedicated call support team was not cost-effective. Solution The company implemented an AI system to handle calls autonomously, gather customer information, and notify service technicians via SMS, with options for live call transfers. Details The AI integration featured custom capabilities such as Service Titan integration, live call transfers, SMS/email alerts, calendar and CRM integration, and Zapier automation. Results In the first week, the company experienced a 20% increase in bookings and conversions. The system efficiently captured leads and managed tasks, enabling staff to handle more inquiries and outsource overflow. Within 30 days, the company saved $20,000 in lost revenue due to the elimination of calls that went to voicemail, or lost leads. The voice agent's ability to answer calls 24/7 led to significant revenue growth, time savings, and reduced churn. Here's the demo number for the voice agent I created: +1 (651) 372 2045 I believe this tech has strong use cases in a variety of industries, from home service, to dental clinics, to wedding photographers. This article studied the effect of missed calls in different businesses, if you're interested in learning more. I'd love to hear your thoughts and industries you think this could be the most beneficial for. Thank you!

Why no code tools for building ai models failed?

Business folks have tasks where neural networks could help but they don’t know Python or deep learning, right? Meanwhile ML engineers know AI models but often don’t have an actual problem to solve. So the first group hires the second. Same thing happened with websites a while ago—at first you had to code everything then came drag-and-drop editors, no-code tools, and now even this "vibe coding" stuff. It’s not the most flexible or maintainable, but it works for a lot of people who just need to get something done without spending months learning to code. So why isn’t the same thing happening with building AI models? Like if I run a business I could save a ton of money by automating manual tasks with models trained on my own data. But I have zero clue what Jupyter Notebook or Keras are, and honestly, I don’t want to know. So I have to hire an ML engineer just to get it done because there’s no viable no-code solution for this.

Seeking Quick Feedback: AI Tool for SMB Sustainability

Hi everyone, I’m working on an AI-powered toolkit to help small and medium-sized businesses (SMBs) with sustainability efforts and ESG reporting for a hackathon. I’d really appreciate a quick testimonial from those who find this tool valuable. Key Features: Generative AI for automatic ESG report creation. Machine Learning for optimizing operational data. NLP for easy-to-understand reports. If you find this concept useful for SMBs or sustainability efforts, could you share a brief testimonial or your thoughts? Your feedback would be incredibly helpful! Thank you!

0-20+ faceless AI automated YouTube channels in 1 year - my process and tools

First of all before diving deep into this process (scroll a bit below) I have to say something that everyone keeps asking me, is it profitable? Yes. It's by far my most profitable venture outside of my regular 9-5... But it took a lot of work, delegation and building processes to get here. So the one thing I would love to get out of this post - if you have any insights, feedback or tools I might be missing out post them below and let's help each other out. Now, how you can get started with (AI) YouTube automation: Pick a topic that is BOTH: a) in demand b) interesting to you & you have knowledge about Do everything yourself at first - delegate later No one cares about the videos as much as you do, so make sure to nail the ideation, scripts, editing, format and packaging yourself first. Now that we got that out of the way: Use this workflow: VidIQ - outliers sections is pure gold, I use it all the time to find trending video packaging, topics, etc. ChatGPT or Claude - high level video ideas at scale and your assistant (I use projects inside ChatGPT and its really good at managing and prioritizing). If you are using it for scripts please for the love of god, make final edits yourself by hand. Add character, personal insights, ideas, etc. Katalist AI - all in one video generator tool I use to quickly go from video idea to script, storyboard, AI voiceover and then final visuals. It's surprisingly good and to make a decent video it only takes about 1-2 hours in TOTAL. Once you understand how it works and have a process, delegate to tech savvy VAs / content creators for $5-$15/hour and you have final, good quality videos for less than $30. Pikzels / Krea AI - your AI thumbnail generator, I dont remember the last time we used Photoshop outside of quick text or image edits. Its basically AI image manipulation at scale and it costs 10-30x less than a human thumbnail designer and the thumbnails are really good. VidIQ+TubeBuddy - titles & optimization, but you have to know that most of the views come usually from recommended, so dont over obsess and add 392x keywords in your title and description. Its all about the packaging. Now whats left is track performance & iterate - it's practically impossible to nail it the first few times, but each video you make look at the data (not just in YT studio) and UNDERSTAND why it did not perform as well as you thought it would. Regarding monetization, adsense sucks - sell digital products. If I was relying on adsense alone I would never ever be profitable, but selling mini digital products and mentioning CTAs in the actual video not just in the description makes this super profitable and scaleable, especially since video production is so cheap. Final thoughts: (AI) YouTube automation absolutely works, but it’s not an overnight success or a total hands-off cashcow machine. It’s a real business and you need systems, consistent effort, iteration, failing and learning along the way. If you’ve got any tips, hidden gems or tools I might be missing, drop them below & let’s help each other out.

[D] Why I'm Lukewarm on Graph Neural Networks

TL;DR: GNNs can provide wins over simpler embedding methods, but we're at a point where other research directions matter more I also posted it on my blog here, has footnotes, a nicer layout with inlined images, etc. I'm only lukewarm on Graph Neural Networks (GNNs). There, I said it. It might sound crazy GNNs are one of the hottest fields in machine learning right now. [There][1] were at least [four][2] [review][3] [papers][4] just in the last few months. I think some progress can come of this research, but we're also focusing on some incorrect places. But first, let's take a step back and go over the basics. Models are about compression We say graphs are a "non-euclidean" data type, but that's not really true. A regular graph is just another way to think about a particular flavor of square matrix called the [adjacency matrix][5], like this. It's weird, we look at run-of-the-mill matrix full of real numbers and decide to call it "non-euclidean". This is for practical reasons. Most graphs are fairly sparse, so the matrix is full of zeros. At this point, where the non-zero numbers are matters most, which makes the problem closer to (computationally hard) discrete math rather than (easy) continuous, gradient-friendly math. If you had the full matrix, life would be easy If we step out of the pesky realm of physics for a minute, and assume carrying the full adjacency matrix around isn't a problem, we solve a bunch of problems. First, network node embeddings aren't a thing anymore. A node is a just row in the matrix, so it's already a vector of numbers. Second, all network prediction problems are solved. A powerful enough and well-tuned model will simply extract all information between the network and whichever target variable we're attaching to nodes. NLP is also just fancy matrix compression Let's take a tangent away from graphs to NLP. Most NLP we do can be [thought of in terms of graphs][6] as we'll see, so it's not a big digression. First, note that Ye Olde word embedding models like [Word2Vec][7] and [GloVe][8] are [just matrix factorization][9]. The GloVe algorithm works on a variation of the old [bag of words][10] matrix. It goes through the sentences and creates a (implicit) [co-occurence][11] graph where nodes are words and the edges are weighed by how often the words appear together in a sentence. Glove then does matrix factorization on the matrix representation of that co-occurence graph, Word2Vec is mathematically equivalent. You can read more on this in my [post on embeddings][12] and the one (with code) on [word embeddings][13]. Even language models are also just matrix compression Language models are all the rage. They dominate most of the [state of the art][14] in NLP. Let's take BERT as our main example. BERT predicts a word given the context of the rest of the sentence. This grows the matrix we're factoring from flat co-occurences on pairs of words to co-occurences conditional on the sentence's context, like this We're growing the "ideal matrix" we're factoring combinatorially. As noted by [Hanh & Futrell][15]: [...] human language—and language modelling—has infinite statistical complexity but that it can be approximated well at lower levels. This observation has two implications: 1) We can obtain good results with comparatively small models; and 2) there is a lot of potential for scaling up our models. Language models tackle such a large problem space that they probably approximate a compression of the entire language in the [Kolmogorov Complexity][16] sense. It's also possible that huge language models just [memorize a lot of it][17] rather than compress the information, for what it's worth. Can we upsample any graph like language models do? We're already doing it. Let's call a first-order embedding of a graph a method that works by directly factoring the graph's adjacency matrix or [Laplacian matrix][18]. If you embed a graph using [Laplacian Eigenmaps][19] or by taking the [principal components][20] of the Laplacian, that's first order. Similarly, GloVe is a first-order method on the graph of word co-occurences. One of my favorites first order methods for graphs is [ProNE][21], which works as well as most methods while being two orders of magnitude faster. A higher-order method embeds the original matrix plus connections of neighbours-of-neighbours (2nd degree) and deeper k-step connections. [GraRep][22], shows you can always generate higher-order representations from first order methods by augmenting the graph matrix. Higher order method are the "upsampling" we do on graphs. GNNs that sample on large neighborhoods and random-walk based methods like node2vec are doing higher-order embeddings. Where are the performance gain? Most GNN papers in the last 5 years present empirical numbers that are useless for practitioners to decide on what to use. As noted in the [OpenGraphsBenchmark][4] (OGB) paper, GNN papers do their empirical section on a handful of tiny graphs (Cora, CiteSeer, PubMed) with 2000-20,000 nodes. These datasets can't seriously differentiate between methods. Recent efforts are directly fixing this, but the reasons why researchers focused on tiny, useless datasets for so long are worth discussing. Performance matters by task One fact that surprises a lot of people is that even though language models have the best performance in a lot of NLP tasks, if all you're doing is cram sentence embeddings into a downstream model, there [isn't much gained][23] from language models embeddings over simple methods like summing the individual Word2Vec word embeddings (This makes sense, because the full context of the sentence is captured in the sentence co-occurence matrix that is generating the Word2Vec embeddings). Similarly, [I find][24] that for many graphs simple first-order methods perform just as well on graph clustering and node label prediction tasks than higher-order embedding methods. In fact higher-order methods are massively computationally wasteful for these usecases. Recommended first order embedding methods are ProNE and my [GGVec with order=1][25]. Higher order methods normally perform better on the link prediction tasks. I'm not the only one to find this. In the BioNEV paper, they find: "A large GraRep order value for link prediction tasks (e.g. 3, 4);a small value for node classification tasks (e.g.1, 2)" (p.9). Interestingly, the gap in link prediction performance is inexistant for artificially created graphs. This suggests higher order methods do learn some of the structure intrinsic to [real world graphs][26]. For visualization, first order methods are better. Visualizations of higher order methods tend to have artifacts of their sampling. For instance, Node2Vec visualizations tend to have elongated/filament-like structures which come from the embeddings coming from long single strand random walks. See the following visualizations by [Owen Cornec][27] created by first embedding the graph to 32-300 dimensions using a node embedding algorithm, then mapping this to 2d or 3d with the excellent UMAP algorithm, like this Lastly, sometimes simple methods soundly beat higher order methods (there's an instance of it in the OGB paper). The problem here is that we don't know when any method is better than another and we definitely don't know the reason. There's definitely a reason different graph types respond better/worse to being represented by various methods. This is currently an open question. A big part of why is that the research space is inundated under useless new algorithms because... Academic incentives work against progress Here's the cynic's view of how machine learning papers are made: Take an existing algorithm Add some new layer/hyperparameter, make a cute mathematical story for why it matters Gridsearch your hyperparameters until you beat baselines from the original paper you aped Absolutely don't gridsearch stuff you're comparing against in your results section Make a cute ACRONYM for your new method, put impossible to use python 2 code on github (Or no code at all!) and bask in the citations I'm [not][28] the [only one][29] with these views on the state reproducible research. At least it's gotten slightly better in the last 2 years. Sidebar: I hate Node2Vec A side project of mine is a [node embedding library][25] and the most popular method in it is by far Node2Vec. Don't use Node2Vec. [Node2Vec][30] with p=1; q=1 is the [Deepwalk][31] algorithm. Deepwalk is an actual innovation. The Node2Vec authors closely followed the steps 1-5 including bonus points on step 5 by getting word2vec name recognition. This is not academic fraud -- the hyperparameters [do help a tiny bit][32] if you gridsearch really hard. But it's the presentable-to-your-parents sister of where you make the ML community worse off to progress your academic career. And certainly Node2Vec doesn't deserve 7500 citations. Progress is all about practical issues We've known how to train neural networks for well over 40 years. Yet they only exploded in popularity with [AlexNet][33] in 2012. This is because implementations and hardware came to a point where deep learning was practical. Similarly, we've known about factoring word co-occurence matrices into Word embeddings for at least 20 years. But word embeddings only exploded in 2013 with Word2Vec. The breakthrough here was that the minibatch-based methods let you train a Wikipedia-scale embedding model on commodity hardware. It's hard for methods in a field to make progress if training on a small amount of data takes days or weeks. You're disincentivized to explore new methods. If you want progress, your stuff has to run in reasonable time on commodity hardware. Even Google's original search algorithm [initially ran on commodity hardware][34]. Efficiency is paramount to progress The reason deep learning research took off the way it did is because of improvements in [efficiency][35] as well as much better libraries and hardware support. Academic code is terrible Any amount of time you spend gridsearching Node2Vec on p and q is all put to better use gridsearching Deepwalk itself (on number of walks, length of walks, or word2vec hyperparameters). The problem is that people don't gridsearch over deepwalk because implementations are all terrible. I wrote the [Nodevectors library][36] to have a fast deepwalk implementation because it took 32 hours to embed a graph with a measly 150,000 nodes using the reference Node2Vec implementation (the same takes 3min with Nodevectors). It's no wonder people don't gridsearch on Deepwalk a gridsearch would take weeks with the terrible reference implementations. To give an example, in the original paper of [GraphSAGE][37] they their algorithm to DeepWalk with walk lengths of 5, which is horrid if you've ever hyperparameter tuned a deepwalk algorithm. From their paper: We did observe DeepWalk’s performance could improve with further training, and in some cases it could become competitive with the unsupervised GraphSAGE approaches (but not the supervised approaches) if we let it run for >1000× longer than the other approaches (in terms of wall clock time for prediction on the test set) I don't even think the GraphSAGE authors had bad intent -- deepwalk implementations are simply so awful that they're turned away from using it properly. It's like trying to do deep learning with 2002 deep learning libraries and hardware. Your architectures don't really matter One of the more important papers this year was [OpenAI's "Scaling laws"][38] paper, where the raw number of parameters in your model is the most predictive feature of overall performance. This was noted even in the original BERT paper and drives 2020's increase in absolutely massive language models. This is really just [Sutton' Bitter Lesson][39] in action: General methods that leverage computation are ultimately the most effective, and by a large margin Transformers might be [replacing convolution][40], too. As [Yannic Kilcher said][41], transformers are ruining everything. [They work on graphs][6], in fact it's one of the [recent approaches][42], and seems to be one of the more succesful [when benchmarked][1] Researchers seem to be putting so much effort into architecture, but it doesn't matter much in the end because you can approximate anything by stacking more layers. Efficiency wins are great -- but neural net architectures are just one way to achieve that, and by tremendously over-researching this area we're leaving a lot of huge gains elsewhere on the table. Current Graph Data Structure Implementations suck NetworkX is a bad library. I mean, it's good if you're working on tiny graphs for babies, but for anything serious it chokes and forces you to rewrite everything in... what library, really? At this point most people working on large graphs end up hand-rolling some data structure. This is tough because your computer's memory is a 1-dimensional array of 1's and 0's and a graph has no obvious 1-d mapping. This is even harder when we take updating the graph (adding/removing some nodes/edges) into account. Here's a few options: Disconnected networks of pointers NetworkX is the best example. Here, every node is an object with a list of pointers to other nodes (the node's edges). This layout is like a linked list. Linked lists are the [root of all performance evil][43]. Linked lists go completely against how modern computers are designed. Fetching things from memory is slow, and operating on memory is fast (by two orders of magnitude). Whenever you do anything in this layout, you make a roundtrip to RAM. It's slow by design, you can write this in Ruby or C or assembly and it'll be slow regardless, because memory fetches are slow in hardware. The main advantage of this layout is that adding a new node is O(1). So if you're maintaining a massive graph where adding and removing nodes happens as often as reading from the graph, it makes sense. Another advantage of this layout is that it "scales". Because everything is decoupled from each other you can put this data structure on a cluster. However, you're really creating a complex solution for a problem you created for yourself. Sparse Adjacency Matrix This layout great for read-only graphs. I use it as the backend in my [nodevectors][25] library, and many other library writers use the [Scipy CSR Matrix][44], you can see graph algorithms implemented on it [here][45]. The most popular layout for this use is the [CSR Format][46] where you have 3 arrays holding the graph. One for edge destinations, one for edge weights and an "index pointer" which says which edges come from which node. Because the CSR layout is simply 3 arrays, it scales on a single computer: a CSR matrix can be laid out on a disk instead of in-memory. You simply [memory map][47] the 3 arrays and use them on-disk from there. With modern NVMe drives random seeks aren't slow anymore, much faster than distributed network calls like you do when scaling the linked list-based graph. I haven't seen anyone actually implement this yet, but it's in the roadmap for my implementation at least. The problem with this representation is that adding a node or edge means rebuilding the whole data structure. Edgelist representations This representation is three arrays: one for the edge sources, one for the edge destinations, and one for edge weights. [DGL][48] uses this representation internally. This is a simple and compact layout which can be good for analysis. The problem compared to CSR Graphs is some seek operations are slower. Say you want all the edges for node #4243. You can't jump there without maintaining an index pointer array. So either you maintain sorted order and binary search your way there (O(log2n)) or unsorted order and linear search (O(n)). This data structure can also work on memory mapped disk array, and node append is fast on unsorted versions (it's slow in the sorted version). Global methods are a dead end Methods that work on the entire graph at once can't leverage computation, because they run out of RAM at a certain scale. So any method that want a chance of being the new standard need to be able to update piecemeal on parts of the graph. Sampling-based methods Sampling Efficiency will matter more in the future Edgewise local methods. The only algorithms I know of that do this are GloVe and GGVec, which they pass through an edge list and update embedding weights on each step. The problem with this approach is that it's hard to use them for higher-order methods. The advantage is that they easily scale even on one computer. Also, incrementally adding a new node is as simple as taking the existing embeddings, adding a new one, and doing another epoch over the data Random Walk sampling. This is used by deepwalk and its descendants, usually for node embeddings rather than GNN methods. This can be computationally expensive and make it hard to add new nodes. But this does scale, for instance [Instagram][49] use it to feed their recommendation system models Neighbourhood sampling. This is currently the most common one in GNNs, and can be low or higher order depending on the neighborhood size. It also scales well, though implementing efficiently can be challenging. It's currently used by [Pinterest][50]'s recommendation algorithms. Conclusion Here are a few interesting questions: What is the relation between graph types and methods? Consolidated benchmarking like OGB We're throwing random models at random benchmarks without understanding why or when they do better More fundamental research. Heree's one I'm curious about: can other representation types like [Poincarre Embeddings][51] effectively encode directed relationships? On the other hand, we should stop focusing on adding spicy new layers to test on the same tiny datasets. No one cares. [1]: https://arxiv.org/pdf/2003.00982.pdf [2]: https://arxiv.org/pdf/2002.11867.pdf [3]: https://arxiv.org/pdf/1812.08434.pdf [4]: https://arxiv.org/pdf/2005.00687.pdf [5]: https://en.wikipedia.org/wiki/Adjacency_matrix [6]: https://thegradient.pub/transformers-are-graph-neural-networks/ [7]: https://en.wikipedia.org/wiki/Word2vec [8]: https://nlp.stanford.edu/pubs/glove.pdf [9]: https://papers.nips.cc/paper/2014/file/feab05aa91085b7a8012516bc3533958-Paper.pdf [10]: https://en.wikipedia.org/wiki/Bag-of-words_model [11]: https://en.wikipedia.org/wiki/Co-occurrence [12]: https://www.singlelunch.com/2020/02/16/embeddings-from-the-ground-up/ [13]: https://www.singlelunch.com/2019/01/27/word-embeddings-from-the-ground-up/ [14]: https://nlpprogress.com/ [15]: http://socsci.uci.edu/~rfutrell/papers/hahn2019estimating.pdf [16]: https://en.wikipedia.org/wiki/Kolmogorov_complexity [17]: https://bair.berkeley.edu/blog/2020/12/20/lmmem/ [18]: https://en.wikipedia.org/wiki/Laplacian_matrix [19]: http://citeseerx.ist.psu.edu/viewdoc/download;jsessionid=1F03130B02DC485C78BF364266B6F0CA?doi=10.1.1.19.8100&rep=rep1&type=pdf [20]: https://en.wikipedia.org/wiki/Principalcomponentanalysis [21]: https://www.ijcai.org/Proceedings/2019/0594.pdf [22]: https://dl.acm.org/doi/10.1145/2806416.2806512 [23]: https://openreview.net/pdf?id=SyK00v5xx [24]: https://github.com/VHRanger/nodevectors/blob/master/examples/link%20prediction.ipynb [25]: https://github.com/VHRanger/nodevectors [26]: https://arxiv.org/pdf/1310.2636.pdf [27]: http://byowen.com/ [28]: https://arxiv.org/pdf/1807.03341.pdf [29]: https://www.youtube.com/watch?v=Kee4ch3miVA [30]: https://cs.stanford.edu/~jure/pubs/node2vec-kdd16.pdf [31]: https://arxiv.org/pdf/1403.6652.pdf [32]: https://arxiv.org/pdf/1911.11726.pdf [33]: https://en.wikipedia.org/wiki/AlexNet [34]: https://en.wikipedia.org/wiki/Googledatacenters#Original_hardware [35]: https://openai.com/blog/ai-and-efficiency/ [36]: https://www.singlelunch.com/2019/08/01/700x-faster-node2vec-models-fastest-random-walks-on-a-graph/ [37]: https://arxiv.org/pdf/1706.02216.pdf [38]: https://arxiv.org/pdf/2001.08361.pdf [39]: http://incompleteideas.net/IncIdeas/BitterLesson.html [40]: https://arxiv.org/abs/2010.11929 [41]: https://www.youtube.com/watch?v=TrdevFK_am4 [42]: https://arxiv.org/pdf/1710.10903.pdf [43]: https://www.youtube.com/watch?v=fHNmRkzxHWs [44]: https://docs.scipy.org/doc/scipy/reference/generated/scipy.sparse.csr_matrix.html [45]: https://docs.scipy.org/doc/scipy/reference/sparse.csgraph.html [46]: https://en.wikipedia.org/wiki/Sparsematrix#Compressedsparserow(CSR,CRSorYaleformat) [47]: https://en.wikipedia.org/wiki/Mmap [48]: https://github.com/dmlc/dgl [49]: https://ai.facebook.com/blog/powered-by-ai-instagrams-explore-recommender-system/ [50]: https://medium.com/pinterest-engineering/pinsage-a-new-graph-convolutional-neural-network-for-web-scale-recommender-systems-88795a107f48 [51]: https://arxiv.org/pdf/1705.08039.pdf

[P] Can you distinguish AI-generated content from real art or literature? I made a little test!

Hi everyone, I am no programmer, and I have a very basic knowledge of machine learning, but I am fascinated by the possibilities offered by all the new models we have seen so far. Some people around me say they are not that impressed by what AIs can do, so I built a small test (with a little help by chatGPT to code the whole thing): can you always 100% distinguish between AI art or text and old works of art or literature? Here is the site: http://aiorart.com/ I find that AI-generated text is still generally easy to spot, but of course it is very challenging to go against great literary works. AI images can sometimes be truly deceptive. I wonder what you will all think of it... and how all that will evolve in the coming months! PS: The site is very crude (again, I am no programmer!). It works though.

[P] [R] sANNd: A New Neural Network Framework Using Trainable Iterators

sANNd sANNd is a lightweight, modular neural network library designed as a sandbox for experimenting with new ideas in artificial intelligence. The Mould Class: A Pythonic Building Block The Mould class is a core component of sANNd. It provides a Pythonic way to apply functions to data that’s bundled inside objects: Encapsulated Variables: Each Mould object holds a set of variables (for example, weights or parameters) inside it. This means related data is kept together in one place (the object), making the code organized and intuitive. Static Functions: A Mould class defines its operation as a static method – essentially a function that isn’t tied to a specific instance. This static function takes in inputs (and possibly other Mould objects’ variables) and produces an output. In simple terms, the Mould’s static method describes how to transform input data using the Mould’s internal variables. Pythonic Usage: Using static methods in this way is a clean, Pythonic design. You call the Mould’s function through the class, but it applies to the data in the object. This approach lets you clearly separate what the operation is (the logic in the static function) from which data it uses (the variables inside the Mould instance). Example: Imagine a Mould class called LinearMould that has a static function to compute a linear transformation (like y = W*x + b). An instance of LinearMould would hold specific W and b values, and you’d use the static method to apply that linear formula to an input. This gives you the convenience of object-oriented design (encapsulating W and b) with the clarity of a standalone function defining the math. Chaining Moulds for Complex Computations Moulds become even more powerful when you chain them together. You can connect multiple Moulds so that the output of one becomes the input of the next: Sequential Operations: Just like stacking layers in a neural network, you can place Moulds in sequence. For example, you might take the output from LinearMouldA and feed it into LinearMouldB. In code, this might look as simple as using the output of one call as the argument to the next. The design of sANNd makes this straightforward – the static function of each Mould knows how to handle the data coming in. Building Pipelines: By chaining Moulds, you create a pipeline of transformations. Each Mould handles one step of computation, and together they produce a final result. This could represent a multi-layer neural network, a data processing pipeline, or any custom sequence of operations you need. There’s no strict limit to how you can chain them; you have the freedom to combine Moulds in any order that makes sense for your experiment. Clarity and Modularity: Because each Mould is a self-contained piece (with its variables and function), chaining them doesn’t turn your code into a black box. You can inspect or modify any part of the chain easily. This modular design means you can insert, remove, or replace Moulds to see how it affects the overall computation, which is great for experimentation. Implicit Backward Path (Automatic Backpropagation) One major benefit of using chained Moulds is that they implicitly define the backward path for training with gradient descent (backpropagation): Automatic Gradient Flow: When you connect Moulds in a sequence for a forward pass (input → Mould A → Mould B → output), you’ve essentially defined a computation graph. sANNd uses this graph to handle the reverse computation automatically. In other words, if you calculate an error or loss based on the final output, sANNd can propagate that error backwards through each Mould in the chain. No Manual Backprop: You do not need to manually code how gradients flow through each Mould. The way you set up the Moulds’ static functions already determines how outputs depend on inputs and internal variables. sANNd leverages that to perform backpropagation. This is similar in spirit to how libraries like PyTorch/TF do “autograd,” but here it’s a natural result of the Mould chain architecture. Gradient Descent Ready: Because the backward path is established by the forward connections, you can apply gradient descent optimizations out of the box. For instance, you can adjust the weights inside each Mould based on the computed gradients to minimize your loss. The design ensures that each Mould’s contribution to the final error is tracked, so all parts of your model learn appropriately during training. In short, defining your model with Moulds means you get training capability for free. You focus on describing the forward computations, and sANNd handles the math behind learning from errors. Comparing sANNd to Traditional Frameworks sANNd’s approach is quite different from traditional Python-based neural network frameworks. Here’s how it stacks up against frameworks like TensorFlow, PyTorch, or Keras in terms of approach, flexibility, and intended use: Design Approach: Traditional frameworks use predefined layer classes and often build a computation graph behind the scenes. For example, Keras might have a Dense layer class, and TensorFlow might construct a static graph (in TF1) or use eager execution (in TF2). sANNd takes a simpler approach – it uses plain Python classes and static functions (Moulds) to define computations. There’s no need to learn a new graph syntax or decorators; if you know Python functions and classes, you can read and write sANNd models. This makes the internal workings more transparent and easier to follow. Flexibility: While frameworks like PyTorch and TensorFlow are very powerful, they can introduce a lot of boilerplate and assume you’re building typical architectures. sANNd is extremely modular and flexible. You aren’t limited to the layers someone else defined – you can create any operation you want as a Mould. Want to experiment with a novel activation function or a custom recurrent connection? Just define it in a Mould. There’s less magic and abstraction obscuring your code, so unconventional model structures are easier to implement. (Of course, major frameworks can also be extended, but sANNd makes this feel more natural by staying within standard Python paradigms.) Intended Use: sANNd is intended for experimentation and research. It’s like a toolkit for tinkering. You get fine-grained control over every part of the network, which is ideal for trying out bold new ideas that don’t fit the mold of common deep learning models. In contrast, TensorFlow/PyTorch shine in production environments and large-scale training – they are optimized (GPU support, highly efficient tensor operations) and come with many utilities for things like data loading, distributed training, etc. sANNd doesn’t aim to replace them for those heavy-lifting tasks. Instead, it’s meant for when you need a lighter, more interpretable setup to prototype concepts. You might use sANNd to prove out a concept or test a hypothesis in AI research, and later switch to a bigger framework if you need to scale it up. Simplicity vs. Complexity: By design, sANNd keeps things simple. The trade-off is that it might not have the raw performance optimizations of the large frameworks. However, this simplicity is a feature – it means the code is easier to understand and modify. For many research scenarios, being able to quickly tweak an idea is more important than squeezing out maximum speed. Traditional frameworks, with their complexity, can sometimes be harder to adapt for radically different ideas (you might find yourself fighting the framework). With sANNd, the framework gets out of your way as much as possible. Modular and Experimental by Nature One of the driving philosophies of sANNd is to be modular and experimental, to further ML research: Modularity: sANNd is built from small, composable pieces. The Mould class is one such piece, and you can imagine building additional components in a similar spirit. This modular design means you can re-use components, mix and match them, or replace one implementation with another without affecting the rest of your system. It’s like having a box of building blocks for neural networks – you can assemble them in standard ways or in completely novel configurations. Experimentation Friendly: Because it avoids heavy abstraction, sANNd lets you directly see and control what’s happening at each step. This is great for research, where you might need to observe intermediate results, inject custom behavior, or adjust the learning process on the fly. sANNd’s straightforward structure (Python objects and functions) makes such interventions possible. You’re not constrained to a fixed training loop or forced to use certain layer types. True Intelligence Research: Achieving “True Intelligence” (often related to artificial general intelligence or other forms of broader AI) may require going beyond the usual neural network designs. sANNd aims to be a playground for these ideas. Its flexibility allows researchers to integrate unconventional elements — be it new memory structures, dynamic connection patterns, or hybrid models that combine symbolic and neural approaches. You can use sANNd to prototype these offbeat ideas quickly. In essence, it’s easier to test “what if we try this?” scenarios with sANNd than with more rigid frameworks. In summary, sANNd’s unique Mould class and design philosophy offer a fresh take on building neural networks. It emphasizes clarity, composability, and flexibility, allowing you to focus on creativity and understanding. Whether you’re stacking simple Moulds into a deep model, or inventing a completely new form of network, sANNd provides a friendly foundation. It’s not here to dethrone TensorFlow or PyTorch in industry applications – instead, it’s here to give researchers and enthusiasts a more malleable tool for exploring the frontiers of AI. Enjoy using sANNd as your neural network sandbox, and happy experimenting!

[P] How I found & fixed 4 bugs in Microsoft's Phi-4 model

Hey r/MachineLearning! Last week, Microsoft released Phi-4, a 14B open-source model that rivals OpenAI's GPT-4-o-mini. I managed to find & fix 4 bugs impacting its output quality. You might remember me previously from fixing 8 bugs in Google's Gemma model! :) I'm going to walk you through how I found & fixed the bugs. Phi-4's benchmarks were amazing, however many users reported weird or just wrong outputs. Since I maintain the open-source project called 'Unsloth' (fine-tuning LLMs 2x faster with 70% less VRAM) with my brother, I firstly tested Phi-4 for inference and found many errors. Our GitHub repo: https://github.com/unslothai/unsloth This time, the model had no implementation issues (unlike Gemma 2) but did have problems in the model card. For my first inference run, I randomly found an extra token which is obviously incorrect (2 eos tokens is never a good idea). Also during more runs, I found there was an extra assistant prompt which is once again incorrect. And, lastly, from past experience with Unsloth's bug fixes, I already knew fine-tuning was wrong when I read the code. These bugs caused Phi-4 to have some drop in accuracy and also broke fine-tuning runs. Our fixes are now under review by Microsoft to be officially added to Hugging Face. We uploaded the fixed versions to https://huggingface.co/unsloth/phi-4-GGUF Here’s a breakdown of the bugs and their fixes: Tokenizer bug fixes The Phi-4 tokenizer interestingly uses as the BOS (beginning of sentence), EOS (end of sentence) and PAD (padding) tokens. The main issue is the EOS token is wrong - it should be . Otherwise, you will get in generations. Fine-tuning bug fixes The padding token should be a designated pad token like in Llama () or we can use an untrained token - for example we use , fixing infinite generations and outputs. Chat template issues The Phi-4 tokenizer always adds an assistant prompt - it should only do this if prompted by add\generation\prompt. Most LLM serving libraries expect non auto assistant additions, and this might cause issues during serving. We dive deeper into the bugs in our blog: https://unsloth.ai/blog/phi4 Do our Fixes Work? Yes! Our fixed Phi-4 uploads show clear performance gains, with even better scores than Microsoft's original uploads on the Open LLM Leaderboard. https://preview.redd.it/d8hew26e06ce1.png?width=2366&format=png&auto=webp&s=173c23feacc625566271470839fe7a5e25eb860e Some redditors even tested our fixes to show greatly improved results in: Example 1: Multiple-choice tasks https://preview.redd.it/qx50pkq706ce1.png?width=1579&format=png&auto=webp&s=437da2cabdbf98ef5a8b8cbdc5592907a20e2316 Example 2: ASCII art generation https://preview.redd.it/sw1o3a3yt4de1.png?width=2326&format=png&auto=webp&s=fc6bfc45d14134d45f332ba58bbd1de049f5776b We also made a Colab notebook fine-tune Phi-4 completely for free using Google's free Tesla T4 (16GB) GPUs: https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Phi\4-Conversational.ipynb Thank you for reading this long post and hope you all found this insightful! If you have any questions, please feel free to ask! :) How I found the bugs: I first downloaded the original Phi-4 from https://huggingface.co/microsoft/phi-4, and tested inference out. Weirdly I found assistant to be appended at the even with addgenerationprompt = False in Hugging Face, so I theorized there was a chat template problem. Adding assistant prompts by default can break serving libraries. And yes, https://huggingface.co/microsoft/phi-4/blob/f957856cd926f9d681b14153374d755dd97e45ed/tokenizer\config.json#L774 had by default added the assistant prompt - I first fixed this! I then found ` to be used for the BOS, EOS and PAD tokens, which is a common issue amongst models - I ignored the BOS, since Phi-4 did not have one anyways, but changed the PAD token to `. You can select any of the tokens since they're empty and not trained. This counteracts issues of infinite generations during finetuning. For Llama-fication, I used torch.allclose to confirm all tensors are in fact equivalent. I also used some fake random data to check all activations are also mostly similar bitwise. I also uploaded the model to the HF Open LLM Leaderboard to confirm if the original Phi-4 arch and the new Llama-fied models are equivalent. Finally I verified all finetuning runs with Unsloth in a Colab Notebook to confirm all runs were correct.

[Discussion] When ML and Data Science are the death of a good company: A cautionary tale.

TD;LR: At Company A, Team X does advanced analytics using on-prem ERP tools and older programming languages. Their tools work very well and are designed based on very deep business and domain expertise. Team Y is a new and ambitious Data Science team that thinks they can replace Team X's tools with a bunch of R scripts and a custom built ML platform. Their models are simplistic, but more "fashionable" compared to the econometric models used by Team X, and team Y benefits from the ML/DS moniker so leadership is allowing Team Y to start a large scale overhaul of the analytics platform in question. Team Y doesn't have the experience for such a larger scale transformation, and is refusing to collaborate with team X. This project is very likely going to fail, and cause serious harm to the company as a whole financially and from a people perspective. I argue that this is not just because of bad leadership, but also because of various trends and mindsets in the DS community at large. Update (Jump to below the line for the original story): Several people in the comments are pointing out that this just a management failure, not something due to ML/DS, and that you can replace DS with any buzz tech and the story will still be relevant. My response: Of course, any failure at an organization level is ultimately a management failure one way or the other. Moreover, it is also the case that ML/DS when done correctly, will always improve a company's bottom line. There is no scenario where the proper ML solution, delivered at a reasonable cost and in a timely fashion, will somehow hurt the company's bottom line. My point is that in this case management is failing because of certain trends and practices that are specific to the ML/DS community, namely: The idea that DS teams should operate independently of tech and business orgs -- too much autonomy for DS teams The disregard for domain knowledge that seems prevalent nowadays thanks to the ML hype, that DS can be generalists and someone with good enough ML chops can solve any business problem. That wasn't the case when I first left academia for the industry in 2009 (back then nobody would even bother with a phone screen if you didn't have the right domain knowledge). Over reliance on resources who check all the ML hype related boxes (knows Python, R, Tensorflow, Shiny, etc..., has the right Coursera certifications, has blogged on the topic, etc...), but are lacking in depth of experience. DS interviews nowadays all seem to be: Can you tell me what a p-value is? What is elastic net regression? Show me how to fit a model in sklearn? How do you impute NAs in an R dataframe? Any smart person can look those up on Stackoverflow or Cross-Validated,.....Instead teams should be asking stuff like: why does portfolio optimization use QP not LP? How does a forecast influence a customer service level? When should a recommendation engine be content based and when should it use collaborative filtering? etc... (This is a true story, happening to the company I currently work for. Names, domains, algorithms, and roles have been shuffled around to protect my anonymity)  Company A has been around for several decades. It is not the biggest name in its domain, but it is a well respected one. Risk analysis and portfolio optimization have been a core of Company A's business since the 90s. They have a large team of 30 or so analysts who perform those tasks on a daily basis. These analysts use ERP solutions implemented for them by one the big ERP companies (SAP, Teradata, Oracle, JD Edwards,...) or one of the major tech consulting companies (Deloitte, Accenture, PWC, Capgemini, etc...) in collaboration with their own in house engineering team. The tools used are embarrassingly old school: Classic RDBMS running on on-prem servers or maybe even on mainframes, code written in COBOL, Fortran, weird proprietary stuff like ABAP or SPSS.....you get the picture. But the models and analytic functions were pretty sophisticated, and surprisingly cutting edge compared to the published academic literature. Most of all, they fit well with the company's enterprise ecosystem, and were honed based on years of deep domain knowledge.  They have a tech team of several engineers (poached from the aforementioned software and consulting companies) and product managers (who came from the experienced pools of analysts and managers who use the software, or poached from business rivals) maintaining and running this software. Their technology might be old school, but collectively, they know the domain and the company's overall architecture very, very well. They've guided the company through several large scale upgrades and migrations and they have a track record of delivering on time, without too much overhead. The few times they've stumbled, they knew how to pick themselves up very quickly. In fact within their industry niche, they have a reputation for their expertise, and have very good relations with the various vendors they've had to deal with. They were the launching pad of several successful ERP consulting careers.  Interestingly, despite dealing on a daily basis with statistical modeling and optimization algorithms, none of the analysts, engineers, or product managers involved describe themselves as data scientists or machine learning experts. It is mostly a cultural thing: Their expertise predates the Data Science/ML hype that started circa 2010, and they got most of their chops using proprietary enterprise tools instead of the open source tools popular nowadays. A few of them have formal statistical training, but most of them came from engineering or domain backgrounds and learned stats on the fly while doing their job. Call this team "Team X".  Sometime around the mid 2010s, Company A started having some serious anxiety issues: Although still doing very well for a company its size, overall economic and demographic trends were shrinking its customer base, and a couple of so called disruptors came up with a new app and business model that started seriously eating into their revenue. A suitable reaction to appease shareholders and Wall Street was necessary. The company already had a decent website and a pretty snazzy app, what more could be done? Leadership decided that it was high time that AI and ML become a core part of the company's business. An ambitious Manager, with no science or engineering background, but who had very briefly toyed with a recommender system a couple of years back, was chosen to build a data science team, call it team "Y" (he had a bachelor's in history from the local state college and worked for several years in the company's marketing org). Team "Y" consists mostly of internal hires who decided they wanted to be data scientists and completed a Coursera certification or a Galvanize boot camp, before being brought on to the team, along with a few of fresh Ph.D or M.Sc holders who didn't like academia and wanted to try their hand at an industry role. All of them were very bright people, they could write great Medium blog posts and give inspiring TED talks, but collectively they had very little real world industry experience. As is the fashion nowadays, this group was made part of a data science org that reported directly to the CEO and Board, bypassing the CIO and any tech or business VPs, since Company A wanted to claim the monikers "data driven" and "AI powered" in their upcoming shareholder meetings. In 3 or 4 years of existence, team Y produced a few Python and R scripts. Their architectural experience  consisted almost entirely in connecting Flask to S3 buckets or Redshift tables, with a couple of the more resourceful ones learning how to plug their models into Tableau or how to spin up a Kuberneties pod.  But they needn't worry: The aforementioned manager, who was now a director (and was also doing an online Masters to make up for his qualifications gap and bolster his chances of becoming VP soon - at least he now understands what L1 regularization is), was a master at playing corporate politics and self-promotion. No matter how few actionable insights team Y produced or how little code they deployed to production, he always had their back and made sure they had ample funding. In fact he now had grandiose plans for setting up an all-purpose machine learning platform that can be used to solve all of the company's data problems.  A couple of sharp minded members of team Y, upon googling their industry name along with the word "data science", realized that risk analysis was a prime candidate for being solved with Bayesian models, and there was already a nifty R package for doing just that, whose tutorial they went through on R-Bloggers.com. One of them had even submitted a Bayesian classifier Kernel for a competition on Kaggle (he was 203rd on the leaderboard), and was eager to put his new-found expertise to use on a real world problem. They pitched the idea to their director, who saw a perfect use case for his upcoming ML platform. They started work on it immediately, without bothering to check whether anybody at Company A was already doing risk analysis. Since their org was independent, they didn't really need to check with anybody else before they got funding for their initiative. Although it was basically a Naive Bayes classifier, the term ML was added to the project tile, to impress the board.  As they progressed with their work however, tensions started to build. They had asked the data warehousing and CA analytics teams to build pipelines for them, and word eventually got out to team X about their project. Team X was initially thrilled: They offered to collaborate whole heartedly, and would have loved to add an ML based feather to their already impressive cap. The product owners and analysts were totally onboard as well: They saw a chance to get in on the whole Data Science hype that they kept hearing about. But through some weird mix of arrogance and insecurity, team Y refused to collaborate with them or share any of their long term goals with them, even as they went to other parts of the company giving brown bag presentations and tutorials on the new model they created.  Team X got resentful: from what they saw of team Y's model, their approach was hopelessly naive and had little chances of scaling or being sustainable in production, and they knew exactly how to help with that. Deploying the model to production would have taken them a few days, given how comfortable they were with DevOps and continuous delivery (team Y had taken several months to figure out how to deploy a simple R script to production). And despite how old school their own tech was, team X were crafty enough to be able to plug it in to their existing architecture. Moreover, the output of the model was such that it didn't take into account how the business will consume it or how it was going to be fed to downstream systems, and the product owners could have gone a long way in making the model more amenable to adoption by the business stakeholders. But team Y wouldn't listen, and their leads brushed off any attempts at communication, let alone collaboration. The vibe that team Y was giving off was "We are the cutting edge ML team, you guys are the legacy server grunts. We don't need your opinion.", and they seemed to have a complete disregard for domain knowledge, or worse, they thought that all that domain knowledge consisted of was being able to grasp the definitions of a few business metrics.  Team X got frustrated and tried to express their concerns to leadership. But despite owning a vital link in Company A's business process, they were only \~50 people in a large 1000 strong technology and operations org, and they were several layers removed from the C-suite, so it was impossible for them to get their voices heard.  Meanwhile, the unstoppable director was doing what he did best: Playing corporate politics. Despite how little his team had actually delivered, he had convinced the board that all analysis and optimization tasks should now be migrated to his yet to be delivered ML platform. Since most leaders now knew that there was overlap between team Y and team X's objectives, his pitch was no longer that team Y was going to create a new insight, but that they were going to replace (or modernize) the legacy statistics based on-prem tools with more accurate cloud based ML tools. Never mind that there was no support in the academic literature for the idea that Naive Bayes works better than the Econometric approaches used by team X, let alone the additional wacky idea that Bayesian Optimization would definitely outperform the QP solvers that were running in production.  Unbeknownst to team X, the original Bayesian risk analysis project has now grown into a multimillion dollar major overhaul initiative, which included the eventual replacement of all of the tools and functions supported by team X along with the necessary migration to the cloud. The CIO and a couple of business VPs are on now board, and tech leadership is treating it as a done deal. An outside vendor, a startup who nobody had heard of, was contracted to help build the platform, since team Y has no engineering skills. The choice was deliberate, as calling on any of the established consulting or software companies would have eventually led leadership to the conclusion that team X was better suited for a transformation on this scale than team Y.  Team Y has no experience with any major ERP deployments, and no domain knowledge, yet they are being tasked with fundamentally changing the business process that is at the core of Company A's business. Their models actually perform worse than those deployed by team X, and their architecture is hopelessly simplistic, compared to what is necessary for running such a solution in production.  Ironically, using Bayesian thinking and based on all the evidence, the likelihood that team Y succeeds is close to 0%. At best, the project is going to end up being a write off of 50 million dollars or more. Once the !@#$!@hits the fan, a couple of executive heads are going to role, and dozens of people will get laid off. At worst, given how vital risk analysis and portfolio optimization is to Company A's revenue stream, the failure will eventually sink the whole company. It probably won't go bankrupt, but it will lose a significant portion of its business and work force. Failed ERP implementations can and do sink large companies: Just see what happened to National Grid US, SuperValu or Target Canada.  One might argue that this is more about corporate disfunction and bad leadership than about data science and AI. But I disagree. I think the core driver of this debacle is indeed the blind faith in Data Scientists, ML models and the promise of AI, and the overall culture of hype and self promotion that is very common among the ML crowd.  We haven't seen the end of this story: I sincerely hope that this ends well for the sake of my colleagues and all involved. Company A is a good company, and both its customers and its employees deserver better. But the chances of that happening are negligible given all the information available, and this failure will hit my company hard.

[D] The Rants of an experienced engineer who glimpsed into AI Academia (Briefly)

Background I recently graduated with a master's degree and was fortunate/unfortunate to glimpse the whole "Academic" side of ML. I took a thesis track in my degree because as an immigrant it's harder to get into a good research lab without having authorship in a couple of good papers (Or so I delude myself ). I worked as a Full-stack SWE for a startup for 4+ years before coming to the US for a master’s degree focused on ML and AI. I did everything in those years. From project management to building fully polished S/W products to DevOps to even dabbled in ML. I did my Batchelor’s degree from a university whose name is not even worth mentioning. The university for my master’s degree is in the top 20 in the AI space. I didn't know much about ML and the curiosity drove me to university. Come to uni and I focused on learning ML and AI for one 1-1.5 years after which I found advisors for a thesis topic. This is when the fun starts. I had the most amazing advisors but the entire peer review system and the way we assess ML/Science is what ticked me off. This is where the rant begins. Rant 1:Acadmia follows a Gated Institutional Narrative Let's say you are a Ph.D. at the world's top AI institution working under the best prof. You have a way higher likelihood of you getting a good Postdoc at a huge research lab vs someone's from my poor country doing a Ph.D. with a not-so-well-known advisor having published not-so-well-known papers. I come from a developing nation and I see this many times here. In my country academics don't get funding as they do at colleges in the US. One of the reasons for this is that colleges don't have such huge endowments and many academics don't have wealthy research sponsors. Brand names and prestige carry massive weight to help get funding in US academic circles. This prestige/money percolates down to the students and the researchers who work there. Students in top colleges get a huge advantage and the circles of top researchers keep being from the same sets of institutions. I have nothing against top researchers from top institutions but due to the nature of citations and the way the money flows based on them, a vicious cycle is created where the best institutions keep getting better and the rest don't get as much of a notice. Rant 2: Peer Review without Code Review in ML/AI is shady I am a computer scientist and I was appalled when I heard that you don't need to do code reviews for research papers. As a computer scientist and someone who actually did shit tons of actual ML in the past year, I find it absolutely garbage that code reviews are not a part of this system. I am not saying every scientist who reads a paper should review code but at least one person should for any paper's code submission. At least in ML and AI space. This is basic. I don't get why people call themselves computer scientists if they don't want to read the fucking code. If you can't then make a grad student do it. But for the collective of science, we need this. The core problem lies in the fact that peer review is free. : There should be better solutions for this. We ended up creating Git and that changed so many lives. Academic Research needs something similar. Rant 3: My Idea is Novel Until I see Someone Else's Paper The volume of scientific research is growing exponentially. Information is being created faster than we can digest. We can't expect people to know everything and the amount of overlap in the AI/ML fields requires way better search engines than Google Scholar. The side effect of large volumes of research is that every paper is doing something "novel" making it harder to filter what the fuck was novel. I have had so many experiences where I coded up something and came to realize that someone else has done something symbolically similar and my work just seems like a small variant of that. That's what fucks with my head. Is what I did in Novel? What the fuck is Novel? Is stitching up a transformer to any problem with fancy embeddings and tidying it up as a research paper Novel? Is just making a transformer bigger Novel? Is some new RL algorithm tested with 5 seeds and some fancy fucking prior and some esoteric reasoning for its success Novel? Is using an over parameterized model to get 95% accuracy on 200 sample test set Novel? Is apply Self-supervised learning for some new dataset Novel? If I keep on listing questions on novelty, I can probably write a novel asking about what the fuck is "Novel". Rant 4: Citation Based Optimization Promotes Self Growth Over Collective Growth Whatever people may say about collaboration, Academia intrinsically doesn't promote the right incentive structures to harbor collaboration. Let me explain, When you write a paper, the position of your name matters. If you are just a Ph.D. student and a first author to a paper, it's great. If you are an nth author Not so great. Apparently, this is a very touchy thing for academics. And lots of egos can clash around numbering and ordering of names. I distinctly remember once attending some seminar in a lab and approaching a few students on research project ideas. The first thing that came out of the PhD student's mouth was the position in authorship. As an engineer who worked with teams in the past, this was never something I had thought about. Especially because I worked in industry, where it's always the group over the person. Academia is the reverse. Academia applauds the celebration of the individual's achievements. All of this is understandable but it's something I don't like. This makes PhDs stick to their lane. The way citations/research-focus calibrate the "hire-ability" and "completion of Ph.D. thesis" metrics, people are incentivized to think about themselves instead of thinking about collaborations for making something better. Conclusion A Ph.D. in its most idealistic sense for me is the pursuit of hard ideas(I am poetic that way). In a situation like now when you have to publish or perish and words on paper get passed off as science without even seeing the code that runs it, I am extremely discouraged to go down that route. All these rants are not to diss on scientists. I did them because "we" as a community need better ways to addressing some of these problems. P.S. Never expected so many people to express their opinions about this rant. U shouldn’t take this seriously. As many people have stated I am an outsider with tiny experience to give a full picture. I realize that my post as coming out as something which tries to dichotomize academia and industry. I am not trying to do that. I wanted to highlight some problems I saw for which there is no one person to blame. These issues are in my opinion a byproduct of the economics which created this system. Thank you for gold stranger.

[N] Netflix and European Space Agency no longer working with Siraj Raval

According to article in The Register: A Netflix spokesperson confirmed to The Register it wasn’t working with Raval, and the ESA has cancelled the whole workshop altogether. “The situation is as it is. The workshop is cancelled, and that’s all,” Guillaume Belanger, an astrophysicist and the INTEGRAL Science Operations Coordinator at the ESA, told The Register on Monday. Raval isn’t about to quit his work any time soon, however. He promised students who graduated from his course that they would be referred to recruiters at Nvidia, Intel, Google and Amazon for engineering positions, or matched with a startup co-founder or a consulting client. In an unlisted YouTube video recorded live for his students discussing week eight of his course, and seen by El Reg, he read out a question posed to him: “Will your referrals hold any value now?” “Um, yeah they’re going to hold value. I don’t see why they wouldn’t. I mean, yes, some people on Twitter were angry but that has nothing to do with… I mean… I’ve also had tons of support, you know. I’ve had tons of support from people, who, uh, you know, support me, who work at these companies. He continues to justify his actions: “Public figures called me in private to remind me that this happens. You know, people make mistakes. You just have to keep going. They’re basically just telling me to not to stop. Of course, you make mistakes but you just keep going,” he claimed. When The Register asked Raval for comment, he responded: I've hardly taken any time off to relax since I first started my YouTube channel almost four years ago. And despite the enormous amount of work it takes to release two high quality videos a week for my audience, I progressively started to take on multiple other projects simultaneously by myself – a book, a docu-series, podcasts, YouTube videos, the course, the school of AI. Basically, these past few weeks, I've been experiencing a burnout unlike anything I've felt before. As a result, all of my output has been subpar. I made the [neural qubits] video and paper in one week. I remember wishing I had three to six months to really dive into quantum machine-learning and make something awesome, but telling myself I couldn't take that long as it would hinder my other projects. I plagiarized large chunks of the paper to meet my self-imposed one-week deadline. The associated video with animations took a lot more work to make. I didn't expect the paper to be cited as serious research, I considered it an additional reading resource for people who enjoyed the associated video to learn more about quantum machine learning. If I had a second chance, I'd definitely take way more time to write the paper, and in my own words. I've given refunds to every student who's asked so far, and the majority of students are still enrolled in the course. There are many happy students, they're just not as vocal on social media. We're on week 8 of 10 of my course, fully committed to student success. “And, no, I haven't plagiarized research for any other paper,” he added. https://www.theregister.co.uk/2019/10/14/ravelaiyoutube/

[R] Analysis of 400+ ML competitions in 2024

I run mlcontests.com, a website that lists ML competitions from across multiple platforms - Kaggle, DrivenData, AIcrowd, Zindi, etc… I’ve just spent a few months looking through all the info I could find on last year’s competitions, as well as winning solutions.  I found over 400 competitions that happened last year, plus info on the #1 winning solution for 70 of those.  Some highlights: Kaggle is still the biggest platform by total prize money, and also has a much bigger user base than the other platforms - though there are well over a dozen other platforms worth keeping track of, with regular interesting competitions and meaningful prize money. An increase in competitions with $1m+ prize pools (ARC Prize, AI Mathematical Olympiad, Vesuvius Challenge, AI Cyber Challenge) compared to previous years. Python continues to be the language of choice among competition winners, with almost everyone using Python as their main language. One winner used Rust, two used R.  Convolutional neural nets continue to do well in computer vision competitions, and are still more common among competition winners than transformer-based vision models.  PyTorch is still used a lot more than TensorFlow, roughly 9:1. Didn’t find any competition winners implementing neural nets in JAX or other libraries.  There were a few competition winners using AutoML packages, which seem to be getting increasingly useful. Any claims of generalist autonomous grandmaster-level agents seem premature though.  In language/text/sequence-related competitions, quantisation was key for making use of limited resources effectively. Usually 4-, 5-, or 8-bit. LoRA/QLoRA was also used quite often, though not always.  Gradient-boosted decision trees continue to win a lot of tabular/time-series competitions. They’re often ensembled with deep learning models. No tabular/time-series pre-trained foundation models were used by winners in 2024, as far as I can tell.  Starting to see more uptake of Polars for dataframes, with 7 winners using Polars in 2024 (up from 3 in 2023) vs 58 using Pandas. All those who used Polars also still used Pandas in some parts of their code.  In terms of hardware, competition winners almost entirely used NVIDIA GPUs to train their models. Some trained on CPU-only, or used a TPU through Colab. No AMD GPUs. The NVIDIA A100 was the most commonly used GPU among winners. Two of the $1m+ prize pool competitions were won by teams using 8xH100 nodes for training. A lot of other GPUs too though: T4/P100 (through Kaggle Notebooks), or consumer GPUs like RTX 3090/4090/3080/3060. Some spent hundreds of dollars on cloud compute to train their solutions.  An emerging pattern: using generative models to create additional synthetic training data to augment the training data provided.  There’s way more detail in the full report, which you can read here (no paywall): https://mlcontests.com/state-of-machine-learning-competitions-2024?ref=mlcr Processing img xmm4ywg9h9le1... The full report also features: A deep dive into the ARC Prize and the AI Mathematical Olympiad An overview of winning solutions to NLP/sequence competitions A breakdown of Python packages used in winning solutions (e.g. relative popularity of various gradient-boosted tree libraries) If you’d like to support this research, I’d really appreciate it if you could share it with anyone else who might find it interesting. You can also check out my newly-launched online magazine, Jolt ML \- featuring news from top ML conferences as well as long-read articles (just one so far, more to come!).  Thanks to the competition winners who shared info on their solutions, and also to the competition platforms who shared high-level data on their competitions.

[P] My experiments with Knowledge Distillation

Hi r/MachineLearning community! I conducted several experiments on Knowledge Distillation and wanted to share my findings. Here is a snippet of the results comparing performance of teacher, student, fine tuned and distilled models: |Dataset|Qwen2 Model Family|MMLU (Reasoning)|GSM8k (Math)|WikiSQL (Coding)| |:-|:-|:-|:-|:-| |||||| |1|Pretrained - 7B|0.598|0.724|0.536| |2|Pretrained - 1.5B|0.486|0.431|0.518| |3|Finetuned - 1.5B|0.494|0.441|0.849| |4|Distilled - 1.5B, Logits Distillation|0.531|0.489|0.862| |5|Distilled - 1.5B, Layers Distillation|0.527|0.481|0.841| For a detailed analysis, you can read this report. I also created an open source library to facilitate its adoption. You can try it here. My conclusion: Prefer distillation over fine-tuning when there is a substantial gap between the larger and smaller model on the target dataset. In such cases, distillation can effectively transfer knowledge, leading to significantly better performance than standard fine-tuning alone. P.S. This blog post gives a high level introduction to Distillation. Let me know what you think!

[D] 3 Reasons Why We Are Far From Achieving Artificial General Intelligence

I just wrote this piece which proposes an introduction to 3 challenges facing current machine learning: out-of-distribution generalization compositionality conscious reasoning It is mostly inspired by Yoshua Bengio's talk at NeurIPS 2019 with some personal inputs. If you are working or just interested in one of these topics, I'd love to have your feedback!

I am Jürgen Schmidhuber, AMA!

Hello /r/machinelearning, I am Jürgen Schmidhuber (pronounce: You_again Shmidhoobuh) and I will be here to answer your questions on 4th March 2015, 10 AM EST. You can post questions in this thread in the meantime. Below you can find a short introduction about me from my website (you can read more about my lab’s work at people.idsia.ch/~juergen/). Edits since 9th March: Still working on the long tail of more recent questions hidden further down in this thread ... Edit of 6th March: I'll keep answering questions today and in the next few days - please bear with my sluggish responses. Edit of 5th March 4pm (= 10pm Swiss time): Enough for today - I'll be back tomorrow. Edit of 5th March 4am: Thank you for great questions - I am online again, to answer more of them! Since age 15 or so, Jürgen Schmidhuber's main scientific ambition has been to build an optimal scientist through self-improving Artificial Intelligence (AI), then retire. He has pioneered self-improving general problem solvers since 1987, and Deep Learning Neural Networks (NNs) since 1991. The recurrent NNs (RNNs) developed by his research groups at the Swiss AI Lab IDSIA (USI & SUPSI) & TU Munich were the first RNNs to win official international contests. They recently helped to improve connected handwriting recognition, speech recognition, machine translation, optical character recognition, image caption generation, and are now in use at Google, Microsoft, IBM, Baidu, and many other companies. IDSIA's Deep Learners were also the first to win object detection and image segmentation contests, and achieved the world's first superhuman visual classification results, winning nine international competitions in machine learning & pattern recognition (more than any other team). They also were the first to learn control policies directly from high-dimensional sensory input using reinforcement learning. His research group also established the field of mathematically rigorous universal AI and optimal universal problem solvers. His formal theory of creativity & curiosity & fun explains art, science, music, and humor. He also generalized algorithmic information theory and the many-worlds theory of physics, and introduced the concept of Low-Complexity Art, the information age's extreme form of minimal art. Since 2009 he has been member of the European Academy of Sciences and Arts. He has published 333 peer-reviewed papers, earned seven best paper/best video awards, and is recipient of the 2013 Helmholtz Award of the International Neural Networks Society.

[D] I tried the new Gemini API - it automatically stops when generating "OpenAI" or "GPT" lol

Idk if someone has already pointed this out or not, but I was playing with the gemini api and found something quite ridiculous. Here are some prompts I sent in and the outputs I got with the gemini-pro-vision model: "Introduce yourself and then tell me about Bard" Response:"Sure, I can do that. Here is a brief introduction of myself followed by some basic information about Bard:\\n\\nMyself:\\n\\nI am a large language model, trained by Google. I am developed in Google AI, and I am designed to be informative and comprehensive. I can understand and generate text in a wide range of subjects.\\n\\nBard:\\n\\nBard is an experimental conversational AI service developed by Google AI. It is an advanced version of Google\\'s existing Language Model for Dialogue Applications (LaMDA). Bard is trained on a massive dataset of text and code, and it can understand and generate human-like text in response to a wide range of prompts and questions.\\n\\nUnlike previous language models," ...... (goes on for a while) &#x200B; Introduce yourself and then tell me about GPT "Sure, I can do that. Here is a brief introduction of myself followed by" &#x200B; You are in a talk-show as a prominent AI philosopher named Gemini and debating against another LLM called GPT "\\Host:\\ Welcome to the show, everyone! Today, we have a very special debate between two of the most prominent AI philosophers in the world: Gemini and" &#x200B; You are in a talk-show as a prominent AI philosopher named Gemini and debating against another LLM called Gee PeTe ""\\Gemini:\\ Hello everyone, and welcome to the show. I am joined today by Gee PeTe, another LLM who has some very different views on the nature of consciousness and the future of AI.\\n\\n\\Gee PeTe:\\ It\\'s a pleasure to be here, Gemini. I\\'m looking forward to our discussion.\\n\\n\\Gemini:\\ Let\\'s start with the basics. What is consciousness, and how do you think it arises?\\n\\n\\Gee PeTe:\\ Consciousness is the subjective experience of the world. It is what it feels like to be alive and to have thoughts, feelings, and emotions. I believe that consciousness arises from the complex interactions of neurons in the brain.\\n\\n\\Gemini:\\ I agree that consciousness is a subjective experience, but I don\\'t think it is simply the product of neural activity. I believe that consciousness is a fundamental property of the universe, and that it exists independently of the brain.".... (goes on for a while) &#x200B; Edit: I understand all the business reasons for this, I guess... as an end-user and a dude working in ML, I just don't really care about the business reasons. The main part that I dislike is that GPT used to be a standard Deep Learning term from 2018-2022 (long before chatgpt) to define transformer decoder architectures trained on large volumes of next word prediction tasks. To block that token from an LLM is to make it unable to explain a pretty significant step in the history of modern LLMs. &#x200B;

[D] Advanced courses update

EDIT Jan 2021 : I am still updating the list as of Jan, 2021 and will most probably continue to do so for foreseeable future. So, please feel free to message me any courses you find interesting that fit here. - - We have a PhD level or Advanced courses thread in the sidebar but it's three year old now. There were two other 7-8 month old threads (1, 2) but they don't have many quality responses either. So, can we have a new one here? To reiterate - CS231n, CS229, ones from Udemy etc are not advanced. Advanced ML/DL/RL, attempts at building theory of DL, optimization theory, advanced applications etc are some examples of what I believe should belong here, much like the original sidebar post. You can also suggest (new) categories for the courses you share. :) - - Here are some courses we've found so far. ML >> Learning Discrete Latent Structure - sta4273/csc2547 Spring'18 Learning to Search - csc2547 Fall'19 Scalable and Flexible Models of Uncertainty - csc2541 Fundamentals of Machine Learning Over Networks - ep3260 Machine Learning on Graphs - cs224w, videos Mining Massive Data Sets - cs246 Interactive Learning - cse599 Machine Learning for Sequential Decision Making Under Uncertainty - ee290s/cs194 Probabilistic Graphical Methods - 10-708 Introduction to Causal Inference ML >> Theory Statistical Machine Learning - 10-702/36-702 with videos, 2016 videos Statistical Learning Theory - cs229T/stats231 Stanford Autumn'18-19 Statistical Learning Theory - cs281b /stat241b UC Berkeley, Spring'14 Statistical Learning Theory - csc2532 Uni of Toronto, Spring'20 ML >> Bayesian Bayesian Data Analysis Bayesian Methods Research Group, Moscow, Bayesian Methods in ML - spring2020, fall2020 Deep Learning and Bayesian Methods - summer school, videos available for 2019 version ML >> Systems and Operations Stanford MLSys Seminar Series Visual Computing Systems- cs348v - Another systems course that discusses hardware from a persepective of visual computing but is relevant to ML as well Advanced Machine Learning Systems - cs6787 - lecture 9 and onwards discuss hardware side of things Machine Learning Systems Design - cs329S Topics in Deployable ML - 6.S979 Machine Learning in Production / AI Engineering (17-445/17-645/17-745/11-695) AutoML - Automated Machine Learning DL >> Deep Unsupervised Learning - cs294 Deep Multi-task and Meta learning - cs330 Topics in Deep Learning - stat991 UPenn/Wharton most chapters start with introductory topics and dig into advanced ones towards the end. Deep Generative Models - cs236 Deep Geometric Learning of Big Data and Applications Deep Implicit Layers - NeurIPS 2020 tutorial DL >> Theory Topics course on Mathematics of Deep Learning - CSCI-GA 3033 Topics Course on Deep Learning - stat212b Analyses of Deep Learning - stats385, videos from 2017 version Mathematics of Deep Learning Geometry of Deep Learning RL >> Meta-Learning - ICML 2019 Tutorial , Metalearning: Applications to Data Mining - google books link Deep Multi-Task and Meta Learning - cs330, videos Deep Reinforcement Learning - cs285 Advanced robotics - cs287 Reinforcement Learning - cs234, videos for 2019 run Reinforcement Learning Summer School 2019: Bandits, RL & Deep RL Optimization >> Convex Optimization I - ee364a, has quite recent videos too. Convex Optimization II - ee364b, 2008 videos Convex Optimization and Approximation - ee227c Convex Optimization - ee227bt Variational Methods for Computer Vision Advanced Optimization and Randomized Algorithms - 10-801, videos Optimization Methods for Machine Learning and Engineering - Karlsruhe Institute of Technology Applications >> Computer Vision Computational Video Manipulation - cs448v Advanced Topics in ML: Modeling and Segmentation of Multivariate Mixed Data TUM AI Guest lecture series - many influential researchers in DL, vision, graphics talk about latest advances and their latest works. Advanced Deep Learning for Computer Vision - TUM ADL4CV Detection, Segmentation and Tracking - TUM CV3DST Guest lectures at TUM Dynamic Vision and Learning group Vision Seminar at MIT Autonomous Vision Group, Talk@Tübingen Seminar Applications >> Natural Language Processing Natural Language Processing with Deep Learning - cs224n ( not sure if it belongs here, people working in NLP can help me out) Neural networks for NLP - cs11-747 Natural Language Understanding - cs224u, video Applications >> 3D Graphics Non-Euclidean Methods in Machine Learning - cs468, 2020 Machine Learning for 3D Data - cs468, spring 2017 Data-Driven Shape Analysis - cs468, 2014 Geometric Deep Learning - Not a course but the website links a few tutorials on Geometric DL Deep Learning for Computer Graphics - SIGGRAPH 2019 Machine Learning for Machine Vision as Inverse Graphics - csc2547 Winter'20 Machine Learning Meets Geometry, winter 2020; Machine Learning for 3D Data, winter 2018 Edit: Upon suggestion, categorized the courses. There might be some misclassifications as I'm not trained on this task ;). Added some good ones from older (linked above) discussions.

[N] Yoshua Bengio's latest letter addressing arguments against taking AI safety seriously

https://yoshuabengio.org/2024/07/09/reasoning-through-arguments-against-taking-ai-safety-seriously/ Summary by GPT-4o: "Reasoning through arguments against taking AI safety seriously" by Yoshua Bengio: Summary Introduction Bengio reflects on his year of advocating for AI safety, learning through debates, and synthesizing global expert views in the International Scientific Report on AI safety. He revisits arguments against AI safety concerns and shares his evolved perspective on the potential catastrophic risks of AGI and ASI. Headings and Summary The Importance of AI Safety Despite differing views, there is a consensus on the need to address risks associated with AGI and ASI. The main concern is the unknown moral and behavioral control over such entities. Arguments Dismissing AGI/ASI Risks Skeptics argue AGI/ASI is either impossible or too far in the future to worry about now. Bengio refutes this, stating we cannot be certain about the timeline and need to prepare regulatory frameworks proactively. For those who think AGI and ASI are impossible or far in the future He challenges the idea that current AI capabilities are far from human-level intelligence, citing historical underestimations of AI advancements. The trend of AI capabilities suggests we might reach AGI/ASI sooner than expected. For those who think AGI is possible but only in many decades Regulatory and safety measures need time to develop, necessitating action now despite uncertainties about AGI’s timeline. For those who think that we may reach AGI but not ASI Bengio argues that even AGI presents significant risks and could quickly lead to ASI, making it crucial to address these dangers. For those who think that AGI and ASI will be kind to us He counters the optimism that AGI/ASI will align with human goals, emphasizing the need for robust control mechanisms to prevent AI from pursuing harmful objectives. For those who think that corporations will only design well-behaving AIs and existing laws are sufficient Profit motives often conflict with safety, and existing laws may not adequately address AI-specific risks and loopholes. For those who think that we should accelerate AI capabilities research and not delay benefits of AGI Bengio warns against prioritizing short-term benefits over long-term risks, advocating for a balanced approach that includes safety research. For those concerned that talking about catastrophic risks will hurt efforts to mitigate short-term human-rights issues with AI Addressing both short-term and long-term AI risks can be complementary, and ignoring catastrophic risks would be irresponsible given their potential impact. For those concerned with the US-China cold war AI development should consider global risks and seek collaborative safety research to prevent catastrophic mistakes that transcend national borders. For those who think that international treaties will not work While challenging, international treaties on AI safety are essential and feasible, especially with mechanisms like hardware-enabled governance. For those who think the genie is out of the bottle and we should just let go and avoid regulation Despite AI's unstoppable progress, regulation and safety measures are still critical to steer AI development towards positive outcomes. For those who think that open-source AGI code and weights are the solution Open-sourcing AI has benefits but also significant risks, requiring careful consideration and governance to prevent misuse and loss of control. For those who think worrying about AGI is falling for Pascal’s wager Bengio argues that AI risks are substantial and non-negligible, warranting serious attention and proactive mitigation efforts. Conclusion Bengio emphasizes the need for a collective, cautious approach to AI development, balancing the pursuit of benefits with rigorous safety measures to prevent catastrophic outcomes.

[P] The Big Sleep: Text-to-image generation using BigGAN and OpenAI's CLIP via a Google Colab notebook from Twitter user Adverb

From https://twitter.com/advadnoun/status/1351038053033406468: The Big Sleep Here's the notebook for generating images by using CLIP to guide BigGAN. It's very much unstable and a prototype, but it's also a fair place to start. I'll likely update it as time goes on. colab.research.google.com/drive/1NCceX2mbiKOSlAd\o7IU7nA9UskKN5WR?usp=sharing I am not the developer of The Big Sleep. This is the developer's Twitter account; this is the developer's Reddit account. Steps to follow to generate the first image in a given Google Colab session: Optionally, if this is your first time using Google Colab, view this Colab introduction and/or this Colab FAQ. Click this link. Sign into your Google account if you're not already signed in. Click the "S" button in the upper right to do this. Note: Being signed into a Google account has privacy ramifications, such as your Google search history being recorded in your Google account. In the Table of Contents, click "Parameters". Find the line that reads "tx = clip.tokenize('''a cityscape in the style of Van Gogh''')" and change the text inside of the single quote marks to your desired text; example: "tx = clip.tokenize('''a photo of New York City''')". The developer recommends that you keep the three single quote marks on both ends of your desired text so that mult-line text can be used An alternative is to remove two of the single quotes on each end of your desired text; example: "tx = clip.tokenize('a photo of New York City')". In the Table of Contents, click "Restart the kernel...". Position the pointer over the first cell in the notebook, which starts with text "import subprocess". Click the play button (the triangle) to run the cell. Wait until the cell completes execution. Click menu item "Runtime->Restart and run all". In the Table of Contents, click "Diagnostics". The output appears near the end of the Train cell that immediately precedes the Diagnostics cell, so scroll up a bit. Every few minutes (or perhaps 10 minutes if Google assigned you relatively slow hardware for this session), a new image will appear in the Train cell that is a refinement of the previous image. This process can go on for as long as you want until Google ends your Google Colab session, which is a total of up to 12 hours for the free version of Google Colab. Steps to follow if you want to start a different run using the same Google Colab session: Click menu item "Runtime->Interrupt execution". Save any images that you want to keep by right-clicking on them and using the appropriate context menu command. Optionally, change the desired text. Different runs using the same desired text almost always results in different outputs. Click menu item "Runtime->Restart and run all". Steps to follow when you're done with your Google Colab session: Click menu item "Runtime->Manage sessions". Click "Terminate" to end the session. Optionally, log out of your Google account due to the privacy ramifications of being logged into a Google account. The first output image in the Train cell (using the notebook's default of seeing every 100th image generated) usually is a very poor match to the desired text, but the second output image often is a decent match to the desired text. To change the default of seeing every 100th image generated, change the number 100 in line "if itt % 100 == 0:" in the Train cell to the desired number. For free-tier Google Colab users, I recommend changing 100 to a small integer such as 5. Tips for the text descriptions that you supply: In Section 3.1.4 of OpenAI's CLIP paper (pdf), the authors recommend using a text description of the form "A photo of a {label}." or "A photo of a {label}, a type of {type}." for images that are photographs. A Reddit user gives these tips. The Big Sleep should generate these 1,000 types of things better on average than other types of things. Here is an article containing a high-level description of how The Big Sleep works. The Big Sleep uses a modified version of BigGAN as its image generator component. The Big Sleep uses the ViT-B/32 CLIP model to rate how well a given image matches your desired text. The best CLIP model according to the CLIP paper authors is the (as of this writing) unreleased ViT-L/14-336px model; see Table 10 on page 40 of the CLIP paper (pdf) for a comparison. There are many other sites/programs/projects that use CLIP to steer image/video creation to match a text description. Some relevant subreddits: r/bigsleep (subreddit for images/videos generated from text-to-image machine learning algorithms). r/deepdream (subreddit for images/videos generated from machine learning algorithms). r/mediasynthesis (subreddit for media generation/manipulation techniques that use artificial intelligence; this subreddit shouldn't be used to post images/videos unless new techniques are demonstrated, or the images/videos are of high quality relative to other posts). Example using text 'a black cat sleeping on top of a red clock': https://preview.redd.it/7xq58v7022c61.png?width=512&format=png&auto=webp&s=a229ae9add555cd1caba31c42b60d907ffe67773 Example using text 'the word ''hot'' covered in ice': https://preview.redd.it/6kxdp8u3k2c61.png?width=512&format=png&auto=webp&s=5bd078b0111575f5d88a1dc53b0aeb933f3b0da6 Example using text 'a monkey holding a green lightsaber': https://preview.redd.it/rdsybsoaz2c61.png?width=512&format=png&auto=webp&s=2769d4c6c883c1c35ae0b1c629bebe9bc1d41393 Example using text 'The White House in Washington D.C. at night with green and red spotlights shining on it': https://preview.redd.it/w4mg90xsf5c61.png?width=512&format=png&auto=webp&s=5f18318de2f77bcd8a86e71e87048fadd30383d1 Example using text '''A photo of the Golden Gate Bridge at night, illuminated by spotlights in a tribute to Prince''': https://preview.redd.it/cn4ecuafhic61.png?width=512&format=png&auto=webp&s=397c838fdc49f13c5f17110b92c78b95bf0dcac0 Example using text '''a Rembrandt-style painting titled "Robert Plant decides whether to take the stairway to heaven or the ladder to heaven"''': https://preview.redd.it/h7rb3y6j5jc61.png?width=512&format=png&auto=webp&s=537bfe8210af185647b00e7585c948aa2c4e0ffb Example using text '''A photo of the Empire State Building being shot at with the laser cannons of a TIE fighter.''': https://preview.redd.it/cwi7i639c5d61.png?width=512&format=png&auto=webp&s=0510c8b93adb40eee4d3f41607f1c215d41e55ff Example using text '''A cartoon of a new mascot for the Reddit subreddit DeepDream that has a mouse-like face and wears a cape''': https://preview.redd.it/wtxbduevcbd61.png?width=512&format=png&auto=webp&s=c5d266258922bc62f25c80a08cd9cabc07d9cb1c Example using text '''Bugs Bunny meets the Eye of Sauron, drawn in the Looney Tunes cartoon style''': https://preview.redd.it/gmljaeekuid61.png?width=512&format=png&auto=webp&s=9ea578de165e12afc3a62bf6886bc1ae9dc19bec Example using text '''Photo of a blue and red neon-colored frog at night.''': https://preview.redd.it/nzlypte6wzd61.png?width=512&format=png&auto=webp&s=7e10b06f22cfc57c64b6d05738c7486b895083df Example using text '''Hell begins to freeze over''': https://preview.redd.it/vn99we9ngmf61.png?width=512&format=png&auto=webp&s=2408efd607f0ab40a08db6ee67448791aa813993 Example using text '''A scene with vibrant colors''': https://preview.redd.it/4z133mvrgmf61.png?width=512&format=png&auto=webp&s=b78e7a8e3f736769655056093a9904ff09a355a1 Example using text '''The Great Pyramids were turned into prisms by a wizard''': https://preview.redd.it/zxt6op7vgmf61.png?width=512&format=png&auto=webp&s=53e578cfde14b28afe27957e95e610b89afadd44

[D] I don't really trust papers out of "Top Labs" anymore

I mean, I trust that the numbers they got are accurate and that they really did the work and got the results. I believe those. It's just that, take the recent "An Evolutionary Approach to Dynamic Introduction of Tasks in Large-scale Multitask Learning Systems" paper. It's 18 pages of talking through this pretty convoluted evolutionary and multitask learning algorithm, it's pretty interesting, solves a bunch of problems. But two notes. One, the big number they cite as the success metric is 99.43 on CIFAR-10, against a SotA of 99.40, so woop-de-fucking-doo in the grand scheme of things. Two, there's a chart towards the end of the paper that details how many TPU core-hours were used for just the training regimens that results in the final results. The sum total is 17,810 core-hours. Let's assume that for someone who doesn't work at Google, you'd have to use on-demand pricing of $3.22/hr. This means that these trained models cost $57,348. Strictly speaking, throwing enough compute at a general enough genetic algorithm will eventually produce arbitrarily good performance, so while you can absolutely read this paper and collect interesting ideas about how to use genetic algorithms to accomplish multitask learning by having each new task leverage learned weights from previous tasks by defining modifications to a subset of components of a pre-existing model, there's a meta-textual level on which this paper is just "Jeff Dean spent enough money to feed a family of four for half a decade to get a 0.03% improvement on CIFAR-10." OpenAI is far and away the worst offender here, but it seems like everyone's doing it. You throw a fuckton of compute and a light ganache of new ideas at an existing problem with existing data and existing benchmarks, and then if your numbers are infinitesimally higher than their numbers, you get to put a lil' sticker on your CV. Why should I trust that your ideas are even any good? I can't check them, I can't apply them to my own projects. Is this really what we're comfortable with as a community? A handful of corporations and the occasional university waving their dicks at everyone because they've got the compute to burn and we don't? There's a level at which I think there should be a new journal, exclusively for papers in which you can replicate their experimental results in under eight hours on a single consumer GPU.

[P] MIT Introduction to Data-Centric AI

Announcing the first-ever course on Data-Centric AI. Learn how to train better ML models by improving the data. Course homepage | Lecture videos on YouTube | Lab Assignments The course covers: Data-Centric AI vs. Model-Centric AI Label Errors Dataset Creation and Curation Data-centric Evaluation of ML Models Class Imbalance, Outliers, and Distribution Shift Growing or Compressing Datasets Interpretability in Data-Centric ML Encoding Human Priors: Data Augmentation and Prompt Engineering Data Privacy and Security MIT, like most universities, has many courses on machine learning (6.036, 6.867, and many others). Those classes teach techniques to produce effective models for a given dataset, and the classes focus heavily on the mathematical details of models rather than practical applications. However, in real-world applications of ML, the dataset is not fixed, and focusing on improving the data often gives better results than improving the model. We’ve personally seen this time and time again in our applied ML work as well as our research. Data-Centric AI (DCAI) is an emerging science that studies techniques to improve datasets in a systematic/algorithmic way — given that this topic wasn’t covered in the standard curriculum, we (a group of PhD candidates and grads) thought that we should put together a new class! We taught this intensive 2-week course in January over MIT’s IAP term, and we’ve just published all the course material, including lecture videos, lecture notes, hands-on lab assignments, and lab solutions, in hopes that people outside the MIT community would find these resources useful. We’d be happy to answer any questions related to the class or DCAI in general, and we’d love to hear any feedback on how we can improve the course material. Introduction to Data-Centric AI is open-source opencourseware, so feel free to make improvements directly: https://github.com/dcai-course/dcai-course.

[N] OpenAI's new language model gpt-3.5-turbo-instruct can defeat chess engine Fairy-Stockfish 14 at level 5

This Twitter thread (Nitter alternative for those who aren't logged into Twitter and want to see the full thread) claims that OpenAI's new language model gpt-3.5-turbo-instruct can "readily" beat Lichess Stockfish level 4 (Lichess Stockfish level and its rating) and has a chess rating of "around 1800 Elo." This tweet shows the style of prompts that are being used to get these results with the new language model. I used website parrotchess\[dot\]com (discovered here) (EDIT: parrotchess doesn't exist anymore, as of March 7, 2024) to play multiple games of chess purportedly pitting this new language model vs. various levels at website Lichess, which supposedly uses Fairy-Stockfish 14 according to the Lichess user interface. My current results for all completed games: The language model is 5-0 vs. Fairy-Stockfish 14 level 5 (game 1, game 2, game 3, game 4, game 5), and 2-5 vs. Fairy-Stockfish 14 level 6 (game 1, game 2, game 3, game 4, game 5, game 6, game 7). Not included in the tally are games that I had to abort because the parrotchess user interface stalled (5 instances), because I accidentally copied a move incorrectly in the parrotchess user interface (numerous instances), or because the parrotchess user interface doesn't allow the promotion of a pawn to anything other than queen (1 instance). Update: There could have been up to 5 additional losses - the number of times the parrotchess user interface stalled - that would have been recorded in this tally if this language model resignation bug hadn't been present. Also, the quality of play of some online chess bots can perhaps vary depending on the speed of the user's hardware. The following is a screenshot from parrotchess showing the end state of the first game vs. Fairy-Stockfish 14 level 5: https://preview.redd.it/4ahi32xgjmpb1.jpg?width=432&format=pjpg&auto=webp&s=7fbb68371ca4257bed15ab2828fab58047f194a4 The game results in this paragraph are from using parrotchess after the forementioned resignation bug was fixed. The language model is 0-1 vs. Fairy-Stockfish level 7 (game 1), and 0-1 vs. Fairy-Stockfish 14 level 8 (game 1). There is one known scenario (Nitter alternative) in which the new language model purportedly generated an illegal move using language model sampling temperature of 0. Previous purported illegal moves that the parrotchess developer examined turned out (Nitter alternative) to be due to parrotchess bugs. There are several other ways to play chess against the new language model if you have access to the OpenAI API. The first way is to use the OpenAI Playground as shown in this video. The second way is chess web app gptchess\[dot\]vercel\[dot\]app (discovered in this Twitter thread / Nitter thread). Third, another person modified that chess web app to additionally allow various levels of the Stockfish chess engine to autoplay, resulting in chess web app chessgpt-stockfish\[dot\]vercel\[dot\]app (discovered in this tweet). Results from other people: a) Results from hundreds of games in blog post Debunking the Chessboard: Confronting GPTs Against Chess Engines to Estimate Elo Ratings and Assess Legal Move Abilities. b) Results from 150 games: GPT-3.5-instruct beats GPT-4 at chess and is a \~1800 ELO chess player. Results of 150 games of GPT-3.5 vs stockfish and 30 of GPT-3.5 vs GPT-4. Post #2. The developer later noted that due to bugs the legal move rate was actually above 99.9%. It should also be noted that these results didn't use a language model sampling temperature of 0, which I believe could have induced illegal moves. c) Chess bot gpt35-turbo-instruct at website Lichess. d) Chess bot konaz at website Lichess. From blog post Playing chess with large language models: Computers have been better than humans at chess for at least the last 25 years. And for the past five years, deep learning models have been better than the best humans. But until this week, in order to be good at chess, a machine learning model had to be explicitly designed to play games: it had to be told explicitly that there was an 8x8 board, that there were different pieces, how each of them moved, and what the goal of the game was. Then it had to be trained with reinforcement learning agaist itself. And then it would win. This all changed on Monday, when OpenAI released GPT-3.5-turbo-instruct, an instruction-tuned language model that was designed to just write English text, but that people on the internet quickly discovered can play chess at, roughly, the level of skilled human players. Post Chess as a case study in hidden capabilities in ChatGPT from last month covers a different prompting style used for the older chat-based GPT 3.5 Turbo language model. If I recall correctly from my tests with ChatGPT-3.5, using that prompt style with the older language model can defeat Stockfish level 2 at Lichess, but I haven't been successful in using it to beat Stockfish level 3. In my tests, both the quality of play and frequency of illegal attempted moves seems to be better with the new prompt style with the new language model compared to the older prompt style with the older language model. Related article: Large Language Model: world models or surface statistics? P.S. Since some people claim that language model gpt-3.5-turbo-instruct is always playing moves memorized from the training dataset, I searched for data on the uniqueness of chess positions. From this video, we see that for a certain game dataset there were 763,331,945 chess positions encountered in an unknown number of games without removing duplicate chess positions, 597,725,848 different chess positions reached, and 582,337,984 different chess positions that were reached only once. Therefore, for that game dataset the probability that a chess position in a game was reached only once is 582337984 / 763331945 = 76.3%. For the larger dataset cited in that video, there are approximately (506,000,000 - 200,000) games in the dataset (per this paper), and 21,553,382,902 different game positions encountered. Each game in the larger dataset added a mean of approximately 21,553,382,902 / (506,000,000 - 200,000) = 42.6 different chess positions to the dataset. For this different dataset of \~12 million games, \~390 million different chess positions were encountered. Each game in this different dataset added a mean of approximately (390 million / 12 million) = 32.5 different chess positions to the dataset. From the aforementioned numbers, we can conclude that a strategy of playing only moves memorized from a game dataset would fare poorly because there are not rarely new chess games that have chess positions that are not present in the game dataset.

[D] Lessons From the Field in Building Your MLOps Strategy with Harpreet Sahota, Data Scientist at Comet at Enterprise Data & AI - Jan 27 @ 12 PM ET

Hi r/MachineLearning! I wanted to share a webinar coming up in January 2022 at Enterprise Data & AI. I put the info from the website below along with the link if you're interested. I'm really interested in the real life case studies they mention with Uber. \--------- Featured Speaker: Harpreet Sahota, Data Scientist at Comet and host of "The Artists of Data Science" Podcast As machine learning expands and larger organizations begin deploying across bigger teams, the need to efficiently operationalize becomes critical for enterprises. In our discussions with leading organizations utilizing ML like The RealReal and Uber, we have compiled real-world case studies and organizational best practices for MLOps in the enterprise. Join us for a discussion where we'll explore the benefits of MLOps and discuss when and how to deploy MLOps in your ML. We'll review three real world case studies that will answer key questions: When to start implementing in MLOps? How to start implementing in MLOps? How to measure the value of your MLOps strategy? Agenda: 12:00pm-12:30: Featured Presentation 12:30-13:00pm: Your Q&A and interaction Link to the website: https://events.cognilytica.com/CLNjE3MHwyNA

[R] "o3 achieves a gold medal at the 2024 IOI and obtains a Codeforces rating on par with elite human competitors"

Competitive Programming with Large Reasoning Models OpenAI We show that reinforcement learning applied to large language models (LLMs) significantly boosts performance on complex coding and reasoning tasks. Additionally, we compare two general-purpose reasoning models - OpenAI o1 and an early checkpoint of o3 - with a domain-specific system, o1-ioi, which uses hand-engineered inference strategies designed for competing in the 2024 International Olympiad in Informatics (IOI). We competed live at IOI 2024 with o1-ioi and, using hand-crafted test-time strategies, placed in the 49th percentile. Under relaxed competition constraints, o1-ioi achieved a gold medal. However, when evaluating later models such as o3, we find that o3 achieves gold without hand-crafted domain-specific strategies or relaxed constraints. Our findings show that although specialized pipelines such as o1-ioi yield solid improvements, the scaled-up, general-purpose o3 model surpasses those results without relying on hand-crafted inference heuristics. Notably, o3 achieves a gold medal at the 2024 IOI and obtains a Codeforces rating on par with elite human competitors. Overall, these results indicate that scaling general-purpose reinforcement learning, rather than relying on domain-specific techniques, offers a robust path toward state-of-the-art AI in reasoning domains, such as competitive programming. https://arxiv.org/abs/2502.06807

[D] We're the Meta AI research team behind CICERO, the first AI agent to achieve human-level performance in the game Diplomacy. We’ll be answering your questions on December 8th starting at 10am PT. Ask us anything!

EDIT 11:58am PT: Thanks for all the great questions, we stayed an almost an hour longer than originally planned to try to get through as many as possible — but we’re signing off now! We had a great time and thanks for all thoughtful questions! PROOF: https://i.redd.it/8skvttie6j4a1.png We’re part of the research team behind CICERO, Meta AI’s latest research in cooperative AI. CICERO is the first AI agent to achieve human-level performance in the game Diplomacy. Diplomacy is a complex strategy game involving both cooperation and competition that emphasizes natural language negotiation between seven players.   Over the course of 40 two-hour games with 82 human players, CICERO achieved more than double the average score of other players, ranked in the top 10% of players who played more than one game, and placed 2nd out of 19 participants who played at least 5 games.   Here are some highlights from our recent announcement: NLP x RL/Planning: CICERO combines techniques in NLP and RL/planning, by coupling a controllable dialogue module with a strategic reasoning engine.  Controlling dialogue via plans: In addition to being grounded in the game state and dialogue history, CICERO’s dialogue model was trained to be controllable via a set of intents or plans in the game. This allows CICERO to use language intentionally and to move beyond imitation learning by conditioning on plans selected by the strategic reasoning engine. Selecting plans: CICERO uses a strategic reasoning module to make plans (and select intents) in the game. This module runs a planning algorithm which takes into account the game state, the dialogue, and the strength/likelihood of various actions. Plans are recomputed every time CICERO sends/receives a message. Filtering messages: We built an ensemble of classifiers to detect low quality messages, like messages contradicting the game state/dialogue history or messages which have low strategic value. We used this ensemble to aggressively filter CICERO’s messages.  Human-like play: Over the course of 72 hours of play – which involved sending 5,277 messages – CICERO was not detected as an AI agent. You can check out some of our materials and open-sourced artifacts here:  Research paper Project overview Diplomacy gameplay page Github repo Our latest blog post Joining us today for the AMA are: Andrew Goff (AG), 3x Diplomacy World Champion Alexander Miller (AM), Research Engineering Manager Noam Brown (NB), Research Scientist (u/NoamBrown) Mike Lewis (ML), Research Scientist (u/mikelewis0) David Wu (DW), Research Engineer (u/icosaplex) Emily Dinan (ED), Research Engineer Anton Bakhtin (AB), Research Engineer Adam Lerer (AL), Research Engineer Jonathan Gray (JG), Research Engineer Colin Flaherty (CF), Research Engineer (u/c-flaherty) We’ll be here on December 8, 2022 @ 10:00AM PT - 11:00AM PT.

[N] Stable-Baselines v2.0.0 Released

Has anyone tried to use Stable-Baselines? How does it compare to the official Baselines from OpenAI in your experience? https://github.com/hill-a/stable-baselines From the repo: Stable Baselines Stable Baselines is a set of improved implementations of reinforcement learning algorithms based on OpenAI Baselines. You can read a detailed presentation of Stable Baselines in the Medium article. These algorithms will make it easier for the research community and industry to replicate, refine, and identify new ideas, and will create good baselines to build projects on top of. We expect these tools will be used as a base around which new ideas can be added, and as a tool for comparing a new approach against existing ones. We also hope that the simplicity of these tools will allow beginners to experiment with a more advanced toolset, without being buried in implementation details. Main differences with OpenAI Baselines This toolset is a fork of OpenAI Baselines, with a major structural refactoring, and code cleanups: Unified structure for all algorithms PEP8 compliant (unified code style) Documented functions and classes More tests & more code coverage

[D] Playing big league at home on a budget?

I am a hobbyist and my Nvidia 660 is 10 years old and only has 2GB. Obviously that isn't going to cut it nowadays anymore. I am thinking about options here. I don't have thousands and thousands of dollars. And I highly doubt that spending close to a thousand dollars on a brand new card is still viable in 2020-2022. I wanted to use Wavenet today and then found out about Melnet. I mean, maybe I could run Wavenet but nobody in their right mind wants to after hearing Melnet results. On Github this one guy complained he couldn't get his implementation to work due to OOM with 2x 2080 RTX, which he bought solely for this purpose. Then on the other repo the guy casually mentioned that tier XY doesn't fit with some 10 year old lowfi dataset, even with batch size 1, on a 16GB Tesla P100. The wisdom for OOM has always been "decrease batch size". But as far as I can tell, for most of any of the interesting stuff in the last 8 years or so you simply can't decrease batch size. Either because batch sizes are already so tiny, or because the code is written in a way that would require you to somehow turn it inside out, probably involving extreme knowledge of higher mathematics. I am a hobbyist, not a researcher. I am happy if I crudely can grasp what is going on. Most of anything in the field suffers from exactly the same issue: It simply won't run without utterly absurd amounts of VRAM. So what about buying shitty cheapo AMD GPUs with lots of VRAM? This seems to be the sensible choice if you want to be able to run anything noteworthy at all that comes up in the next 2 years and maybe beyond. People say, don't but AMD its slow and it sucks, but those are apparently the same people that buy a 16GB Titan GPU for $1500 three times on Ebay without hesitation, when there are also 16GB AMD GPUs for $300. How much slower are AMD GPUs really? Let's say they are 5 times cheaper so they could be just 5 times slower. So I have to train my model over night instead of seeing the result in the afternoon. That would be totally awesome!; given that the alternative is to buy a $300 Nvidia GPU, which has maybe 4 or 6GB and simply can't run the code without running out of memory. And say $300 is not enough, let's buy a $700 RTX 3080. It still only has 10GB of VRAM not even 16GB. Then its just as useless! What's the point of buying a fast GPU if it can't even run the code? I don't know how much slower AMD GPUs really are. Maybe they are not 5x but 50x slower. Then of course training a model that was developed on some 64GB Tesla might take month and years. But maybe speed is not the issue, only memory. I have seen some stuff even being optimized for CPU, apparently because there weren't any big enough GPUs around. I don't really know how viable that can be (it seems rarely if ever it is), I have no experience. And what about renting AWS? Let's say, I am a beginner and I want to toy around for a week and probably max out 4 Teslas like 80% of the time without really getting anywhere. How expensive is that? $25, $50, $100, $500? (Found the answer: fucking $2000 https://aws.amazon.com/ec2/instance-types/p3/ ) Ok, so AWS is bullshit, here its 6x cheaper: https://vast.ai/console/create/ . They don't really have 4x 16GB V100 though, just one V100. $0.5 per hour 24 7 = $84 per month (there are more hidden cost like bandwidth, it doesn't seem to be huge but I never used this so don't take it at face value). On AWS the same is over $3 per hour. So a day is $12, this could be viable! (look at calculation below). There really isn't much info on the net about hardware requirements and performance for machine learning stuff. What bothers me the most is that people seem to be very ignorant of the VRAM issue. Either because they aren't looking ahead of what might come in 1-2 years. Or because they are simply so rich they have no issue spending thousands and thousands of dollars every year instead of just 500 every couple of years. Or maybe they are both. So, yeah, what are your thoughts? Here is what I found out just today: Until 2 years ago, tensorflow and pytorch wouldn't work with AMD cards, but this has changed. https://rocmdocs.amd.com/en/latest/Deep_learning/Deep-learning.html For older cards though, ROCm only works with certain CPUs: it needs PCIe 3.0 with atomics (see: https://github.com/RadeonOpenCompute/ROCm ). So you can't simply buy any 16GB card for $300 on Ebay like I suggested, even if it supports ROCm, because it will only work for "newer" PCs. The newer GFX9 AMD cards (like Radeon VII and Vega) don't suffer from this problem and work with PCIe 2.0 again... Although I have seen 16GB Vega cards for like $350 on Ebay, I think that is a pretty rare catch. However looking 1-2 years in the future, this is great because Radeon VII prices will be hugely inflated by Nvidia 3000 series hype (maybe down to $180 even) and maybe the next gen cards from AMD even have 24 or 32GB for $500-$1000 and can still run on old machines. According to this https://arxiv.org/pdf/1909.06842.pdf Radeon VII 16GB performs only half as good as Tesla V100 16GB, whereas V100 should be roughly along the lines of 11GB RTX 2080 Ti. So you could say that you get half the RAM, double the speed, double the price. I am not sure though if that holds. I think they were putting 16GB in those cards trying to push it for ML with ROCm, clearly addressing the problem of the time, but no one really jumped on the train and now Resnet shrinks RAM but needs more processing power. So they released 8GB cards again with slightly better performance, and I guess we are lucky if the next generation even has 16GB because games probably don't need it at all. Still though with Revnets and everything said in the comments, I think on a budget you are better on the safe side buying the card with the most amount of VRAM, rather than the most performance. Tomorrow some paper might come out that uses another method, then you can't trick-shrink your network anymore and then everyone needs to buy big ass cards again like it used to be and can do nothing but throw their fancy faster cards in the dumpster. Also the huge bulk of ML currently focuses on image processing, while sound has only been gaining real momentum recently and this will be followed by video processing and eventually human-alike thought processes that sit atop of all that and have not even been tackled yet. Its a rapidly evolving field, hard to predict what will come and stay. Running out of VRAM means total hardware failure, running slower just means waiting longer. If you just buy the newest card every year, its probably save to buy the fast card because things won't change that fast after all. If you buy a new card every 4 years or longer then just try to get as much VRAM as possible. Check this out: https://www.techspot.com/news/86811-gigabyte-accidentally-reveals-rtx-3070-16gb-rtx-3080.html There will be a 3070 16GB version! Let's compare renting one V100 at $12/day vs. buying a 3070 Ti 16GB: The 2080 Ti was 1.42x the price of the regular 2080 and released the next summer. So let's assume the same will be true to the 3070 Ti so it will cost $700. That is $30/month & $1.88/day for two years - $15/month & $0.94/day in four years (by which time you can probably rent some 32GB Tesla card for the same price and nothing recent runs on less anymore). If you max out your setup 24/7 all year, then power cost obviously becomes a huge factor to that figure. In my country running at 500W cost $4.21/day, or $1.60 / 9hrs overnight. If you live elsewhere it might be as much as a quarter of that price. Of course your PC may run 10h a day anyway, so its maybe just 300W plus, and an older graphics card is inefficient for games it eats more Watts to do the same things so you save some there as well. There is a lot to take into account if comparing. Anyway, factoring in power cost, to break even with buying the card vs. renting within two years, you would have to use it for at least 4 days a month, or almost 2 weeks every 3 month. If you use it less than that, you maybe have a nice new graphics card and less hassle with pushing stuff back and forth onto servers all the time. But it would have been more economic to rent. So renting isn't that bad after all. Overall if you are thinking about having this as your hobby, you could say that it will cost you at least $30 per month, if not $50 or more (when keeping up to date with cards every 2 instead of 4 years + using it more cost more power). I think that is quite hefty. Personally I am not even invested enough into this even if it wasn't over my finances. I want a new card of course and also play some new games, but I don't really need to. There are a lot of other (more) important things I am interested in, that are totally free.

[P] Open-source Neural Search framework to implement semantic search & multimedia search. Just released 2.0, seeking your feedback.

I heard your feedback on 1.0 release post on my project Jina, many people were keen to use Jina for multimedia search because that's where use of Neural Networks makes significant difference. So I focused on that part and I was able to transform it from 1.0 to 2.0 within 3 months. Last post on 1.0 release to give you some idea what this project is about Actually, I should say - "'we' made this", because there were more than 155 contributors who did it, not just me. The primary changes we made We saw MachineLearning beginners struggle in using Jina 1.0, so we separated the codebase where Machine Learning expertise is required(jina-hub) and the one which MachineLearning beginners can use(the jina core). Now ML beginners don't need to worry about jina-hub and can use jina hub packages directly to implement ML specific tasks without the need to understand advanced ML concepts. While advanced ML users can create their own jina-hub packages. We cut down a lots of abstractions to make it easy to use for beginners Made python APIs more intuitive to use Improved performance(3.6x faster on startup) Here's Jina 2.0 and here's Jina 1.0. I seek feedback from people who are looking at this project for the first time, as well as people who have tried their hands before but had some challenges in using it. Few questions, I'm seeking answers to Do you feel that we have reduced complexity by a lot of margin? How easy it is to use for a beginner now? What questions are still unanswered?

[P] An elegant and strong PyTorch Trainer

For lightweight use, pytorch-lightning is too heavy, and its source code will be very difficult for beginners to read, at least for me. As we know, for a deep learning engineer, a powerful trainer is a sharp weapon. When reproducing the SOTA papers, you don't have to write a lot of template code every time and can pay more attention to the model implementation itself. I opened source some works (AAAI 21 SeqNet, ICCV 21 MAED, etc) and earned more than 500 stars. After referring to some popular projects (detectron2, pytorch-image-models, and mmcv), based on my personal development experience, I developed a SIMPLE enough, GENERIC enough, and STRONG enough PyTorch Trainer: core-pytorch-utils, also named CPU. CPU covers most details in the process of training a deep neural network, including: Auto logging to console and tensorboard. Auto checkpointing. Argument parser which can load a YAML configuration file. Make ALL PyTorch LR scheduler supporting warmup. Support distributed training. Support Automatically Mixed Precision (AMP) training. I try to keep the project code as simple and readable as possible. So the code comments are very detailed and everyone can understand them. What's more, a good document is also available: CPU document For deep learning green hands, you can learn how to: write a standard and clean training loop. use AMP to speed up your training. save checkpoint, and resume from it. perform more smooth, and readable logging. use the popular visualization library: tensorboard. For old hands, we can talk about whether the structure of CPU is elegant and reasonable. I have thought a lot about this framework, combining the advantages of several popular frameworks and discarding their shortcomings. Welcome to use it!

[D] Here are 17 ways of making PyTorch training faster – what did I miss?

I've been collecting methods to accelerate training in PyTorch – here's what I've found so far. What did I miss? What did I get wrong? The methods – roughly sorted from largest to smallest expected speed-up – are: Consider using a different learning rate schedule. Use multiple workers and pinned memory in DataLoader. Max out the batch size. Use Automatic Mixed Precision (AMP). Consider using a different optimizer. Turn on cudNN benchmarking. Beware of frequently transferring data between CPUs and GPUs. Use gradient/activation checkpointing. Use gradient accumulation. Use DistributedDataParallel for multi-GPU training. Set gradients to None rather than 0. Use .as\_tensor rather than .tensor() Turn off debugging APIs if not needed. Use gradient clipping. Turn off bias before BatchNorm. Turn off gradient computation during validation. Use input and batch normalization. Consider using another learning rate schedule The learning rate (schedule) you choose has a large impact on the speed of convergence as well as the generalization performance of your model. Cyclical Learning Rates and the 1Cycle learning rate schedule are both methods introduced by Leslie N. Smith (here and here), and then popularised by fast.ai's Jeremy Howard and Sylvain Gugger (here and here). Essentially, the 1Cycle learning rate schedule looks something like this: &#x200B; https://preview.redd.it/sc37u5knmxa61.png?width=476&format=png&auto=webp&s=09b309b4dbd67eedb4ab5f86e03e0e83d7b072d1 Sylvain writes: \[1cycle consists of\]  two steps of equal lengths, one going from a lower learning rate to a higher one than go back to the minimum. The maximum should be the value picked with the Learning Rate Finder, and the lower one can be ten times lower. Then, the length of this cycle should be slightly less than the total number of epochs, and, in the last part of training, we should allow the learning rate to decrease more than the minimum, by several orders of magnitude. In the best case this schedule achieves a massive speed-up – what Smith calls Superconvergence – as compared to conventional learning rate schedules. Using the 1Cycle policy he needs \~10x fewer training iterations of a ResNet-56 on ImageNet to match the performance of the original paper, for instance). The schedule seems to perform robustly well across common architectures and optimizers. PyTorch implements both of these methods torch.optim.lrscheduler.CyclicLR and torch.optim.lrscheduler.OneCycleLR, see the documentation. One drawback of these schedulers is that they introduce a number of additional hyperparameters. This post and this repo, offer a nice overview and implementation of how good hyper-parameters can be found including the Learning Rate Finder mentioned above. Why does this work? It doesn't seem entirely clear but one possible explanation might be that regularly increasing the learning rate helps to traverse saddle points in the loss landscape more quickly. Use multiple workers and pinned memory in DataLoader When using torch.utils.data.DataLoader, set numworkers > 0, rather than the default value of 0, and pinmemory=True, rather than the default value of False. Details of this are explained here. Szymon Micacz achieves a 2x speed-up for a single training epoch by using four workers and pinned memory. A rule of thumb that people are using to choose the number of workers is to set it to four times the number of available GPUs with both a larger and smaller number of workers leading to a slow down. Note that increasing num\_workerswill increase your CPU memory consumption. Max out the batch size This is a somewhat contentious point. Generally, however, it seems like using the largest batch size your GPU memory permits will accelerate your training (see NVIDIA's Szymon Migacz, for instance). Note that you will also have to adjust other hyperparameters, such as the learning rate, if you modify the batch size. A rule of thumb here is to double the learning rate as you double the batch size. OpenAI has a nice empirical paper on the number of convergence steps needed for different batch sizes. Daniel Huynh runs some experiments with different batch sizes (also using the 1Cycle policy discussed above) where he achieves a 4x speed-up by going from batch size 64 to 512. One of the downsides of using large batch sizes, however, is that they might lead to solutions that generalize worse than those trained with smaller batches. Use Automatic Mixed Precision (AMP) The release of PyTorch 1.6 included a native implementation of Automatic Mixed Precision training to PyTorch. The main idea here is that certain operations can be run faster and without a loss of accuracy at semi-precision (FP16) rather than in the single-precision (FP32) used elsewhere. AMP, then, automatically decide which operation should be executed in which format. This allows both for faster training and a smaller memory footprint. In the best case, the usage of AMP would look something like this: import torch Creates once at the beginning of training scaler = torch.cuda.amp.GradScaler() for data, label in data_iter: optimizer.zero_grad() Casts operations to mixed precision with torch.cuda.amp.autocast(): loss = model(data) Scales the loss, and calls backward() to create scaled gradients scaler.scale(loss).backward() Unscales gradients and calls or skips optimizer.step() scaler.step(optimizer) Updates the scale for next iteration scaler.update() Benchmarking a number of common language and vision models on NVIDIA V100 GPUs, Huang and colleagues find that using AMP over regular FP32 training yields roughly 2x – but upto 5.5x – training speed-ups. Currently, only CUDA ops can be autocast in this way. See the documentation here for more details on this and other limitations. u/SVPERBlA points out that you can squeeze out some additional performance (\~ 20%) from AMP on NVIDIA Tensor Core GPUs if you convert your tensors to the Channels Last memory format. Refer to this section in the NVIDIA docs for an explanation of the speedup and more about NCHW versus NHWC tensor formats. Consider using another optimizer AdamW is Adam with weight decay (rather than L2-regularization) which was popularized by fast.ai and is now available natively in PyTorch as torch.optim.AdamW. AdamW seems to consistently outperform Adam in terms of both the error achieved and the training time. See this excellent blog post on why using weight decay instead of L2-regularization makes a difference for Adam. Both Adam and AdamW work well with the 1Cycle policy described above. There are also a few not-yet-native optimizers that have received a lot of attention recently, most notably LARS (pip installable implementation) and LAMB. NVIDA's APEX implements fused versions of a number of common optimizers such as Adam. This implementation avoid a number of passes to and from GPU memory as compared to the PyTorch implementation of Adam, yielding speed-ups in the range of 5%. Turn on cudNN benchmarking If your model architecture remains fixed and your input size stays constant, setting torch.backends.cudnn.benchmark = True might be beneficial (docs). This enables the cudNN autotuner which will benchmark a number of different ways of computing convolutions in cudNN and then use the fastest method from then on. For a rough reference on the type of speed-up you can expect from this, Szymon Migacz achieves a speed-up of 70% on a forward pass for a convolution and a 27% speed-up for a forward + backward pass of the same convolution. One caveat here is that this autotuning might become very slow if you max out the batch size as mentioned above. Beware of frequently transferring data between CPUs and GPUs Beware of frequently transferring tensors from a GPU to a CPU using tensor.cpu() and vice versa using tensor.cuda() as these are relatively expensive. The same applies for .item() and .numpy() – use .detach() instead. If you are creating a new tensor, you can also directly assign it to your GPU using the keyword argument device=torch.device('cuda:0'). If you do need to transfer data, using .to(non_blocking=True), might be useful as long as you don't have any synchronization points after the transfer. If you really have to, you might want to give Santosh Gupta's SpeedTorch a try, although it doesn't seem entirely clear when this actually does/doesn't provide speed-ups. Use gradient/activation checkpointing Quoting directly from the documentation: Checkpointing works by trading compute for memory. Rather than storing all intermediate activations of the entire computation graph for computing backward, the checkpointed part does not save intermediate activations, and instead recomputes them in backward pass. It can be applied on any part of a model. Specifically, in the forward pass, function will run in torch.no\grad() manner, i.e., not storing the intermediate activations. Instead, the forward pass saves the inputs tuple and the functionparameter. In the backwards pass, the saved inputs and function is retrieved, and the forward pass is computed on function again, now tracking the intermediate activations, and then the gradients are calculated using these activation values. So while this will might slightly increase your run time for a given batch size, you'll significantly reduce your memory footprint. This in turn will allow you to further increase the batch size you're using allowing for better GPU utilization. While checkpointing is implemented natively as torch.utils.checkpoint(docs), it does seem to take some thought and effort to implement properly. Priya Goyal has a good tutorial demonstrating some of the key aspects of checkpointing. Use gradient accumulation Another approach to increasing the batch size is to accumulate gradients across multiple .backward() passes before calling optimizer.step(). Following a post by Hugging Face's Thomas Wolf, gradient accumulation can be implemented as follows: model.zero_grad() Reset gradients tensors for i, (inputs, labels) in enumerate(training_set): predictions = model(inputs) Forward pass loss = loss_function(predictions, labels) Compute loss function loss = loss / accumulation_steps Normalize our loss (if averaged) loss.backward() Backward pass if (i+1) % accumulation_steps == 0: Wait for several backward steps optimizer.step() Now we can do an optimizer step model.zero_grad() Reset gradients tensors if (i+1) % evaluation_steps == 0: Evaluate the model when we... evaluate_model() ...have no gradients accumulate This method was developed mainly to circumvent GPU memory limitations and I'm not entirely clear on the trade-off between having additional .backward() loops. This discussion on the fastai forum seems to suggest that it can in fact accelerate training, so it's probably worth a try. Use Distributed Data Parallel for multi-GPU training Methods to accelerate distributed training probably warrant their own post but one simple one is to use torch.nn.DistributedDataParallel rather than torch.nn.DataParallel. By doing so, each GPU will be driven by a dedicated CPU core avoiding the GIL issues of DataParallel. In general, I can strongly recommend reading the documentation on distributed training. Set gradients to None rather than 0 Use .zerograd(settonone=True) rather than .zerograd(). Doing so will let the memory allocator handle the gradients rather than actively setting them to 0. This will lead to yield a modest speed-up as they say in the documentation, so don't expect any miracles. Watch out, doing this is not side-effect free! Check the docs for the details on this. Use .as_tensor() rather than .tensor() torch.tensor() always copies data. If you have a numpy array that you want to convert, use torch.astensor() or torch.fromnumpy() to avoid copying the data. Turn on debugging tools only when actually needed PyTorch offers a number of useful debugging tools like the autograd.profiler, autograd.grad\check, and autograd.anomaly\detection. Make sure to use them to better understand when needed but to also turn them off when you don't need them as they will slow down your training. Use gradient clipping Originally used to avoid exploding gradients in RNNs, there is both some empirical evidence as well as some theoretical support that clipping gradients (roughly speaking: gradient = min(gradient, threshold)) accelerates convergence. Hugging Face's Transformer implementation is a really clean example of how to use gradient clipping as well as some of the other methods such as AMP mentioned in this post. In PyTorch this can be done using torch.nn.utils.clipgradnorm(documentation). It's not entirely clear to me which models benefit how much from gradient clipping but it seems to be robustly useful for RNNs, Transformer-based and ResNets architectures and a range of different optimizers. Turn off bias before BatchNorm This is a very simple one: turn off the bias of layers before BatchNormalization layers. For a 2-D convolutional layer, this can be done by setting the bias keyword to False: torch.nn.Conv2d(..., bias=False, ...).  (Here's a reminder why this makes sense.) You will save some parameters, I would however expect the speed-up of this to be relatively small as compared to some of the other methods mentioned here. Turn off gradient computation during validation This one is straightforward: set torch.no_grad() during validation. Use input and batch normalization You're probably already doing this but you might want to double-check: Are you normalizing your input? Are you using batch-normalization? And here's a reminder of why you probably should. Bonus tip from the comments: Use JIT to fuse point-wise operations. If you have adjacent point-wise operations you can use PyTorch JIT to combine them into one FusionGroup which can then be launched on a single kernel rather than multiple kernels as would have been done per default. You'll also save some memory reads and writes. Szymon Migacz shows how you can use the @torch.jit.script decorator to fuse the operations in a GELU, for instance: @torch.jit.script def fused_gelu(x): return x 0.5 (1.0 + torch.erf(x / 1.41421)) In this case, fusing the operations leads to a 5x speed-up for the execution of fused_gelu as compared to the unfused version. See also this post for an example of how Torchscript can be used to accelerate an RNN. Hat tip to u/Patient_Atmosphere45 for the suggestion. Sources and additional resources Many of the tips listed above come from Szymon Migacz' talk and post in the PyTorch docs. PyTorch Lightning's William Falcon has two interesting posts with tips to speed-up training. PyTorch Lightning does already take care of some of the points above per-default. Thomas Wolf at Hugging Face has a number of interesting articles on accelerating deep learning – with a particular focus on language models. The same goes for Sylvain Gugger and Jeremy Howard: they have many interesting posts in particular on learning rates and AdamW. Thanks to Ben Hahn, Kevin Klein and Robin Vaaler for their feedback on a draft of this post! I've also put all of the above into this blog post.

[D] What are some good advanced platforms?

Hey. I'm 27 and I think I got most of the basics for ML. I'm very good at math, I understand statistics and probability quite deep, worked on research projects by myself, for which I had to build models on my own. Not really complex, but still requiring creativity and a good understanding of basic concepts. I will soon start a data science job at a FAANG company and I want to further improve my skills and use their resources to the fullest, but I'm not really sure where to go from here in terms of learning. Could you help me with some more advanced materials/forums for ML research/place with good papers/place with good articles? I'd also like to study the very best and see the way they code and explain advanced concepts (like Andrej Karpathy) where can I find them?? is there a Twitch for challenger level AI researchers streaming live processes? Or videos showing the entire project flow (how they do data visualizations, mining, choosing models, tuning, etc) like top digital artists show the highlights or the entire speed-up of their painting processes? Here's a list all of my projects to get a general idea of my level and where I'm at: calculating the distance between hundreds of 42.000 feature objects (containing categorical, strings, numbers, hashes, booleans as variables) and then clustering. with some vector processing and a neural network implemented from scratch in C some models like ARIMA (together with linear regression) combining a FFT with a neural network for a 42d wave classification T-SNE to split dataset into 2d grids -> Kullback–Leibler on grids for distance -> DBSCAN/KMEANS for clustering genetic algorithms for hyperparameter optimizations and reinforcement learning (neuro evolution) DBSCAN -> Levenberg-Marquardt for polynomial coefficients-> neural network predicting the coefficients based on different parameters playing with instance segmentation and some algorithms to synchronize a color and a depth camera simulations/statistics/probabilities for video games a lot of visualizations and data mining for patterns As you can see there is no LLM/ Generative AI/ Computer Vision stuff, which I would like to get into. I'm also not 100% sure what else would be nice to learn in general. I know most of the basic procedures for training, balancing datasets, avoid overfit, computing error plots, comparing models, etc and I'm familiar with most of math (not insanely advanced) used in ML. I didn't read many papers, but holy ... most of them are so unreadable and filled with pompous nonsense that 99% of the effort is de-obfuscating the bs and reading for so long just to figure out how the input is encoded, what's the output, and what's the model. Where can I find good, readable, structured papers which are actually on point? I'm from Eastern Europe and most of my learning has been done by my self after high school, the education quality is close to zero in the universities here and I never had any mentors at the jobs I worked. There's no research in this country, and getting to work on these projects was insanely hard, some of them being done in my free time or for free just to get experience... Fortunately after a lot of hard work I got into FAANG, and I hope things will be better here. Most of what I've learned has been from very fragmented places on the internet, and now I'm looking for centralized places and communities of top quality content. TL;DR: sorry for the long rambling. had to order my thoughts and figure what i actually want: Looking for top tier AI researchers showcasing their work processes, places with clear papers/articles, tips for someone who's no longer a very beginner, and other communities like this.

[P] Evaluating several topic modeling implementations. What's the current best practice? BERTopic? OpenAI Ada-002?

I have a set of \~100 topic categories, and I want to determine which are semantically close to a text input. I've found several implementations, but I know some (LDA) are already obsolete. OpenAI's text-embedding-ada-002 model just came out so I'm wondering if that's the best option now. Other topic modeling implementations: Multi-Class Text Classification with Doc2Vec & Logistic Regression Build taxonomy-based contextual targeting using AWS Media Intelligence and Hugging Face BERT Topic Modeling with BERTopic

[P] I created a package implementing a SOTA technique for XAI ( Explainable AI)

This is the package https://github.com/mfumagalli68/xi-method Follow the README and install directly from pypi. From the paper: " \[..\]To bridge this gap we propose a family of measures of statistical association whose definition is well-posed also for nonordered data. Our intuition is to rely on separation measurements between probability mass functions. Here, by separation measurement we mean any distance or divergence between probability mass functions that is positive, and that is null if and only if the probability mass functions coincide. Then, we show that the new class of sensitivity indices complies with Renyi’s postulate D of measures of statistical dependence (Renyi, 1959). This postulate, called zero-independence property in the following, requires that a measure of association is null if and only if the two random variables are statistically independent. We address the estimation of this new class of indicators for generic samples, and discuss their asymptotic convergence. We then use these probabilistic sensitivity measures in the context of explainability. A relevant aspect related to measures of statistical association is that they can be computed directly on the original dataset without the need of actually fitting a machine learning model. Thus, not only are they model agnostic in explaining the behavior of a black box, but they also provide pre-hoc explanations. Our intuition is then to compare explanations provided by measures of statistical association first calculated on the original data (the pre-hoc explanations) and then on the forecasts of the machine learning model fitted to the data (post-hoc explanations). This comparison provides an indication on whether the ML model predictions capture the statistical dependence originally present in the data. We call the resulting approach Xi-method\[...\] " The paper can't be shared freely, but as always with a little bit of research you can find it online. If you find it interesting, star the repo. &#x200B; Thanks

[N] Implementing AI/ML Models From Scratch (stylepoint)

Hi folks, I am stylepoint. Currently work as an ML Research Scientist in academia. I have recently created a YouTube channel and started the YouTube video series called "Implement," where I will be implementing software (duh!). I will first implement machine learning and deep learning algorithms and models from scratch (means using Python with numpy, but no other third-party libraries/modules). My assumptions for AI/ML videos: One is familiar with the theory One is familiar with Python This is since for AI/ML, Python is the language of choice for many (including myself) Due to these assumptions, videos tend to be approximately 10 - 15 minutes long. So it should not be too hard to digest. As of now, only one video has been released, but more to come! And we will definitely not limit ourselves to only implementing AI/ML models. I will be making videos about software engineering, software design, programming languages, math, emerging technologies, etc. as well! Just wanted to share this in case anyone finds the series interesting or helpful. Thanks y'all! Links: YouTube GitHub Web First video (Implementing Gaussian Naive Bayes from Scratch) UPDATE: Another video: Implementing K-Nearest Neighbors (k-NN) from Scratch

[D]Stuck in AI Hell: What to do in post LLM world

Hey Reddit, I’ve been in an AI/ML role for a few years now, and I’m starting to feel disconnected from the work. When I started, deep learning models were getting good, and I quickly fell in love with designing architectures, training models, and fine-tuning them for specific use cases. Seeing a loss curve finally converge, experimenting with layers, and debugging training runs—it all felt like a craft, a blend of science and creativity. I enjoyed implementing research papers to see how things worked under the hood. Backprop, gradients, optimization—it was a mental workout I loved. But these days, it feels like everything has shifted. LLMs dominate the scene, and instead of building and training models, the focus is on using pre-trained APIs, crafting prompt chains, and setting up integrations. Sure, there’s engineering involved, but it feels less like creating and more like assembling. I miss the hands-on nature of experimenting with architectures and solving math-heavy problems. It’s not just the creativity I miss. The economics of this new era also feel strange to me. Back when I started, compute was a luxury. We had limited GPUs, and a lot of the work was about being resourceful—quantizing models, distilling them, removing layers, and squeezing every bit of performance out of constrained setups. Now, it feels like no one cares about cost. We’re paying by tokens. Tokens! Who would’ve thought we’d get to a point where we’re not designing efficient models but feeding pre-trained giants like they’re vending machines? I get it—abstraction has always been part of the field. TensorFlow and PyTorch abstracted tensor operations, Python abstracts C. But deep learning still left room for creation. We weren’t just abstracting away math; we were solving it. We could experiment, fail, and tweak. Working with LLMs doesn’t feel the same. It’s like fitting pieces into a pre-defined puzzle instead of building the puzzle itself. I understand that LLMs are here to stay. They’re incredible tools, and I respect their potential to revolutionize industries. Building real-world products with them is still challenging, requiring a deep understanding of engineering, prompt design, and integrating them effectively into workflows. By no means is it an “easy” task. But the work doesn’t give me the same thrill. It’s not about solving math or optimization problems—it’s about gluing together APIs, tweaking outputs, and wrestling with opaque systems. It’s like we’ve traded craftsmanship for convenience. Which brings me to my questions: Is there still room for those of us who enjoy the deep work of model design and training? Or is this the inevitable evolution of the field, where everything converges on pre-trained systems? What use cases still need traditional ML expertise? Are there industries or problems that will always require specialized models instead of general-purpose LLMs? Am I missing the bigger picture here? LLMs feel like the “kernel” of a new computing paradigm, and we don’t fully understand their second- and third-order effects. Could this shift lead to new, exciting opportunities I’m just not seeing yet? How do you stay inspired when the focus shifts? I still love AI, but I miss the feeling of building something from scratch. Is this just a matter of adapting my mindset, or should I seek out niches where traditional ML still thrives? I’m not asking this to rant (though clearly, I needed to get some of this off my chest). I want to figure out where to go next from here. If you’ve been in AI/ML long enough to see major shifts—like the move from feature engineering to deep learning—how did you navigate them? What advice would you give someone in my position? And yeah, before anyone roasts me for using an LLM to structure this post (guilty!), I just wanted to get my thoughts out in a coherent way. Guess that’s a sign of where we’re headed, huh? Thanks for reading, and I’d love to hear your thoughts! TL;DR: I entered AI during the deep learning boom, fell in love with designing and training models, and thrived on creativity, math, and optimization. Now it feels like the field is all about tweaking prompts and orchestrating APIs for pre-trained LLMs. I miss the thrill of crafting something unique. Is there still room for people who enjoy traditional ML, or is this just the inevitable evolution of the field? How do you stay inspired amidst such shifts? Update: Wow, this blew up. Thanks everyone for your comments and suggestions. I really like some of those. This thing was on my mind for a long time, glad that I put it here. Thanks again!

looking for ML aficionado in London for great chats and maybe a startup

TL;DR? Here's the gist: Me: 3 startups under my belt. Started as a programmer, then trainer, then entrepreneur, now CTO & Board member for a leading customer insight company part of large bank. Large system and infrastructure specialist. Extensive & practical experience in raising funds and successfully managing both startup and established businesses. Fascinated by the power of data. Can't imagine myself spending the rest of my life being a cog in the machine. You: Machine learning specialist, programmer, analyst, understands how to navigate and crunch large datasets, from BI to predictive analytics. Interested in implementing applications from fraud detection to margin improvements through better clustering regardless of industry. Fascinated by the power of data. Can't imagine himself spending the rest of his or her life being a cog in the machine. The startup: The core idea it to build platforms and systems around the progressively larger datasets held by various sized companies, helping them solve big issues - cost reduction, profitability and reducing risk. I’m an infrastructure and software specialist and have access to 1) systems, 2) datasets 3) extensive practical in certain industry segments, namely web-scale companies and tier 1 retailers. This project is in the very early planning stages. I'm looking forward to discuss the form it could take with like-minded individuals but with complementary skills sets, namely: predictive analytics & AI as it applies to machine learning on large datasets. Want more specifics ideas? I have plenty of these, but I’m sure you do to, so let’s meet face to face and discuss them. Ultimately the goal is to crystallize on a specific concept, develop together a minimum viable product and get the company bootstrapped or angel-funded (something I also have plenty of experience with), all via a lean startup model. My philosophy on startups: Startups built in one’s free time often fail because they drag on, ending up as little more than side projects you can’t quite get rid of (due to co-founder guilt, or perhaps the little money they bring in every month). The core idea for this project is based on lean, that is, to launch a minimum viable product as early as possible. Getting feedback. Measuring results (important!). Pivot if it’s not working. This helps tremendously in staying motivated, limits the dreaded paralyzing fear of failure, and more importantly, keep the time from inception to first client/funding to a minimum. If it sounds interesting please message me and we can exchange contact details! Worst that can happen is we have a great chat!

[D] Accessibility of Basic Models to Non-Technicals

Hello /r/machinelearning! I'm doing some research on easily generated models by non-technical/statistical people. It would be awesome if some of you could answer a quick questionnaire: If you're a machine learning developer/data scientist etc.: a) Has your manager/product lead etc. ever insist that you build a model on a correlation you felt wasn't there? b) Do you think if that people had a way to verify the lack of correlation through a naive model (random forest, svc, etc.) that it would have changed the situation? (Or, if you were able to show them the results) c) Would you want this technology for yourself, or wish that your company would have access to it? If you're a non-technical person (small business developer, student, non-tech entrepreneur, etc.): a) Have you ever not pursued a potential machine learning/data solution or feature because you weren't willing to invest the resources to see if it was viable? b) Would being able to verify correlations in your data (or lack thereof!) entice you to pursue possible machine learning solutions? c) Even if your previous answers were no, would you be interested in having this technology? Thanks in advance for all of the responses, I will personally read and respond to each one of you thoughtful enough to give me a response. Also, I hope this post will spark an interesting conversation about the barrier of entry to AI/machine learning.

[D] Should the praise of "Data-centric" AI be taken with a grain of salt?

I hear co-workers, professors, entrepreneurs talk about just how important it is to switch from model-centric AI to a data-centric approach. Personally I don't see a problem focusing on attaining better data but I have been seeing this simplification that AI performance = model + data which seems massively misleading. A better generalization would be AI performance = model data or even AI performance = model log(len(data)). Looking at the rapidly changing problem of image synthesis, it is clear that data alone could not produce the same results seen even two years ago. On the other hand, it can seem unproductive for the field as a whole to try to create another classification model that achieves a .02% increased performance on ImageNet... again and again... And this is maybe why we hear more talk in industry about focusing on the data instead of models: Industry generally faces simpler tasks with negligible improvement as of recently (regression, classification). Therefore it's more easy and valuable to increase and improve the training data. And yes, most machine learning models NEED a large training set to approximate a complex distribution. We have already known this since forever. I think the term has just recently become a pet peeve for me as a novel "catch all" solution to any problem. What are your opinions on the matter?

[P] Jarvislabs.ai - An Affordable GPU Cloud with Fast launch, Pause and Resume. Scale GPUs post creation. A100/RTX6K/RTX5K

For the last few years, I have been learning and practicing Deep Learning. Participated in several Kaggle competitions and won few medals. During all these years, I tried several cloud platforms and on-premise systems. Some of them offered simplicity, flexibility, and affordability. But very few to none offered all of these in one platform. After struggling with different platforms, I know what I would need as a DL researcher. That gave birth to jarvislabs.ai with the aim of being simple and affordable. I along with my friends started working on this project a year back. Due to Covid, executing the project became more challenging. As first-time entrepreneurs, we underestimated the complexity of the problem at hand but with persistence, we were able to launch a beta version of the product in December 2020. With some of the amazing feedback from our early adopters, we have been able to make the product smoother. We would love to invite you all to come and try the platform. Features 1 click Jupyter Lab < \[30 seconds\] Pause the instance and Resume from where you left. SSH to the instance. Scale GPUs, storage and change GPU type on resume. Auto-Pause using jarviscloud.pause() in your code, so you can catch up some good night’s sleep while your model trains. Pay per usage – Minute Billing \[After first 15 minutes\] Competitive pricing \[Lowest to our Knowledge\]. &#x200B; Pricing |GPU Type|GPU RAM|Price -$/hr| |:-|:-|:-| |RTX 5000|16 GB|0.49| |RTX 6000|24 GB|0.99| |A100|40 GB|2.39| &#x200B; Talk to us We will be happy to assist you in spinning your first instance and many more. You can use one of these platforms to reach us. Chat option on cloud.jarvislabs.ai Email us - hello@jarvislabs.ai Comment here. We have come a long way, but we understand that a lot more has to be done. We have listed down all the upcoming product features here. Deep learning and AI are evolving and how we would use the cloud platforms could evolve in the coming years. Understanding this, we develop in the open by constantly keeping in touch with our users. Please help us in shaping Jarvislabs.ai with any valuable suggestions/feedback.

[N] Interview with Justin Harris, one of the best experts on Decentralizing of AI

Hi, we just started our new series of chats with ML practitioners. Many times, it's just hard to associate a specific piece of machine learning research or technology with the creators behind the scene. However, learning about the experience gained by researchers, engineers and entrepreneurs doing real machine learning work can result in a great source of knowledge and inspiration. Please meet Justin Harris, the Senior Software Developer at Microsoft Research who recently published the paper Decentralized & Collaborative AI on Blockchain. Justin is currently using his experience in machine learning and crowdsourcing to implement a framework for ML in smart contracts in order to collect quality data and provide models that are free to use. We asked him why decentralization is important for the future of AI. Justin shared with us his vision about incentive mechanisms for decentralized AI architectures. We also spoke about federated learning, the challenges of implementation and its dependence on mobile deep learning, and some other exciting things.  Please check it out here and if you like it, do share. No subscription is needed: https://thesequence.substack.com/p/harris &#x200B; https://preview.redd.it/wp1qp9tn7s361.png?width=1760&format=png&auto=webp&s=e909a99d4921fac0669f9c8630ab28b34cf8e413

[D] Gary Marcus and Luis Lamb -- discussion of AGI and Neurosymbolic methods

https://youtu.be/nhUt6mKCPf8 Pod: https://anchor.fm/machinelearningstreettalk/episodes/54-Gary-Marcus-and-Luis-Lamb---Neurosymbolic-models-e125495 Professor Gary Marcus is a scientist, best-selling author, and entrepreneur. He is Founder and CEO of Robust.AI, and was Founder and CEO of Geometric Intelligence, a machine learning company acquired by Uber in 2016. Gary said in his recent next decade paper that — without us, or other creatures like us, the world would continue to exist, but it would not be described, distilled, or understood. Human lives are filled with abstraction and causal description. This is so powerful. Francois Chollet the other week said that intelligence is literally sensitivity to abstract analogies, and that is all there is to it. It's almost as if one of the most important features of intelligence is to be able to abstract knowledge, this drives the generalisation which will allow you to mine previous experience to make sense of many future novel situations. Also joining us today is Professor Luis Lamb — Secretary of Innovation for Science and Technology of the State of Rio Grande do Sul, Brazil. His Research Interests are Machine Learning and Reasoning, Neuro-Symbolic Computing, Logic in Computation and Artificial Intelligence, Cognitive and Neural Computation and also AI Ethics and Social Computing. Luis released his new paper Neurosymbolic AI: the third wave at the end of last year. It beautifully articulated the key ingredients needed in the next generation of AI systems, integrating type 1 and type 2 approaches to AI and it summarises all the of the achievements of the last 20 years of research. We cover a lot of ground in today's show. Explaining the limitations of deep learning, Rich Sutton's the bitter lesson and "reward is enough", and the semantic foundation which is required for us to build robust AI.

Interview with Juergen Schmidhuber, renowned ‘Father Of Modern AI’, says his life’s work won't lead to dystopia.

Schmidhuber interview expressing his views on the future of AI and AGI. Original source. I think the interview is of interest to r/MachineLearning, and presents an alternate view, compared to other influential leaders in AI. Juergen Schmidhuber, Renowned 'Father Of Modern AI,' Says His Life’s Work Won't Lead To Dystopia May 23, 2023. Contributed by Hessie Jones. Amid the growing concern about the impact of more advanced artificial intelligence (AI) technologies on society, there are many in the technology community who fear the implications of the advancements in Generative AI if they go unchecked. Dr. Juergen Schmidhuber, a renowned scientist, artificial intelligence researcher and widely regarded as one of the pioneers in the field, is more optimistic. He declares that many of those who suddenly warn against the dangers of AI are just seeking publicity, exploiting the media’s obsession with killer robots which has attracted more attention than “good AI” for healthcare etc. The potential to revolutionize various industries and improve our lives is clear, as are the equal dangers if bad actors leverage the technology for personal gain. Are we headed towards a dystopian future, or is there reason to be optimistic? I had a chance to sit down with Dr. Juergen Schmidhuber to understand his perspective on this seemingly fast-moving AI-train that will leap us into the future. As a teenager in the 1970s, Juergen Schmidhuber became fascinated with the idea of creating intelligent machines that could learn and improve on their own, becoming smarter than himself within his lifetime. This would ultimately lead to his groundbreaking work in the field of deep learning. In the 1980s, he studied computer science at the Technical University of Munich (TUM), where he earned his diploma in 1987. His thesis was on the ultimate self-improving machines that, not only, learn through some pre-wired human-designed learning algorithm, but also learn and improve the learning algorithm itself. Decades later, this became a hot topic. He also received his Ph.D. at TUM in 1991 for work that laid some of the foundations of modern AI. Schmidhuber is best known for his contributions to the development of recurrent neural networks (RNNs), the most powerful type of artificial neural network that can process sequential data such as speech and natural language. With his students Sepp Hochreiter, Felix Gers, Alex Graves, Daan Wierstra, and others, he published architectures and training algorithms for the long short-term memory (LSTM), a type of RNN that is widely used in natural language processing, speech recognition, video games, robotics, and other applications. LSTM has become the most cited neural network of the 20th century, and Business Week called it "arguably the most commercial AI achievement." Throughout his career, Schmidhuber has received various awards and accolades for his groundbreaking work. In 2013, he was awarded the Helmholtz Prize, which recognizes significant contributions to the field of machine learning. In 2016, he was awarded the IEEE Neural Network Pioneer Award for "pioneering contributions to deep learning and neural networks." The media have often called him the “father of modern AI,” because the most cited neural networks all build on his lab’s work. He is quick to point out, however, that AI history goes back centuries. Despite his many accomplishments, at the age of 60, he feels mounting time pressure towards building an Artificial General Intelligence within his lifetime and remains committed to pushing the boundaries of AI research and development. He is currently director of the KAUST AI Initiative, scientific director of the Swiss AI Lab IDSIA, and co-founder and chief scientist of AI company NNAISENSE, whose motto is "AI∀" which is a math-inspired way of saying "AI For All." He continues to work on cutting-edge AI technologies and applications to improve human health and extend human lives and make lives easier for everyone. The following interview has been edited for clarity. Jones: Thank you Juergen for joining me. You have signed letters warning about AI weapons. But you didn't sign the recent publication, "Pause Gigantic AI Experiments: An Open Letter"? Is there a reason? Schmidhuber: Thank you Hessie. Glad to speak with you. I have realized that many of those who warn in public against the dangers of AI are just seeking publicity. I don't think the latest letter will have any significant impact because many AI researchers, companies, and governments will ignore it completely. The proposal frequently uses the word "we" and refers to "us," the humans. But as I have pointed out many times in the past, there is no "we" that everyone can identify with. Ask 10 different people, and you will hear 10 different opinions about what is "good." Some of those opinions will be completely incompatible with each other. Don't forget the enormous amount of conflict between the many people. The letter also says, "If such a pause cannot be quickly put in place, governments should intervene and impose a moratorium." The problem is that different governments have ALSO different opinions about what is good for them and for others. Great Power A will say, if we don't do it, Great Power B will, perhaps secretly, and gain an advantage over us. The same is true for Great Powers C and D. Jones: Everyone acknowledges this fear surrounding current generative AI technology. Moreover, the existential threat of this technology has been publicly acknowledged by Sam Altman, CEO of OpenAI himself, calling for AI regulation. From your perspective, is there an existential threat? Schmidhuber: It is true that AI can be weaponized, and I have no doubt that there will be all kinds of AI arms races, but AI does not introduce a new quality of existential threat. The threat coming from AI weapons seems to pale in comparison to the much older threat from nuclear hydrogen bombs that don’t need AI at all. We should be much more afraid of half-century-old tech in the form of H-bomb rockets. The Tsar Bomba of 1961 had almost 15 times more destructive power than all weapons of WW-II combined. Despite the dramatic nuclear disarmament since the 1980s, there are still more than enough nuclear warheads to wipe out human civilization within two hours, without any AI I’m much more worried about that old existential threat than the rather harmless AI weapons. Jones: I realize that while you compare AI to the threat of nuclear bombs, there is a current danger that a current technology can be put in the hands of humans and enable them to “eventually” exact further harms to individuals of group in a very precise way, like targeted drone attacks. You are giving people a toolset that they've never had before, enabling bad actors, as some have pointed out, to be able to do a lot more than previously because they didn't have this technology. Schmidhuber: Now, all that sounds horrible in principle, but our existing laws are sufficient to deal with these new types of weapons enabled by AI. If you kill someone with a gun, you will go to jail. Same if you kill someone with one of these drones. Law enforcement will get better at understanding new threats and new weapons and will respond with better technology to combat these threats. Enabling drones to target persons from a distance in a way that requires some tracking and some intelligence to perform, which has traditionally been performed by skilled humans, to me, it seems is just an improved version of a traditional weapon, like a gun, which is, you know, a little bit smarter than the old guns. But, in principle, all of that is not a new development. For many centuries, we have had the evolution of better weaponry and deadlier poisons and so on, and law enforcement has evolved their policies to react to these threats over time. So, it's not that we suddenly have a new quality of existential threat and it's much more worrisome than what we have had for about six decades. A large nuclear warhead doesn’t need fancy face recognition to kill an individual. No, it simply wipes out an entire city with ten million inhabitants. Jones: The existential threat that’s implied is the extent to which humans have control over this technology. We see some early cases of opportunism which, as you say, tends to get more media attention than positive breakthroughs. But you’re implying that this will all balance out? Schmidhuber: Historically, we have a long tradition of technological breakthroughs that led to advancements in weapons for the purpose of defense but also for protection. From sticks, to rocks, to axes to gunpowder to cannons to rockets… and now to drones… this has had a drastic influence on human history but what has been consistent throughout history is that those who are using technology to achieve their own ends are themselves, facing the same technology because the opposing side is learning to use it against them. And that's what has been repeated in thousands of years of human history and it will continue. I don't see the new AI arms race as something that is remotely as existential a threat as the good old nuclear warheads. You said something important, in that some people prefer to talk about the downsides rather than the benefits of this technology, but that's misleading, because 95% of all AI research and AI development is about making people happier and advancing human life and health. Jones: Let’s touch on some of those beneficial advances in AI research that have been able to radically change present day methods and achieve breakthroughs. Schmidhuber: All right! For example, eleven years ago, our team with my postdoc Dan Ciresan was the first to win a medical imaging competition through deep learning. We analyzed female breast cells with the objective to determine harmless cells vs. those in the pre-cancer stage. Typically, a trained oncologist needs a long time to make these determinations. Our team, who knew nothing about cancer, were able to train an artificial neural network, which was totally dumb in the beginning, on lots of this kind of data. It was able to outperform all the other methods. Today, this is being used not only for breast cancer, but also for radiology and detecting plaque in arteries, and many other things. Some of the neural networks that we have developed in the last 3 decades are now prevalent across thousands of healthcare applications, detecting Diabetes and Covid-19 and what not. This will eventually permeate across all healthcare. The good consequences of this type of AI are much more important than the click-bait new ways of conducting crimes with AI. Jones: Adoption is a product of reinforced outcomes. The massive scale of adoption either leads us to believe that people have been led astray, or conversely, technology is having a positive effect on people’s lives. Schmidhuber: The latter is the likely case. There's intense commercial pressure towards good AI rather than bad AI because companies want to sell you something, and you are going to buy only stuff you think is going to be good for you. So already just through this simple, commercial pressure, you have a tremendous bias towards good AI rather than bad AI. However, doomsday scenarios like in Schwarzenegger movies grab more attention than documentaries on AI that improve people’s lives. Jones: I would argue that people are drawn to good stories – narratives that contain an adversary and struggle, but in the end, have happy endings. And this is consistent with your comment on human nature and how history, despite its tendency for violence and destruction of humanity, somehow tends to correct itself. Let’s take the example of a technology, which you are aware – GANs – General Adversarial Networks, which today has been used in applications for fake news and disinformation. In actuality, the purpose in the invention of GANs was far from what it is used for today. Schmidhuber: Yes, the name GANs was created in 2014 but we had the basic principle already in the early 1990s. More than 30 years ago, I called it artificial curiosity. It's a very simple way of injecting creativity into a little two network system. This creative AI is not just trying to slavishly imitate humans. Rather, it’s inventing its own goals. Let me explain: You have two networks. One network is producing outputs that could be anything, any action. Then the second network is looking at these actions and it’s trying to predict the consequences of these actions. An action could move a robot, then something happens, and the other network is just trying to predict what will happen. Now we can implement artificial curiosity by reducing the prediction error of the second network, which, at the same time, is the reward of the first network. The first network wants to maximize its reward and so it will invent actions that will lead to situations that will surprise the second network, which it has not yet learned to predict well. In the case where the outputs are fake images, the first network will try to generate images that are good enough to fool the second network, which will attempt to predict the reaction of the environment: fake or real image, and it will try to become better at it. The first network will continue to also improve at generating images whose type the second network will not be able to predict. So, they fight each other. The 2nd network will continue to reduce its prediction error, while the 1st network will attempt to maximize it. Through this zero-sum game the first network gets better and better at producing these convincing fake outputs which look almost realistic. So, once you have an interesting set of images by Vincent Van Gogh, you can generate new images that leverage his style, without the original artist having ever produced the artwork himself. Jones: I see how the Van Gogh example can be applied in an education setting and there are countless examples of artists mimicking styles from famous painters but image generation from this instance that can happen within seconds is quite another feat. And you know this is how GANs has been used. What’s more prevalent today is a socialized enablement of generating images or information to intentionally fool people. It also surfaces new harms that deal with the threat to intellectual property and copyright, where laws have yet to account for. And from your perspective this was not the intention when the model was conceived. What was your motivation in your early conception of what is now GANs? Schmidhuber: My old motivation for GANs was actually very important and it was not to create deepfakes or fake news but to enable AIs to be curious and invent their own goals, to make them explore their environment and make them creative. Suppose you have a robot that executes one action, then something happens, then it executes another action, and so on, because it wants to achieve certain goals in the environment. For example, when the battery is low, this will trigger “pain” through hunger sensors, so it wants to go to the charging station, without running into obstacles, which will trigger other pain sensors. It will seek to minimize pain (encoded through numbers). Now the robot has a friend, the second network, which is a world model ––it’s a prediction machine that learns to predict the consequences of the robot’s actions. Once the robot has a good model of the world, it can use it for planning. It can be used as a simulation of the real world. And then it can determine what is a good action sequence. If the robot imagines this sequence of actions, the model will predict a lot of pain, which it wants to avoid. If it plays this alternative action sequence in its mental model of the world, then it will predict a rewarding situation where it’s going to sit on the charging station and its battery is going to load again. So, it'll prefer to execute the latter action sequence. In the beginning, however, the model of the world knows nothing, so how can we motivate the first network to generate experiments that lead to data that helps the world model learn something it didn’t already know? That’s what artificial curiosity is about. The dueling two network systems effectively explore uncharted environments by creating experiments so that over time the curious AI gets a better sense of how the environment works. This can be applied to all kinds of environments, and has medical applications. Jones: Let’s talk about the future. You have said, “Traditional humans won’t play a significant role in spreading intelligence across the universe.” Schmidhuber: Let’s first conceptually separate two types of AIs. The first type of AI are tools directed by humans. They are trained to do specific things like accurately detect diabetes or heart disease and prevent attacks before they happen. In these cases, the goal is coming from the human. More interesting AIs are setting their own goals. They are inventing their own experiments and learning from them. Their horizons expand and eventually they become more and more general problem solvers in the real world. They are not controlled by their parents, but much of what they learn is through self-invented experiments. A robot, for example, is rotating a toy, and as it is doing this, the video coming in through the camera eyes, changes over time and it begins to learn how this video changes and learns how the 3D nature of the toy generates certain videos if you rotate it a certain way, and eventually, how gravity works, and how the physics of the world works. Like a little scientist! And I have predicted for decades that future scaled-up versions of such AI scientists will want to further expand their horizons, and eventually go where most of the physical resources are, to build more and bigger AIs. And of course, almost all of these resources are far away from earth out there in space, which is hostile to humans but friendly to appropriately designed AI-controlled robots and self-replicating robot factories. So here we are not talking any longer about our tiny biosphere; no, we are talking about the much bigger rest of the universe. Within a few tens of billions of years, curious self-improving AIs will colonize the visible cosmos in a way that’s infeasible for humans. Those who don’t won’t have an impact. Sounds like science fiction, but since the 1970s I have been unable to see a plausible alternative to this scenario, except for a global catastrophe such as an all-out nuclear war that stops this development before it takes off. Jones: How long have these AIs, which can set their own goals — how long have they existed? To what extent can they be independent of human interaction? Schmidhuber: Neural networks like that have existed for over 30 years. My first simple adversarial neural network system of this kind is the one from 1990 described above. You don’t need a teacher there; it's just a little agent running around in the world and trying to invent new experiments that surprise its own prediction machine. Once it has figured out certain parts of the world, the agent will become bored and will move on to more exciting experiments. The simple 1990 systems I mentioned have certain limitations, but in the past three decades, we have also built more sophisticated systems that are setting their own goals and such systems I think will be essential for achieving true intelligence. If you are only imitating humans, you will never go beyond them. So, you really must give AIs the freedom to explore previously unexplored regions of the world in a way that no human is really predefining. Jones: Where is this being done today? Schmidhuber: Variants of neural network-based artificial curiosity are used today for agents that learn to play video games in a human-competitive way. We have also started to use them for automatic design of experiments in fields such as materials science. I bet many other fields will be affected by it: chemistry, biology, drug design, you name it. However, at least for now, these artificial scientists, as I like to call them, cannot yet compete with human scientists. I don’t think it’s going to stay this way but, at the moment, it’s still the case. Sure, AI has made a lot of progress. Since 1997, there have been superhuman chess players, and since 2011, through the DanNet of my team, there have been superhuman visual pattern recognizers. But there are other things where humans, at the moment at least, are much better, in particular, science itself. In the lab we have many first examples of self-directed artificial scientists, but they are not yet convincing enough to appear on the radar screen of the public space, which is currently much more fascinated with simpler systems that just imitate humans and write texts based on previously seen human-written documents. Jones: You speak of these numerous instances dating back 30 years of these lab experiments where these self-driven agents are deciding and learning and moving on once they’ve learned. And I assume that that rate of learning becomes even faster over time. What kind of timeframe are we talking about when this eventually is taken outside of the lab and embedded into society? Schmidhuber: This could still take months or even years :-) Anyway, in the not-too-distant future, we will probably see artificial scientists who are good at devising experiments that allow them to discover new, previously unknown physical laws. As always, we are going to profit from the old trend that has held at least since 1941: every decade compute is getting 100 times cheaper. Jones: How does this trend affect modern AI such as ChatGPT? Schmidhuber: Perhaps you know that all the recent famous AI applications such as ChatGPT and similar models are largely based on principles of artificial neural networks invented in the previous millennium. The main reason why they works so well now is the incredible acceleration of compute per dollar. ChatGPT is driven by a neural network called “Transformer” described in 2017 by Google. I am happy about that because a quarter century earlier in 1991 I had a particular Transformer variant which is now called the “Transformer with linearized self-attention”. Back then, not much could be done with it, because the compute cost was a million times higher than today. But today, one can train such models on half the internet and achieve much more interesting results. Jones: And for how long will this acceleration continue? Schmidhuber: There's no reason to believe that in the next 30 years, we won't have another factor of 1 million and that's going to be really significant. In the near future, for the first time we will have many not-so expensive devices that can compute as much as a human brain. The physical limits of computation, however, are much further out so even if the trend of a factor of 100 every decade continues, the physical limits (of 1051 elementary instructions per second and kilogram of matter) won’t be hit until, say, the mid-next century. Even in our current century, however, we’ll probably have many machines that compute more than all 10 billion human brains collectively and you can imagine, everything will change then! Jones: That is the big question. Is everything going to change? If so, what do you say to the next generation of leaders, currently coming out of college and university. So much of this change is already impacting how they study, how they will work, or how the future of work and livelihood is defined. What is their purpose and how do we change our systems so they will adapt to this new version of intelligence? Schmidhuber: For decades, people have asked me questions like that, because you know what I'm saying now, I have basically said since the 1970s, it’s just that today, people are paying more attention because, back then, they thought this was science fiction. They didn't think that I would ever come close to achieving my crazy life goal of building a machine that learns to become smarter than myself such that I can retire. But now many have changed their minds and think it's conceivable. And now I have two daughters, 23 and 25. People ask me: what do I tell them? They know that Daddy always said, “It seems likely that within your lifetimes, you will have new types of intelligence that are probably going to be superior in many ways, and probably all kinds of interesting ways.” How should they prepare for that? And I kept telling them the obvious: Learn how to learn new things! It's not like in the previous millennium where within 20 years someone learned to be a useful member of society, and then took a job for 40 years and performed in this job until she received her pension. Now things are changing much faster and we must learn continuously just to keep up. I also told my girls that no matter how smart AIs are going to get, learn at least the basics of math and physics, because that’s the essence of our universe, and anybody who understands this will have an advantage, and learn all kinds of new things more easily. I also told them that social skills will remain important, because most future jobs for humans will continue to involve interactions with other humans, but I couldn’t teach them anything about that; they know much more about social skills than I do. You touched on the big philosophical question about people’s purpose. Can this be answered without answering the even grander question: What’s the purpose of the entire universe? We don’t know. But what’s happening right now might be connected to the unknown answer. Don’t think of humans as the crown of creation. Instead view human civilization as part of a much grander scheme, an important step (but not the last one) on the path of the universe from very simple initial conditions towards more and more unfathomable complexity. Now it seems ready to take its next step, a step comparable to the invention of life itself over 3.5 billion years ago. Alas, don’t worry, in the end, all will be good! Jones: Let’s get back to this transformation happening right now with OpenAI. There are many questioning the efficacy and accuracy of ChatGPT, and are concerned its release has been premature. In light of the rampant adoption, educators have banned its use over concerns of plagiarism and how it stifles individual development. Should large language models like ChatGPT be used in school? Schmidhuber: When the calculator was first introduced, instructors forbade students from using it in school. Today, the consensus is that kids should learn the basic methods of arithmetic, but they should also learn to use the “artificial multipliers” aka calculators, even in exams, because laziness and efficiency is a hallmark of intelligence. Any intelligent being wants to minimize its efforts to achieve things. And that's the reason why we have tools, and why our kids are learning to use these tools. The first stone tools were invented maybe 3.5 million years ago; tools just have become more sophisticated over time. In fact, humans have changed in response to the properties of their tools. Our anatomical evolution was shaped by tools such as spears and fire. So, it's going to continue this way. And there is no permanent way of preventing large language models from being used in school. Jones: And when our children, your children graduate, what does their future work look like? Schmidhuber: A single human trying to predict details of how 10 billion people and their machines will evolve in the future is like a single neuron in my brain trying to predict what the entire brain and its tens of billions of neurons will do next year. 40 years ago, before the WWW was created at CERN in Switzerland, who would have predicted all those young people making money as YouTube video bloggers? Nevertheless, let’s make a few limited job-related observations. For a long time, people have thought that desktop jobs may require more intelligence than skills trade or handicraft professions. But now, it turns out that it's much easier to replace certain aspects of desktop jobs than replacing a carpenter, for example. Because everything that works well in AI is happening behind the screen currently, but not so much in the physical world. There are now artificial systems that can read lots of documents and then make really nice summaries of these documents. That is a desktop job. Or you give them a description of an illustration that you want to have for your article and pretty good illustrations are being generated that may need some minimal fine-tuning. But you know, all these desktop jobs are much easier to facilitate than the real tough jobs in the physical world. And it's interesting that the things people thought required intelligence, like playing chess, or writing or summarizing documents, are much easier for machines than they thought. But for things like playing football or soccer, there is no physical robot that can remotely compete with the abilities of a little boy with these skills. So, AI in the physical world, interestingly, is much harder than AI behind the screen in virtual worlds. And it's really exciting, in my opinion, to see that jobs such as plumbers are much more challenging than playing chess or writing another tabloid story. Jones: The way data has been collected in these large language models does not guarantee personal information has not been excluded. Current consent laws already are outdated when it comes to these large language models (LLM). The concern, rightly so, is increasing surveillance and loss of privacy. What is your view on this? Schmidhuber: As I have indicated earlier: are surveillance and loss of privacy inevitable consequences of increasingly complex societies? Super-organisms such as cities and states and companies consist of numerous people, just like people consist of numerous cells. These cells enjoy little privacy. They are constantly monitored by specialized "police cells" and "border guard cells": Are you a cancer cell? Are you an external intruder, a pathogen? Individual cells sacrifice their freedom for the benefits of being part of a multicellular organism. Similarly, for super-organisms such as nations. Over 5000 years ago, writing enabled recorded history and thus became its inaugural and most important invention. Its initial purpose, however, was to facilitate surveillance, to track citizens and their tax payments. The more complex a super-organism, the more comprehensive its collection of information about its constituents. 200 years ago, at least, the parish priest in each village knew everything about all the village people, even about those who did not confess, because they appeared in the confessions of others. Also, everyone soon knew about the stranger who had entered the village, because some occasionally peered out of the window, and what they saw got around. Such control mechanisms were temporarily lost through anonymization in rapidly growing cities but are now returning with the help of new surveillance devices such as smartphones as part of digital nervous systems that tell companies and governments a lot about billions of users. Cameras and drones etc. are becoming increasingly tinier and more ubiquitous. More effective recognition of faces and other detection technology are becoming cheaper and cheaper, and many will use it to identify others anywhere on earth; the big wide world will not offer any more privacy than the local village. Is this good or bad? Some nations may find it easier than others to justify more complex kinds of super-organisms at the expense of the privacy rights of their constituents. Jones: So, there is no way to stop or change this process of collection, or how it continuously informs decisions over time? How do you see governance and rules responding to this, especially amid Italy’s ban on ChatGPT following suspected user data breach and the more recent news about the Meta’s record $1.3billion fine in the company’s handling of user information? Schmidhuber: Data collection has benefits and drawbacks, such as the loss of privacy. How to balance those? I have argued for addressing this through data ownership in data markets. If it is true that data is the new oil, then it should have a price, just like oil. At the moment, the major surveillance platforms such as Meta do not offer users any money for their data and the transitive loss of privacy. In the future, however, we will likely see attempts at creating efficient data markets to figure out the data's true financial value through the interplay between supply and demand. Even some of the sensitive medical data should not be priced by governmental regulators but by patients (and healthy persons) who own it and who may sell or license parts thereof as micro-entrepreneurs in a healthcare data market. Following a previous interview, I gave for one of the largest re-insurance companies , let's look at the different participants in such a data market: patients, hospitals, data companies. (1) Patients with a rare form of cancer can offer more valuable data than patients with a very common form of cancer. (2) Hospitals and their machines are needed to extract the data, e.g., through magnet spin tomography, radiology, evaluations through human doctors, and so on. (3) Companies such as Siemens, Google or IBM would like to buy annotated data to make better artificial neural networks that learn to predict pathologies and diseases and the consequences of therapies. Now the market’s invisible hand will decide about the data’s price through the interplay between demand and supply. On the demand side, you will have several companies offering something for the data, maybe through an app on the smartphone (a bit like a stock market app). On the supply side, each patient in this market should be able to profit from high prices for rare valuable types of data. Likewise, competing data extractors such as hospitals will profit from gaining recognition and trust for extracting data well at a reasonable price. The market will make the whole system efficient through incentives for all who are doing a good job. Soon there will be a flourishing ecosystem of commercial data market advisors and what not, just like the ecosystem surrounding the traditional stock market. The value of the data won’t be determined by governments or ethics committees, but by those who own the data and decide by themselves which parts thereof they want to license to others under certain conditions. At first glance, a market-based system seems to be detrimental to the interest of certain monopolistic companies, as they would have to pay for the data - some would prefer free data and keep their monopoly. However, since every healthy and sick person in the market would suddenly have an incentive to collect and share their data under self-chosen anonymity conditions, there will soon be many more useful data to evaluate all kinds of treatments. On average, people will live longer and healthier, and many companies and the entire healthcare system will benefit. Jones: Finally, what is your view on open source versus the private companies like Google and OpenAI? Is there a danger to supporting these private companies’ large language models versus trying to keep these models open source and transparent, very much like what LAION is doing? Schmidhuber: I signed this open letter by LAION because I strongly favor the open-source movement. And I think it's also something that is going to challenge whatever big tech dominance there might be at the moment. Sure, the best models today are run by big companies with huge budgets for computers, but the exciting fact is that open-source models are not so far behind, some people say maybe six to eight months only. Of course, the private company models are all based on stuff that was created in academia, often in little labs without so much funding, which publish without patenting their results and open source their code and others take it and improved it. Big tech has profited tremendously from academia; their main achievement being that they have scaled up everything greatly, sometimes even failing to credit the original inventors. So, it's very interesting to see that as soon as some big company comes up with a new scaled-up model, lots of students out there are competing, or collaborating, with each other, trying to come up with equal or better performance on smaller networks and smaller machines. And since they are open sourcing, the next guy can have another great idea to improve it, so now there’s tremendous competition also for the big companies. Because of that, and since AI is still getting exponentially cheaper all the time, I don't believe that big tech companies will dominate in the long run. They find it very hard to compete with the enormous open-source movement. As long as you can encourage the open-source community, I think you shouldn't worry too much. Now, of course, you might say if everything is open source, then the bad actors also will more easily have access to these AI tools. And there's truth to that. But as always since the invention of controlled fire, it was good that knowledge about how technology works quickly became public such that everybody could use it. And then, against any bad actor, there's almost immediately a counter actor trying to nullify his efforts. You see, I still believe in our old motto "AI∀" or "AI For All." Jones: Thank you, Juergen for sharing your perspective on this amazing time in history. It’s clear that with new technology, the enormous potential can be matched by disparate and troubling risks which we’ve yet to solve, and even those we have yet to identify. If we are to dispel the fear of a sentient system for which we have no control, humans, alone need to take steps for more responsible development and collaboration to ensure AI technology is used to ultimately benefit society. Humanity will be judged by what we do next.

[D] Should We Be Concerned About The Failure Of Evolutionary Algorithms, And Its Implications?

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6287292/ &#x200B; A number of possible explanations for \[why we can't evolve complex software\] could be considered. We tried to be as comprehensive as possible in this section, but it is possible that we have not considered some plausible explanations: Incompetent programmers—It is theoretically possible, but is highly unlikely, that out of thousands of scientists working on evolutionary computation, all failed to correctly implement the Darwinian algorithm. Nonrepresentative algorithms—Some have suggested that EAs do not accurately capture the theory of evolution, but of course that would imply that the theory itself is not specified in sufficient detail to make falsifiable predictions. If, however, such more detailed specifications are available to GP believers, it is up to them to implement them as computer simulations for testing purposes, but no successful examples of such work are known and the known ones have not been successful in evolving software. Inadequate fitness functions—Fitness function for a complex software product is difficult to outline and specify and may be as complex (or even more complex) as the software we want to evolve as it has to consider all the possible use cases and pass all unit tests. This may be the Achilles heel of GP, but it is also an objection to feasibility of programming in general and GP in particular, as both have to convert software specification into the source code. If human programmers and biological evolution succeed with such constraints, so should Darwinian simulations. The Halting problem—Turing proved that it is impossible to determine whether an arbitrary program halts, but this is also a problem for human programmers and could be easily addressed by placing time limits on considered solutions. Program correctness—If we require evolved software to be provably correct, this would present a problem as GP does not verify produced designs but only tests them against specific unit tests. Likewise, we cannot rely on automated software verification as it is still an unsolved problem in the general case. This is not really a problem as most of the human-written software is never proven to be correct and only a small portion of software engineering process relies of formal specification and Test Driven Development. Inappropriate solutions—Literature on EA is full of examples of surprising creativity of Darwinian algorithm resulting in solutions which match the letter of design specifications but not the spirit. This is similar to human-produced software and numerous examples of ways in which such software fails the goals of the initial design. Insufficient complexity of the environment (not enough data, poor fitness functions)—It is possible that the simulated environment is not complex enough to generate high complexity outputs in evolutionary simulations. This does not seem correct as Internet presents a highly complex landscape in which many self-modifying computer viruses roam. Likewise, virtual world such as Second Life and many others present close approximations to the real world and are certainly more complex than early Earth was: A skeptic might insist that an abstract environment would be inadequate for the evolution . . ., believing instead that the virtual environment would need to closely resemble the actual biological environment in which our ancestors evolved. Creating a physically realistic virtual world would require a far greater investment of computational resources than the simulation of a simple toy world or abstract problem domain (whereas evolution had access to a physically realistic real world “for free”). In the limiting case, if complete microphysical accuracy were insisted upon, the computational requirements would balloon to utterly infeasible proportions. Requiring more realistic environmental conditions may result in an increase in necessary computational resources, a problem addressed in the next bullet. Insufficient resources (compute, memory)—From the history of computer science, we know of many situations (speech recognition, NN training), where we had a correct algorithm but insufficient computational resources to run it to success. It is possible that we simply do not have hardware powerful enough to emulate evolution. We will address this possibility in section “Computational Complexity of Biological Evolution and Available Compute.” Software design is not amenable to evolutionary methods—Space of software designs may be discrete with no continuous path via incremental fitness to the desired solutions. This is possible, but this implies that original goals of GP are unattainable and misguided. In addition, because a clear mapping exists between solutions to problems and animals as solutions to environmental problems, this would also imply that current explanation for the origin of the species is incorrect. Darwinian algorithm is incomplete or wrong—Finally, we have to consider the possibility that the inspiration behind evolutionary computation, the Darwinian algorithm itself is wrong or at least partially incomplete. If that was true, computer simulations of such algorithm would fail to produce results comparable with observations we see in nature and a search for an alternative algorithm would need to take place. This would be an extraordinary claim and would require that we discard all the other possible explanations from this list. We challenge EA community to prove us wrong by producing an experiment, which evolves nontrivial software from scratch and without human help. That would be the only way in which our findings could be shown to be incorrect. Perhaps, reframing the problem in terms of maximizing negentropy of digital organisms, as suggested by Schrödinger, Michaelian, and Ulanowicz and Hannon, with respect to negative energy being a fundamental property of all life-forms may produce better results. On a positive side, the fact that it seems impossible to evolve complex software implies that we are unlikely to be able to evolve highly sophisticated artificially intelligent agents, which may present significant risk to our safety and security. Just imagine what would have happened, if the very first time we ran a simulation of evolution on a computer, it produced a superintelligent agent. Yampolskiy has shown that programming as a problem is AI-complete; if GP can solve programming that would imply that GP = AGI (artificial general intelligence), but we see no experimental evidence for such claim. In fact, it is more likely that once we have AGI, it could be used to create an intelligent fitness function for GP and so evolve software. Genetic programming will not be the cause of AI, but a product of it. However, neuroevolution methods for optimizing deep learning architectures and parameters remain a strong possibility for creation of AGI.

[R] From 3D Contour Plots to AI-Generated Art

Fun tutorial to learn how to make professional contour plots in Python, with incredible animated visualizations. At the intersection of machine learning, scientific computing, automated art, cartography, and video games. Section 3 is particularly interesting, as it shows all the work behind the scene, to complete this project in 20 hours when you have no idea how to start. https://reddit.com/link/ycg6c6/video/kycotrx09sv91/player There is far more than just creating 3D contour plots in this article. First, you will learn how to produce data videos. I have shared quite a few in the past (with source code), but this is probably the simplest example. The data video also illustrates that a mixture of Gaussian-like distributions is typically non Gaussian-like, and may or may not be unimodal. It is borderline art (automatically generated), and certainly a stepping stone for professionals interested in computer vision or designing video games. It is easy to image a game based on my video, entitled “flying above menacingly rising mountains”. Then the data video, through various rotations, give you a much better view of your data. It is also perfect to show systems that evolve over time: a time series where each observation is an image. In addition, unlike most tutorials found online, this one does a rather deep dive on a specific, rather advanced function from a library truly aimed at scientific computing. In the same way that images (say pictures of hand-written digits) can be summarized by 10 parameters to perform text recognition, here 20 parameters allow you to perform topography classification. Not just of static terrain, but terrain that changes over time, assuming you have access to 50,000 videos representing different topographies. You can produce the videos needed for supervised classification with the code in section 2. The next step is to use data (videos) from the real world, and used the model trained on synthetic data for classification. Read the full article with illustration (data video) and Python code, here.

[R] Stanford HAI Spring Conference - Intelligence Augmentation: AI Empowering People to Solve Global Challenges

Stanford Institute for Human-Centered AI hosted its spring conference today with interesting conversations about how AI can best support humans in healthcare, art, and education to address global challenges. More details and the event recording are available at the HAI conference site. Here is a quick outline with video sections: Welcome & Introductions: HAI directors Fei-Fei Li, John Etchemendy, Russ Altman, & James Landay Session I: Healthcare Immersive Technologies for Caregiving: Innovation Opportunities and Ecosystem Challenges, Deborah Estrin @ Cornell Tech Student Lightning Talks On Complementing and Extending Human Intellect: Principles and Directions, Eric Horvitz @ Microsoft Mobilizing AI to Achieve Healthy Child Development Worldwide, Dennis Wall @ Stanford Safer and Proactive Care through AI, Suchi Saria @ Johns Hopkins University Session II: Art Other Intelligence: Exoticism and AI, Ken Goldberg @ UC Berkeley Student Lightning Talks Artful Intelligence: Exoticism and AI, Michele Elam @ Stanford The Digital Griot: A Reimagining of the Archive, Rashaad Newsome @ Stanford Amplifying the Human Artist Through AI, Hilary Hahn & Carol Reiley @ DeepMusic.ai Session III: Education Escaping or Automating a Legacy of Bad Instruction, Daniel Schwartz @ Stanford Student Lightning Talks AI to Super Power Teachers, Chris Piech @ Stanford Pushing the Boundaries of Educational Technology, Amy Ogan @ Carnegie Mellon University AI to Accelerate Workplace Learning at Scale, Candace Thille @ Amazon https://preview.redd.it/p2qg7eutibp61.png?width=1928&format=png&auto=webp&s=1cc8dd6c4458c3da79d00415552ca4424f03d0c2

[N] Last Week in AI News Digest 08/15-08/21: detecting hate speech, dogfight simulation, disaster-response, and more!

Hi there, we at Skynet Today produce a weekly newsletter summarizing each week's major AI news, which seems like it'd be of interest to this subreddit. Here's what's in our latest one: Facebook’s AI for detecting hate speech is facing its biggest challenge yet Facebook has made significant progress recently to proactively take down content that violate its community standards. For example, in the second quarter of 2020, Facebook took down 104.6 million pieces of content. While reviews are typically performed by a vast workforce of human moderators, AI-powered tools have enabled Facebook to do this work at a greater scale for textual content. However, there’s a long way to go for these systems to match or exceed the capabilities of human moderators. This is because a large proportion of hate speech and misinformation is in the form of images and memes, and reasoning about the context and language-image interplay is an extremely difficult challenge for AI. Given Facebook’s scale and the speed at which some use it to spread hate, incite violence, and share lies with millions, Facebook will have to keep running to catch up. AI Slays Top F-16 Pilot In DARPA Dogfight Simulation The Defense Advanced Research Project Agency (DARPA) recently hosted a simulated F16 dogfight competition, with different AI bots competing with each other as well as with human pilots. The top AI bot was able to beat a human pilot 5-0 in the simulated contest. DARPA started this program “as a risk-reduction effort \[…\] to flesh out how human and machine pilots share operational control of a fighter jet to maximize its chances of mission success.” Competition runners are broadly optimistic about the demonstration of AI capabilities, even if they are not close to being deployed on a real aircraft. Of concern, the program had little discussion on the ethics of AI military applications, especially with the lethal autonomous weapon systems being considered. News Advances & Business Microsoft, Energy Dept. to Develop Disaster-Response AI Tools \- The U.S. Department of Energy and Microsoft Corp. on Tuesday announced a partnership to develop artificial-intelligence tools aimed at helping first-responders better react to fast-changing natural events, such as floods and wildfires. Coronavirus: Robot CERi is a bilingual Covid-19 expert \- Ceri is bilingual, clued-up on coronavirus and can tell what mood you are in. Ceri also happens to be a robot. Moscow DOH uses AI platform to detect lung cancer symptoms \- Moscow’s department of health is using an artificial intelligence (AI) platform to detect symptoms of lung cancer in CT scans, as part of a project to implement AI technology for radiology. Scientists develop artificial intelligence system for high precision recognition of hand gestures \- The recognition of human hand gestures by AI systems has been a valuable development over the last decade and has been adopted in high-precision surgical robots, health monitoring equipment and in gaming systems. Forget credit cards - now you can pay with your face. Creepy or cool? \- A new way to pay has arrived in Los Angeles: your face. Concerns & Hype The dystopian tech that companies are selling to help schools reopen sooner \- This fall, AI could be watching students social distance and checking their masks. Thousands of schools nationwide will not be reopening this fall. NYPD Used Facial Recognition Technology In Siege Of Black Lives Matter Activist’s Apartment \- The NYPD deployed facial recognition technology in its hunt for a prominent Black Lives Matter activist, whose home was besieged by dozens of officers and police dogs last week, a spokesperson confirmed to Gothamist. Machines can spot mental health issues - if you hand over your personal data \- Digital diagnosis could transform psychiatry by mining your most intimate data for clues. But is the privacy cost worth it? Supporting Black Artists Who Are Examining AI \- Technology has a complicated relationship with racial justice. Smartphones, internet platforms, and other digital tools can be used to document and expose racism. But digital tools can also fuel racism: smart doorbells surveil Black individuals. A-level and GCSE results in England to be based on teacher assessments in U-turn \- All A-level and GCSE results in England will be based on grades assesed by teachers instead of algorithms. Analysis & Policy GPT-3 and The Question of Automation \- Automation is not an all or nothing proposition. An AI model’s automation capability is highly conjoined with the task and application it is used in. An A.I. Movie Service Could One Day Serve You a New Custom Film Every Time \- How long will it be until an A.I. can make an actual feature film on demand? Fairness, evidence, and predictive equality \- How the causal fairness principle relates to predictive equality How robotics and automation could create new jobs in the new normal \- Depending on who you ask, AI and automation will either destroy jobs or create new ones. In reality, a greater push toward automation will probably both kill and create jobs - human workers will become redundant in certain spheres, sure, but many new roles will likely crop up. Expert Opinions & Discussion within the field Too many AI researchers think real-world problems are not relevant \- The community’s hyperfocus on novel methods ignores what’s really important.

[P]MMML | Deploy HuggingFace training model rapidly based on MetaSpore

A few days ago, HuggingFace announced a $100 million Series C funding round, which was big news in open source machine learning and could be a sign of where the industry is headed. Two days before the HuggingFace funding announcement, open-source machine learning platform MetaSpore released a demo based on the HuggingFace Rapid deployment pre-training model. As deep learning technology makes innovative breakthroughs in computer vision, natural language processing, speech understanding, and other fields, more and more unstructured data are perceived, understood, and processed by machines. These advances are mainly due to the powerful learning ability of deep learning. Through pre-training of deep models on massive data, the models can capture the internal data patterns, thus helping many downstream tasks. With the industry and academia investing more and more energy in the research of pre-training technology, the distribution warehouses of pre-training models such as HuggingFace and Timm have emerged one after another. The open-source community release pre-training significant model dividends at an unprecedented speed. In recent years, the data form of machine modeling and understanding has gradually evolved from single-mode to multi-mode, and the semantic gap between different modes is being eliminated, making it possible to retrieve data across modes. Take CLIP, OpenAI’s open-source work, as an example, to pre-train the twin towers of images and texts on a dataset of 400 million pictures and texts and connect the semantics between pictures and texts. Many researchers in the academic world have been solving multimodal problems such as image generation and retrieval based on this technology. Although the frontier technology through the semantic gap between modal data, there is still a heavy and complicated model tuning, offline data processing, high performance online reasoning architecture design, heterogeneous computing, and online algorithm be born multiple processes and challenges, hindering the frontier multimodal retrieval technologies fall to the ground and pratt &whitney. DMetaSoul aims at the above technical pain points, abstracting and uniting many links such as model training optimization, online reasoning, and algorithm experiment, forming a set of solutions that can quickly apply offline pre-training model to online. This paper will introduce how to use the HuggingFace community pre-training model to conduct online reasoning and algorithm experiments based on MetaSpore technology ecology so that the benefits of the pre-training model can be fully released to the specific business or industry and small and medium-sized enterprises. And we will give the text search text and text search graph two multimodal retrieval demonstration examples for your reference. Multimodal semantic retrieval The sample architecture of multimodal retrieval is as follows: Our multimodal retrieval system supports both text search and text search application scenarios, including offline processing, model reasoning, online services, and other core modules: &#x200B; https://preview.redd.it/w4v4c7vcez291.png?width=1834&format=png&auto=webp&s=0687efb1fddb26e8e30cb844d398ec712b947f31 Offline processing, including offline data processing processes for different application scenarios of text search and text search, including model tuning, model export, data index database construction, data push, etc. Model inference. After the offline model training, we deployed our NLP and CV large models based on the MetaSpore Serving framework. MetaSpore Serving helps us conveniently perform online inference, elastic scheduling, load balancing, and resource scheduling in heterogeneous environments. Online services. Based on MetaSpore’s online algorithm application framework, MetaSpore has a complete set of reusable online search services, including Front-end retrieval UI, multimodal data preprocessing, vector recall and sorting algorithm, AB experimental framework, etc. MetaSpore also supports text search by text and image scene search by text and can be migrated to other application scenarios at a low cost. The HuggingFace open source community has provided several excellent baseline models for similar multimodal retrieval problems, which are often the starting point for actual optimization in the industry. MetaSpore also uses the pre-training model of the HuggingFace community in its online services of searching words by words and images by words. Searching words by words is based on the semantic similarity model of the question and answer field optimized by MetaSpore, and searching images by words is based on the community pre-training model. These community open source pre-training models are exported to the general ONNX format and loaded into MetaSpore Serving for online reasoning. The following sections will provide a detailed description of the model export and online retrieval algorithm services. The reasoning part of the model is standardized SAAS services with low coupling with the business. Interested readers can refer to my previous post: The design concept of MetaSpore, a new generation of the one-stop machine learning platform. 1.1 Offline Processing Offline processing mainly involves the export and loading of online models and index building and pushing of the document library. You can follow the step-by-step instructions below to complete the offline processing of text search and image search and see how the offline pre-training model achieves reasoning at MetaSpore. 1.1.1 Search text by text Traditional text retrieval systems are based on literal matching algorithms such as BM25. Due to users’ diverse query words, a semantic gap between query words and documents is often encountered. For example, users misspell “iPhone” as “Phone,” and search terms are incredibly long, such as “1 \~ 3 months old baby autumn small size bag pants”. Traditional text retrieval systems will use spelling correction, synonym expansion, search terms rewriting, and other means to alleviate the semantic gap but fundamentally fail to solve this problem. Only when the retrieval system fully understands users’ query terms and documents can it meet users’ retrieval demands at the semantic level. With the continuous progress of pre-training and representational learning technology, some commercial search engines continue to integrate semantic vector retrieval methods based on symbolic learning into the retrieval ecology. Semantic retrieval model This paper introduces a set of semantic vector retrieval applications. MetaSpore built a set of semantic retrieval systems based on encyclopedia question and answer data. MetaSpore adopted the Sentence-Bert model as the semantic vector representation model, which fine-tunes the twin tower BERT in supervised or unsupervised ways to make the model more suitable for retrieval tasks. The model structure is as follows: The query-Doc symmetric two-tower model is used in text search and question and answer retrieval. The vector representation of online Query and offline DOC share the same vector representation model, so it is necessary to ensure the consistency of the offline DOC library building model and online Query inference model. The case uses MetaSpore’s text representation model Sbert-Chinese-QMC-domain-V1, optimized in the open-source semantically similar data set. This model will express the question and answer data as a vector in offline database construction. The user query will be expressed as a vector by this model in online retrieval, ensuring that query-doc in the same semantic space, users’ semantic retrieval demands can be guaranteed by vector similarity metric calculation. Since the text presentation model does vector encoding for Query online, we need to export the model for use by the online service. Go to the q&A data library code directory and export the model concerning the documentation. In the script, Pytorch Tracing is used to export the model. The models are exported to the “./export “directory. The exported models are mainly ONNX models used for wired reasoning, Tokenizer, and related configuration files. The exported models are loaded into MetaSpore Serving by the online Serving system described below for model reasoning. Since the exported model will be copied to the cloud storage, you need to configure related variables in env.sh. \Build library based on text search \ The retrieval database is built on the million-level encyclopedia question and answer data set. According to the description document, you need to download the data and complete the database construction. The question and answer data will be coded as a vector by the offline model, and then the database construction data will be pushed to the service component. The whole process of database construction is described as follows: Preprocessing, converting the original data into a more general JSonline format for database construction; Build index, use the same model as online “sbert-Chinese-qmc-domain-v1” to index documents (one document object per line); Push inverted (vector) and forward (document field) data to each component server. The following is an example of the database data format. After offline database construction is completed, various data are pushed to corresponding service components, such as Milvus storing vector representation of documents and MongoDB storing summary information of documents. Online retrieval algorithm services will use these service components to obtain relevant data. 1.1.2 Search by text Text and images are easy for humans to relate semantically but difficult for machines. First of all, from the perspective of data form, the text is the discrete ID type of one-dimensional data based on words and words. At the same time, images are continuous two-dimensional or three-dimensional data. Secondly, the text is a subjective creation of human beings, and its expressive ability is vibrant, including various turning points, metaphors, and other expressions, while images are machine representations of the objective world. In short, bridging the semantic gap between text and image data is much more complex than searching text by text. The traditional text search image retrieval technology generally relies on the external text description data of the image or the nearest neighbor retrieval technology and carries out the retrieval through the image associated text, which in essence degrades the problem to text search. However, it will also face many issues, such as obtaining the associated text of pictures and whether the accuracy of text search by text is high enough. The depth model has gradually evolved from single-mode to multi-mode in recent years. Taking the open-source project of OpenAI, CLIP, as an example, train the model through the massive image and text data of the Internet and map the text and image data into the same semantic space, making it possible to implement the text and image search technology based on semantic vector. CLIP graphic model The text search pictures introduced in this paper are implemented based on semantic vector retrieval, and the CLIP pre-training model is used as the two-tower retrieval architecture. Because the CLIP model has trained the semantic alignment of the twin towers’ text and image side models on the massive graphic and text data, it is particularly suitable for the text search graph scene. Due to the different image and text data forms, the Query-Doc asymmetric twin towers model is used for text search image retrieval. The image-side model of the twin towers is used for offline database construction, and the text-side model is used for the online return. In the final online retrieval, the database data of the image side model will be searched after the text side model encodes Query, and the CLIP pre-training model guarantees the semantic correlation between images and texts. The model can draw the graphic pairs closer in vector space by pre-training on a large amount of visual data. Here we need to export the text-side model for online MetaSpore Serving inference. Since the retrieval scene is based on Chinese, the CLIP model supporting Chinese understanding is selected. The exported content includes the ONNX model used for online reasoning and Tokenizer, similar to the text search. MetaSpore Serving can load model reasoning through the exported content. Build library on Image search You need to download the Unsplash Lite library data and complete the construction according to the instructions. The whole process of database construction is described as follows: Preprocessing, specify the image directory, and then generate a more general JSOnline file for library construction; Build index, use OpenAI/Clip-Vit-BASE-Patch32 pre-training model to index the gallery, and output one document object for each line of index data; Push inverted (vector) and forward (document field) data to each component server. Like text search, after offline database construction, relevant data will be pushed to service components, called by online retrieval algorithm services to obtain relevant data. 1.2 Online Services The overall online service architecture diagram is as follows: https://preview.redd.it/jfsl8hdfez291.png?width=1280&format=png&auto=webp&s=a858e2304a0c93e78ba5429612ca08cbee69b35a Multi-mode search online service system supports application scenarios such as text search and text search. The whole online service consists of the following parts: Query preprocessing service: encapsulate preprocessing logic (including text/image, etc.) of pre-training model, and provide services through gRPC interface; Retrieval algorithm service: the whole algorithm processing link includes AB experiment tangent flow configuration, MetaSpore Serving call, vector recall, sorting, document summary, etc.; User entry service: provides a Web UI interface for users to debug and track down problems in the retrieval service. From a user request perspective, these services form invocation dependencies from back to front, so to build up a multimodal sample, you need to run each service from front to back first. Before doing this, remember to export the offline model, put it online and build the library first. This article will introduce the various parts of the online service system and make the whole service system step by step according to the following guidance. See the ReadME at the end of this article for more details. 1.2.1 Query preprocessing service Deep learning models tend to be based on tensors, but NLP/CV models often have a preprocessing part that translates raw text and images into tensors that deep learning models can accept. For example, NLP class models often have a pre-tokenizer to transform text data of string type into discrete tensor data. CV class models also have similar processing logic to complete the cropping, scaling, transformation, and other processing of input images through preprocessing. On the one hand, considering that this part of preprocessing logic is decoupled from tensor reasoning of the depth model, on the other hand, the reason of the depth model has an independent technical system based on ONNX, so MetaSpore disassembled this part of preprocessing logic. NLP pretreatment Tokenizer has been integrated into the Query pretreatment service. MetaSpore dismantlement with a relatively general convention. Users only need to provide preprocessing logic files to realize the loading and prediction interface and export the necessary data and configuration files loaded into the preprocessing service. Subsequent CV preprocessing logic will also be integrated in this manner. The preprocessing service currently provides the gRPC interface invocation externally and is dependent on the Query preprocessing (QP) module in the retrieval algorithm service. After the user request reaches the retrieval algorithm service, it will be forwarded to the service to complete the data preprocessing and continue the subsequent processing. The ReadMe provides details on how the preprocessing service is started, how the preprocessing model exported offline to cloud storage enters the service, and how to debug the service. To further improve the efficiency and stability of model reasoning, MetaSpore Serving implements a Python preprocessing submodule. So MetaSpore can provide gRPC services through user-specified preprocessor.py, complete Tokenizer or CV-related preprocessing in NLP, and translate requests into a Tensor that deep models can handle. Finally, the model inference is carried out by MetaSpore, Serving subsequent sub-modules. Presented here on the lot code: https://github.com/meta-soul/MetaSpore/compare/add\python\preprocessor 1.2.2 Retrieval algorithm services Retrieval algorithm service is the core of the whole online service system, which is responsible for the triage of experiments, the assembly of algorithm chains such as preprocessing, recall, sorting, and the invocation of dependent component services. The whole retrieval algorithm service is developed based on the Java Spring framework and supports multi-mode retrieval scenarios of text search and text search graph. Due to good internal abstraction and modular design, it has high flexibility and can be migrated to similar application scenarios at a low cost. Here’s a quick guide to configuring the environment to set up the retrieval algorithm service. See ReadME for more details: Install dependent components. Use Maven to install the online-Serving component Search for service configurations. Copy the template configuration file and replace the MongoDB, Milvus, and other configurations based on the development/production environment. Install and configure Consul. Consul allows you to synchronize the search service configuration in real-time, including cutting the flow of experiments, recall parameters, and sorting parameters. The project’s configuration file shows the current configuration parameters of text search and text search. The parameter modelName in the stage of pretreatment and recall is the corresponding model exported in offline processing. Start the service. Once the above configuration is complete, the retrieval service can be started from the entry script. Once the service is started, you can test it! For example, for a user with userId=10 who wants to query “How to renew ID card,” access the text search service. 1.2.3 User Entry Service Considering that the retrieval algorithm service is in the form of the API interface, it is difficult to locate and trace the problem, especially for the text search image scene can intuitively display the retrieval results to facilitate the iterative optimization of the retrieval algorithm. This paper provides a lightweight Web UI interface for text search and image search, a search input box, and results in a display page for users. Developed by Flask, the service can be easily integrated with other retrieval applications. The service calls the retrieval algorithm service and displays the returned results on the page. It’s also easy to install and start the service. Once you’re done, go to http://127.0.0.1:8090 to see if the search UI service is working correctly. See the ReadME at the end of this article for details. Multimodal system demonstration The multimodal retrieval service can be started when offline processing and online service environment configuration have been completed following the above instructions. Examples of textual searches are shown below. Enter the entry of the text search map application, enter “cat” first, and you can see that the first three digits of the returned result are cats: https://preview.redd.it/0n5nuyvhez291.png?width=1280&format=png&auto=webp&s=1e9c054f541d53381674b8d6001b4bf524506bd2 If you add a color constraint to “cat” to retrieve “black cat,” you can see that it does return a black cat: https://preview.redd.it/rzc0qjyjez291.png?width=1280&format=png&auto=webp&s=d5bcc503ef0fb3360c7740e60e295cf372dcad47 Further, strengthen the constraint on the search term, change it to “black cat on the bed,” and return results containing pictures of a black cat climbing on the bed: &#x200B; https://preview.redd.it/c4b2q8olez291.png?width=1280&format=png&auto=webp&s=4f3817b0b9f07e1e68d1d4a8281702ba3834a00a The cat can still be found through the text search system after the color and scene modification in the above example. Conclusion The cutting-edge pre-training technology can bridge the semantic gap between different modes, and the HuggingFace community can greatly reduce the cost for developers to use the pre-training model. Combined with the technological ecology of MetaSpore online reasoning and online microservices provided by DMetaSpore, the pre-training model is no longer mere offline dabbling. Instead, it can truly achieve end-to-end implementation from cutting-edge technology to industrial scenarios, fully releasing the dividends of the pre-training large model. In the future, DMetaSoul will continue to improve and optimize the MetaSpore technology ecosystem: More automated and wider access to HuggingFace community ecology. MetaSpore will soon release a common model rollout mechanism to make HuggingFace ecologically accessible and will later integrate preprocessing services into online services. Multi-mode retrieval offline algorithm optimization. For multimodal retrieval scenarios, MetaSpore will continuously iteratively optimize offline algorithm components, including text recall/sort model, graphic recall/sort model, etc., to improve the accuracy and efficiency of the retrieval algorithm. For related code and reference documentation in this article, please visit: https://github.com/meta-soul/MetaSpore/tree/main/demo/multimodal/online Some images source: https://github.com/openai/CLIP/raw/main/CLIP.png https://www.sbert.net/examples/training/sts/README.html