Best Way to Learn About AI | VibeBuilders.ai Resource Directory

#coursera #cloud #technical

Not specified•This week

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!

How do you learn details / potential strategy about technically important new laws in the jurisdictions you operate in?

friendofherschel•This week

How do you learn details / potential strategy about technically important new laws in the jurisdictions you operate in?

I am reading “The Entrepreneur’s Guide to Law and Strategy” and it’s really fantastic so far about giving a pretty great overview of these aspects of business. It was published by Wiley (a reputable textbook publisher) in 2018. In one chapter, the authors go into the EU’s “right to be forgotten” and it got me thinking about complying with laws like that. Unfortunately, the latest edition of the book is still nearly 7 years old and written pre-COVID, pre-genAI, pre-social network and privacy pushback, etc. I assume every time a new law comes out that can impact my business (say, a random privacy law in California) that businesses aren’t just telling their lawyers “use any amount of hours you need to in order to read the San Jose papers every day and then write me a one paragraph brief with an outline and potential changes needed to our business, also all the other papers across the world”. They’d spend a fortune. There has to be something I’m missing. Is there a law review for business that I should be following? I operate in the US only at this time. A more technical newspaper (I take WSJ, but it’s not technical enough for this sort of thing. It might give the “what”, but won’t give a small business owner “what to do with it”)? PS: I’m the type of person who read every word of my mortgage. I am aware the answer might be “don’t worry about it”. But I do worry about it, and am trying to fix that. For example, the insanely popular new lawsuits about website accessibility. I want to avoid things (essentially low hanging lawsuit fruit) like that before they happen to me.

#reddit #learn #details

[N] Ethan Caballero: Broken Neural Scaling Laws | New Podcast Episode

#reddit #ethan #caballero:

evc123•This week

[N] Ethan Caballero: Broken Neural Scaling Laws | New Podcast Episode

video: https://www.youtube.com/watch?v=SV87S38M1J4 OUTLINE: 00:00 Introduction 00:50 The "Scale Is All You Need" Movement 01:07 A Functional Form Predicting Every Scaling Behavior 01:40 A Break Between Two Straight Lines On A Log Log Plot 02:32 The Broken Neural Scaling Laws Equation 04:04 Extrapolating A Ton Of Large Scale Vision And Language Tasks 04:49 Upstream And Downstream Have Different Breaks 05:22 Extrapolating Four Digit Addition Performance 06:11 On The Feasability Of Running Enough Training Runs 06:31 Predicting Sharp Left Turns 07:51 Modeling Double Descent 08:41 Forecasting Interpretability And Controllability 09:33 How Deception Might Happen In Practice 10:24 Sinister Stumbles And Treacherous Turns 11:18 Recursive Self Improvement Precedes Sinister Stumbles 11:51 Humans In The Loop For The Very First Deception 12:32 The Hardware Stuff Is Going To Come After The Software Stuff 12:57 Distributing Your Training By Copy-Pasting Yourself Into Different Servers 13:42 Automating The Entire Hardware Pipeline 14:47 Having Text AGI Spit Out New Robotics Design 16:33 The Case For Existential Risk From AI 18:32 Git Re-basin 18:54 Is Chain-Of-Thoughts Enough For Complex Reasoning In LMs? 19:52 Why Diffusion Models Outperform Other Generative Models 21:13 Using Whisper To Train GPT4 22:33 Text To Video Was Only Slightly Impressive 23:29 The e=mc\^2 of AGI transcript: https://theinsideview.ai/ethan2

Manus, vibe coding, scaling laws and Perplexity’s AI phone

youtube

0.434

0.49

IBM Technology•Mar 14, 2025

Manus, vibe coding, scaling laws and Perplexity’s AI phone

Learn more about artificial intelligence → https://ibm.biz/BdGULB Is Manus a second DeepSeek moment? In episode 46 of Mixture of Experts, host Tim Hwang is joined by Chris Hay, Kaoutar El Maghraoui and Vyoma Gajjar to talk Manus! Next, the rise of vibe coding—what started as a joke has now become a thing? Then, we dive deep into the future of scaling laws. Finally, Perplexity is teaming up with Deutsche Telekom to release an AI phone—what’s the motivation here? Tune-in to today’s Mixture of Experts to find out more! 00:00 – Intro 00:37 -- Manus 14:09 – Vibe coding 30:13 – Scaling laws 39:07 – Perplexity's AI phone The opinions expressed in this podcast are solely those of the participants and do not necessarily reflect the views of IBM or any other organization or entity. Subscribe for AI updates → https://ibm.biz/BdGUuW Visit Mixture of Experts podcast page to learn more AI content → https://ibm.biz/BdGUu7

Fundamentals of Machine Learning and Artificial Intelligence

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.

#coursera #fundamentals #machine

AlmostARockstar•This week

0.5

Zero To One [Book Review]

If you don't feel like reading - check out the video here ##Introduction The more I read into Peter Thiel's background, the more ridiculous it seems.. He’s been involved in controversies over: Racism, Sexism, and, [Radical Right wing libertarianism.] (https://www.bloomberg.com/news/articles/2016-07-21/the-strange-politics-of-peter-thiel-trump-s-most-unlikely-supporter) He’s built a tech company that helps the NSA spy on the world. He supported Donald Trumps presidential campaign. He’s funding research on immortality And to top it off, he helped bankrupt online media company and blog network Gawker by funding Hulk Hogan’s sex tape lawsuit - after a report of his rumoured Homosexuality rattled his chain… Zero to One clearly reflects his unique attitude and doesn't pull any punches with a genuinely interesting point of view, that has clearly worked in the past, to the tune of almost 3 billion USD. But at times, his infatuation with the All American attitude is a little much…and, quite frankly, he’s not the kind of guy I could sit and have a pint with…without grinding my teeth anyway. The content is adapted from Blake Masters' lecture notes from Thiel's 2012 Stanford Course. This definitely helped keep the book concise and fast paced, at least compared to other books I’ve reviewed. The type of content is also quite varied, with a good spread from completely abstract theories — like the Technology vs. Globalisation concept, where the book get's it's title — to practical examples such as the analysis of personalities in chapter 14, "The Founders Paradox" covering Elvis Presley, Sean Parker, Lady Gaga and Bill Gates to name a few. ###Pros Monopolies To most people a monopoly is a negative thing. But while perfect competition can drive down costs and benefit the consumer - competition is bad for business. In fact, in Thiel's opinion, every startup should aim to be a monopoly or, as he puts it: Monopoly is the condition of every successful business. I like his honesty about it. While I’m not sure about the morality of encouraging monopolies at a large scale, I can see the benefit of thinking that way when developing a startup. When you're small, you can’t afford to compete. The best way to avoid competition is to build something nobody can compete with. The concept is summed up nicely at the end of chapter 3: Tolstoy opens Anna Karenina by observing: ‘All happy families are alike; each unhappy family is unhappy in its own way.’ Business is the opposite. All happy companies are different: each one earns a monopoly by solving a unique problem. All failed companies are the same: they failed to escape competition. Pareto The Pareto Law, which you might remember as the 80/20 rule in Tim Ferris’ The Four Hour Work Week, is often used synonymously with the power law of distribution, and shows up everywhere. Thiel refers to it in his section on The Power Law of Venture Capital. If Tim Ferris recommends identifying and removing the 20% of things that take 80% of your effort - Thiel recommends finding the 20% of investments that make 80% of your return. Anything else is a waste. Soberingly, he also suggests that the Pareto Law means: ...you should not necessarily start your own company, even if you are extraordinarily talented. But to me this seems more like a venture capitalists problem, than an entrepreneurs problem - Personally, I believe there’s far more benefit in starting up your own company that purely profit. ###Cons Man and machine? Content-wise, there is very little to dislike in this book. As long as you accept that the book is written specifically for startups - where anything short of exponential growth is considered a failure - it’s exceptionally on point. However, there are a couple sections dotted throughout the book where opinion and wild speculation began to creep in. Chapter 12 is a good example of this entitled: Man and Machine. It’s a short chapter, 12 pages in total, and Thiel essentially preaches and speculates about the impact of better technology and strong AI. I like to dog ear pages with interesting or useful content so I can come back later, but this entire chapter remains untouched. America, fuck yeah! It would be really difficult for a personality as pungent as Theil's to go entirely unnoticed in a book like this, and indeed it breaks through every now and then. I only had a feint idea of Thiel's personality before I read the book, but having read up on his background, I’m actually surprised the book achieves such a neutral, if pragmatic, tone. Pretty early on in the book however, we are introduced to Thiel's concept of Economic Optimism and quite frankly the whole of chapter 6 should have been printed on star spangled, red white and blue pages. I’m not necessarily against the egotistic American spirit but when Thiel writes, in relation to European Pessimism: the US treasury prints ‘in god we trust’ on the dollar; the ECB might as well print ‘kick the can down the road’ on the euro I can smell the bacon double cheese burgers, with those tiny little American flags from here. Ooh Rah! ###TL;DR (a.k.a: Conclusion) Overall, however, I really did enjoy this book and I can see myself coming back to it. Peter Thiel IS controversial, but he has also been undeniably successful with a career punctuated by bold business decisions. The ideas in the book reflect this mind set well. Yes, he backed Trump, be he also (sadly) backed the winner.

#reddit #zero #[book

80+ Social Media Updates Related to Business Marketing That Occurred in last 5 months

0.333

lazymentors•This week

80+ Social Media Updates Related to Business Marketing That Occurred in last 5 months

Tiktok expanded its caption limits from 100 to 500 Characters. Reddit Updates Search tools, Now you can search User Comments. “Comment search is here”. Pinterest Announces New Partnership with WooCommerce to Expand Product Listings. Google’s launched ‘multisearch’ feature that lets you search using text and image at the same time. Etsy sellers went on strike after platform increases transaction fees. Reddit launched $1 million fund to support various projects going on platform. Instagram is updating its ranking algorithm to put more focus on Original Content LinkedIn Added New tools In creator mode: improved content analytics and Updates profile video Options. Tiktok launched its own gif library “Effect House”. Instagram Updates Reels editing tools adding reordering clips feature. Google Search got a new label to direct people to original news sources YouTube launches new Profile Rings for Stories and Live. Snapchat launched YouTube Link stickers to make video sharing easier! Messenger adds new shortcuts, including a slack like @everyone feature. Pinterest Expands it’s Creator funds program to help more Underrepresented creators. Reddit brings back r/place after 5 years. Google Adds New Seller Performance Badges, New Pricing Insights for eCommerce Brands. Meta and Google agrees to New Data Transfer agreement to keep Instagram and Facebook running in EU. Twitter tests New Interactive Ad types to boost its promotional Appeal. Instagram removed In-stream Ads from its Advertising Options. Tiktok launched new program “CAP” to help creative agencies reach its audience. Twitch shuts down its desktop app. Meta launched the ability to add “share to Reels” feature to third Party Apps. TikTok Adds New ‘Background Player’ Option for Live-Streams. Twitter rolls out ALT badge and improved image description. Fast, A Checkout Startup with $15 billion valuation shuts down after spending all the funds raised in 2021. Wordpress announced new pricing with more traffic and storage limits after receiving backlash from the community. Sales force upgrades marketing field services and sales tools with AI. Dropbox shop launches in open beta to allow creators to sell digital content. Tiktok is the most downloaded app in Quarter 1 of 2022. WhatsApp announced launch of ‘Communities’ - more structured group chats with admin controls. Tiktok expands testing a private dislike button for comments. Twitter acquired “Openback” A notification app to improve timeline and relevance of push notifications YouTube and Tiktok added New options for Automated Captions, Improving Accessibility. A new social media App “Be Real” is trending across the internet grabbing Gen-Zs attention to try the app. WhatsApp got permission to expand payment services to its Indian user base of 100 Million. YouTube Shorts now allows creators to splice in long-form videos. You can use long form video audios and clips for YT shorts. New Snapchat feature ‘Dynamic Stories’ uses a publisher’s RSS feed to automatically create Stories posts. Zoom launches AI-powered features aimed at sales teams. Tiktok started testing who viewed your profile feature. Ogilvy Announced they will no longer work with who edit their bodies and faces for ads. If you don’t know “Oglivy” is the most successful advertising agency of the decade. YouTube Launches New ‘Search Insights’ for all creators. Snapchat Added 13 million new users in Q1 2022 more than both Twitter and Facebook. Google is Introduced new options to reject tracking cookies in Europe after receiving fines from violating EU data laws. Sony & Microsoft are planning to integrate Ads into their gaming platforms Xbox and PlayStation. YouTube Adds new Shorts Shelf to Trending Tab to show Top Shorts in an alternative section. Instagram started testing a reels template feature which enables creators to copy formats from other reels. Google Tests “What People Are Saying” Search Results. Twitter Launches New Test of Promotions for Third Party Tools Within the App. Instagram is changing how hashtags work by experimenting removing Recents tab from hashtags section. Google Adds New Publisher Verification Badges to Extension Listings in the Google Web Store Amazon AWS launches $30M accelerator program aimed at minority founders. Meta launched more fundraising options for Instagram Reels in 30 countries. Brave Search and DuckDuckGo will no longer support Google AMP due to privacy issues. Instagram is working on a pinned post feature and will officially launch in next few months. Meta: You can now add Music to your Facebook comments Twitter tests new closed caption button to switch on captions in Video Clip Elon Musk Bought Twitter $44 Billion and Company is set to go private. Google now lets you request the removal of personal contact information from search results YouTube reveals that Ads between YT Shorts are being tested with selective brands. LinkedInis rolling out a new website link feature. Google Reduces Visibility Of Business Edits With Color Changes To Profile Updates. Instagram expands testing of 90 second Reels. Microsoft Advertising now offers incentive features like cash-back and adding stock images from your website. Facebook & Pinterest are growing again despite all the hype around slow growth of both platform in last quarter. Google Added 9 new Ad policies to prevent misleading ads taking place. Tiktok Introduces Third-party cookies to its Pixel. (like Facebook Pixel) Twitter reportedly overcounted number of daily active users for last 3 years. Google launched Media CDN to compete on content delivery. YouTube expands Thank You Monetisation tool to all eligible creators. Twitch is looking to expand their cut from streamers earnings from 30 to 50% and also thinks of boosting Ads. Snapchat launches a $230 flying drone camera and new e-commerce integrations in Snap Summit 2022. YouTube Expands its ‘Pre-Publish Checks’ Tool to the Mobile App Google Search Console’s URL parameter tool is officially removed for a time period. Twitter creators can now get paid through Cryptocurrency on Twitter with Stripe. Jellysmack- One of the Influencer marketing agency acquires YouTube analytics tool Google & Microsoft Ads brought more revenue in last quarter- 22% Gains! WhatsApp is working on a paid subscription for multi-phone and tablet chatting. Instagram users now spend 20% of their time in the reels section. Google tests new Color for clicked search results by you. Now Clicked results are in Purple. Twitter: Elon plans to remove employees and focus more on influencers for twitter’s growth + new monetisation ideas were shared. YouTube revenue falls as more users spend time on shorts tab than consuming long form content. Drop 👋 to receive June Updates!

#reddit #social #media

#reddit #started #learning

TechPrimo•This week

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.

#reddit #started #learning

TechPrimo•This week

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.

Teaching an AI to Play Mario: A Learning Journey

CivilLifeguard189•This week

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! 🚀🕹️🎮

#reddit #teaching #play

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

Brilliant_Fishing110•This week

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

#reddit #randomly #asked

Brilliant_Fishing110•This week

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

#reddit #randomly #asked

chipmux•This week

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? 🚀

#reddit #backend #wants

Automating Tax Expertise with Custom GPT – Need Advice

Gloomy-Wave1418•This week

Automating Tax Expertise with Custom GPT – Need Advice

Hey everyone, I'm an accountant, and I want to build a custom GPT that specializes in tax laws. The idea is to upload all relevant tax laws, regulations, and books (in PDF format) so that when I ask a tax-related question, the AI can not only provide an answer but also cite the exact legal reference. I want to automate this process so that whenever tax laws are updated, the AI stays current. Has anyone here worked on something similar? What’s the best way to structure and automate data ingestion for a knowledge-based AI like this? Any tools or workflows you'd recommend for making the AI more accurate and reliable in referencing legal texts? Looking forward to your insights!

#reddit #automating #expertise

Compare trading strategies on the fly - pnl.ai - please check it out

#reddit #compare #trading

0.6

varturas•This week

Compare trading strategies on the fly - pnl.ai - please check it out

Part of my covid project and part of my long obsession with prediction markets, I have created a web page that displays and allows to compare best and worst performing trading strategies. TL;DR: best stocks + best strategies -> the list of top and bottom performing trading algorithms. Product Typically, trading newsletters and stock-scanners display only price return for top market gainers and losers. I have forever been interested in inspecting top and bottom performing trading strategies for a given set of securities and could not find any websites that do that. So, I decided to create a tool of my own. I wanted the tool that would help me to answer questions like if there is a better strategy than buy and hold, should I follow greed and fear indicator of the market or do the opposite. Top and bottom performing securities do not tell you if a stock is going to go up or down, but they do alert you to rapidly changing market conditions, such as change in the competitive landscape, impending lawsuits, changes in the company's management and, at the very least, the stocks you should avoid in your programmatic trading. Top strategies do all that, but they can also alert you to a change in the market regime. For example, MACD strategy, which is a variant of oscillator strategy, executed on Citibank stock returned 20% in the first half of 2020. In the same time period, the Citibank stock went down and "BuyAndHold" strategy, which is pretty much what it sounds, lost 45%. Now, compare that to the end of 2020 through spring of 2021, when MACD lost 1% and "BuyAndHold" gained 70%. This happened due to the change in the market due to the rally in financial stocks at the end of 2020. The market player who detect change in the market conditions first will reap most benefits. Another example, TSLA since the beginning of 2021 until end of April lost 7%. The StopLoss strategy sells the position after abrupt price drop and waits until the price returns to the level before the drop. For the same time interval the StopLoss strategy gained 10%. In this particular example, StopLoss outperformed BuyAndHold. To me personally, the most important feature is the ability to quickly tweak and modify trading strategies and observe change in their performance. You can change strategies parameters on the fly and even design your own custom trading strategy. In the end, I developed a tool I can use for myself but hope other investors who are experimenting with trading algorithms will find it useful as well. I called it "Profit and Loss AI", or PnL.ai for short. PnL.ai Description The web-tool in the link below allows you to customize parameters of existing strategies and essentially create your own strategy and seeing how it will compare to the set of original strategies. http://ec2-54-185-19-38.us-west-2.compute.amazonaws.com:5006/srv In the section above you can specify security and data range. In the section below you can choose strategy to customize and modify it's parameters. The strategy comparison table will automatically update and will display a newly created strategy side by side with the original strategies. Technology The tool is developed on bokeh and python and allows you to edit configuration parameters of each strategy all without programming knowledge. The strategies are fully specified via key/value pairs in the format of ini files used to initialize programs. The strategy classes are autogenerated by reading the ini config files dynamically using "factory" pattern. You can find a simplified code in this github repo: https://github.com/varturas/PnlAITk Next Steps In the future I want to give users ability to monitor their chosen strategy by receiving trading algo alerts whenever performance of their custom trading algo is changes significantly. I'm going to be adding more strategies, some of standard technical analysis variety and some will be more custom and more advanced. I'll also be adding more columns to the performance table to give better information. You can receive daily newsletter with the list of trading strategies generated by above-mentioned web-tool by registering on http://pnl.ai/ and checking subscribe checkmark.

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

Michaelbetterecycle•This week

0.818

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  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  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)  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.  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

#reddit #team #made

Hit a major milestone with my app that helps people find jobs and optimize their resume

#reddit #major #milestone

Redd_Surfer_•This week

Hit a major milestone with my app that helps people find jobs and optimize their resume

I've been grinding for ~1.5 years now on my sideproject, Jobs-Scout, which helps people find jobs and optimize their resume for any specific role. I've been in industry a number of years as a senior manager, so I have done lots of interviewing and hiring and I think that helps my tool do a better job than others in knowing how to position a resume. It's the non-technical stuff, like branding, SEO etc. thats the hardest for me, but my buddy is now helping and we're starting to make in-roads and traffic is up a lot! 🚀 We hit our 200th paid customer today which is a major milestone for us, and just wanted to share! The app features: resume-to-job analysis using AI (of course!) a free job board updated daily matching and emailing new jobs to users (ie. 'scouting' for jobs hence the name!) resume builder and editor with inline AI optimization free tier (3 free analyses a month) and paid tiers If you're curious, everything's running on AWS, and I code and maintain it myself in the evenings after work, and my colleague is now on marketing and business development. Biggest lesson was finding a trustworthy co-founder. I went through a couple of iterations, but you need a certain personality that's able to keep up with the hustle. Would love feedback or tips on how to keep growing 🚀 . Edit: link: https://www.jobs-scout.com

Michaelbetterecycle•This week

0.818

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  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  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)  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.  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’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

#reddit #i’ve #built

Michaelbetterecycle•This week

0.818

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  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  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)  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.  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

[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

#reddit #lukewarm #graph

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

0.333

[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

#reddit #misuse #deep

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

#reddit #yoshua #bengio's

qtangs•This week

[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.

[N] How Stability AI’s Founder Tanked His Billion-Dollar Startup

[N] How Stability AI’s Founder Tanked His Billion-Dollar Startup

forbes article: https://www.forbes.com/sites/kenrickcai/2024/03/29/how-stability-ais-founder-tanked-his-billion-dollar-startup/ archive no paywall: https://archive.is/snbeV How Stability AI’s Founder Tanked His Billion-Dollar Startup Mar 29, 2024 Stability AI founder Emad Mostaque took the stage last week at the Terranea Resort in Palos Verdes, California to roaring applause and an introduction from an AI-generated Aristotle who announced him as “a modern Prometheus” with “the astuteness of Athena and the vision of Daedalus.” “Under his stewardship, AI becomes the Herculean force poised to vanquish the twin serpents of illness and ailment and extend the olive branch of longevity,” the faux Aristotle proclaimed. “I think that’s the best intro I’ve ever had,” Mostaque said. But behind Mostaque's hagiographic introduction lay a grim and fast metastasizing truth. Stability, once one of AI’s buzziest startups, was floundering. It had been running out of money for months and Mostaque had been unable to secure enough additional funding. It had defaulted on payments to Amazon whose cloud service undergirded Stability’s core offerings. The star research team behind its flagship text-to-image generator Stable Diffusion had tendered their resignations just three days before — as Forbes would first report — and other senior leaders had issued him an ultimatum: resign, or we walk too. Still, onstage before a massive audience of peers and acolytes, Mostaque talked a big game. “AI is jet planes for the mind,” he opined. “AI is our collective intelligence. It's the human Colossus.” He claimed a new, faster version of the Stable Diffusion image generator released earlier this month could generate “200 cats with hats per second.” But later, when he was asked about Stability’s financial model, Mostaque fumbled. “I can’t say that publicly,” he replied. “But it’s going well. We’re ahead of forecast.” Four days later, Mostaque stepped down as CEO of Stability, as Forbes first reported. In a post to X, the service formerly known as Twitter, he claimed he’d voluntarily abdicated his role to decentralize “the concentration of power in AI.” But sources told Forbes that was hardly the case. Behind the scenes, Mostaque had fought to maintain his position and control despite mounting pressure externally and internally to step down. Company documents and interviews with 32 current and former employees, investors, collaborators and industry observers suggest his abrupt exit was the result of poor business judgment and wild overspending that undermined confidence in his vision and leadership, and ultimately kneecapped the company. Mostaque, through his attorneys, declined to comment on record on a detailed list of questions about the reporting in this story. But in an email to Forbes earlier this week he broadly disputed the allegations. “Nobody tells you how hard it is to be a CEO and there are better CEOs than me to scale a business,” he said in a statement. “I am not sure anyone else would have been able to build and grow the research team to build the best and most widely used models out there and I’m very proud of the team there. I look forward to moving onto the next problem to handle and hopefully move the needle.” In an emailed statement, Christian Laforte and Shan Shan Wong, the interim co-CEOs who replaced Mostaque, said, "the company remains focused on commercializing its world leading technology” and providing it “to partners across the creative industries." After starting Stability in 2019, Mostaque built the company into an early AI juggernaut by seizing upon a promising research project that would become Stable Diffusion and funding it into a business reality. The ease with which the software generated detailed images from the simplest text prompts immediately captivated the public: 10 million people used it on any given day, the company told Forbes in early 2023. For some true believers, Mostaque was a crucial advocate for open-source AI development in a space dominated by the closed systems of OpenAI, Google and Anthropic. But his startup’s rise to one of the buzziest in generative AI was in part built on a series of exaggerations and misleading claims, as Forbes first reported last year (Mostaque disputed some points at the time). And they continued after he raised $100 million at a $1 billion valuation just days after launching Stable Diffusion in 2022. His failure to deliver on an array of grand promises, like building bespoke AI models for nation states, and his decision to pour tens of millions into research without a sustainable business plan, eroded Stability’s foundations and jeopardized its future. "He was just giving shit away,” one former employee told Forbes. “That man legitimately wanted to transform the world. He actually wanted to train AI models for kids in Malawi. Was it practical? Absolutely not." By October 2023, Stability would have less than $4 million left in the bank, according to an internal memo prepared for a board meeting and reviewed by Forbes. And mounting debt, including months of overdue Amazon Web Services payments, had already left it in the red. To avoid legal penalties for skipping Americans staff’s payroll, the document explained, the London-based startup was considering delaying tax payments to the U.K. government. It was Stability’s armada of GPUs, the wildly powerful and equally expensive chips undergirding AI, that were so taxing the company’s finances. Hosted by AWS, they had long been one of Mostaque’s bragging points; he often touted them as one of the world’s 10 largest supercomputers. They were responsible for helping Stability’s researchers build and maintain one of the top AI image generators, as well as break important new ground on generative audio, video and 3D models. “Undeniably, Stability has continued to ship a lot of models,” said one former employee. “They may not have profited off of it, but the broader ecosystem benefitted in a huge, huge way.” But the costs associated with so much compute were now threatening to sink the company. According to an internal October financial forecast seen by Forbes, Stability was on track to spend $99 million on compute in 2023. It noted as well that Stability was “underpaying AWS bills for July (by $1M)” and “not planning to pay AWS at the end of October for August usage ($7M).” Then there were the September and October bills, plus $1 million owed to Google Cloud and $600,000 to GPU cloud data center CoreWeave. (Amazon, Google and CoreWeave declined to comment.) With an additional $54 million allocated to wages and operating expenses, Stability’s total projected costs for 2023 were $153 million. But according to its October financial report, its projected revenue for the calendar year was just $11 million. Stability was on track to lose more money per month than it made in an entire year. The company’s dire financial position had thoroughly soured Stability’s current investors, including Coatue, which had invested tens of millions in the company during its $101 million funding round in 2022. In the middle of 2023, Mostaque agreed to an independent audit after Coatue raised a series of concerns, according to a source with direct knowledge of the matter. The outcome of the investigation is unclear. Coatue declined to comment. Within a week of an early October board meeting where Mostaque shared that financial forecast, Lightspeed Venture Partners, another major investor, sent a letter to the board urging them to sell the company. The distressing numbers had “severely undermined” the firm’s confidence in Mostaque’s ability to lead the company. “In particular, we are surprised and deeply concerned by a cash position just now disclosed to us that is inconsistent with prior discussions on this topic,” Lightspeed’s general counsel Brett Nissenberg wrote in the letter, a copy of which was viewed by Forbes. “Lightspeed believes that the company is not likely financeable on terms that would assure the company’s long term sound financial position.” (Lightspeed declined a request for comment.) The calls for a sale led Stability to quietly begin looking for a buyer. Bloomberg reported in November that Stability approached AI startups Cohere and Jasper to gauge their interest. Stability denied this, and Jasper CEO Timothy Young did the same when reached for comment by Forbes. A Cohere representative declined to comment. But one prominent AI company confirmed that Mostaque’s representatives had reached out to them to test the waters. Those talks did not advance because “the numbers didn’t add up,” this person, who declined to be named due to the confidential nature of the talks, told Forbes. Stability also tried to court Samsung as a buyer, going so far as to redecorate its office in advance of a planned meeting with the Korean electronics giant. (Samsung said that it invested in Stability in 2023 and that it does not comment on M&A discussions.) Coatue had been calling for Mostaque’s resignation for months, according to a source with direct knowledge. But it and other investors were unable to oust him because he was the company’s majority shareholder. When they tried a different tact by rallying other investors to offer him a juicy equity package to resign, Mostaque refused, said two sources. By October, Coatue and Lightspeed had had enough. Coatue left the board and Lightspeed resigned its observer seat. “Emad infuriated our initial investors so much it’s just making it impossible for us to raise more money under acceptable terms,” one current Stability executive told Forbes. The early months of 2024 saw Stability’s already precarious position eroding further still. Employees were quietly laid off. Three people in a position to know estimated that at least 10% of staff were cut. And cash reserves continued to dwindle. Mostaque mentioned a lifeline at the October board meeting: $95 million in tentative funding from new investors, pending due diligence. But in the end, only a fraction of it was wired, two sources say, much of it from Intel, which Forbes has learned invested $20 million, a fraction of what was reported. (Intel did not return a request for comment by publication time.) Two hours after Forbes broke the news of Mostaque’s plans to step down as CEO, Stability issued a press release confirming his resignation. Chief operating officer Wong and chief technology officer Laforte have taken over in the interim. Mostaque, who said on X that he still owns a majority of the company, also stepped down from the board, which has now initiated a search for a permanent CEO. There is a lot of work to be done to turn things around, and very little time in which to do it. Said the current Stability executive, “There’s still a possibility of a turnaround story, but the odds drop by the day.” In July of 2023, Mostaque still thought he could pull it off. Halfway through the month, he shared a fundraising plan with his lieutenants. It was wildly optimistic, detailing the raise of $500 million in cash and another $750 million in computing facilities from marquee investors like Nvidia, Google, Intel and the World Bank (Nvidia and Google declined comment. Intel did not respond. The World Bank said it did not invest in Stability). In a Slack message reviewed by Forbes, Mostaque said Google was “willing to move fast” and the round was “likely to be oversubscribed.” It wasn’t. Three people with direct knowledge of these fundraising efforts told Forbes that while there was some interest in Stability, talks often stalled when it came time to disclose financials. Two of them noted that earlier in the year, Mostaque had simply stopped engaging with VCs who asked for numbers. Only one firm invested around that time: actor Ashton Kutcher’s Sound Ventures, which invested $35 million in the form of a convertible SAFE note during the second quarter, according to an internal document. (Sound Ventures did not respond to a request for comment.) And though he’d managed to score a meeting with Nvidia and its CEO Jensen Huang, it ended in disaster, according to two sources. “Under Jensen's microscopic questions, Emad just fell apart,” a source in position to know told Forbes. Huang quickly concluded Stability wasn’t ready for an investment from Nvidia, the sources said. Mostaque told Forbes in an email that he had not met with Huang since 2022, except to say “hello and what’s up a few times after.” His July 2023 message references a plan to raise $150 million from Nvidia. (Nvidia declined to comment.) After a June Forbes investigation citing more than 30 sources revealed Mostaque’s history of misleading claims, Mostaque struggled to raise funding, a Stability investor told Forbes. (Mostaque disputed the story at the time and called it "coordinated lies" in his email this week to Forbes). Increasingly, investors scrutinized his assertions and pressed for data. And Young, now the CEO of Jasper, turned down a verbal offer to be Stability’s president after reading the article, according to a source with direct knowledge of the matter. The collapse of the talks aggravated the board and other executives, who had hoped Young would compensate for the sales and business management skills that Mostaque lacked, according to four people in a position to know. (Young declined to comment.) When Stability’s senior leadership convened in London for the CogX conference in September, the financing had still not closed. There, a group of executives confronted Mostaque asking questions about the company’s cash position and runway, according to three people with direct knowledge of the incident. They did not get the clarity they’d hoped for. By October, Mostaque had reduced his fundraising target by more than 80%. The months that followed saw a steady drumbeat of departures — general counsel Adam Avrunin, vice presidents Mike Melnicki, Ed Newton-Rex and Joe Penna, chief people officer Ozden Onder — culminating in the demoralizing March exit of Stable Diffusion’s primary developers Robin Rombach, Andreas Blattmann, Patrick Esser and Dominik Lorenz. Rombach, who led the team, had been angling to leave for months, two sources said, first threatening to resign last summer because of the fundraising failures. Others left over concerns about cash flow, as well as liabilities — including what four people described as Mostaque’s lax approach to ensuring that Stability products could not be used to produce child sexual abuse imagery. “Stability AI is committed to preventing the misuse of AI and prohibits the use of our image models and services for unlawful activity, including attempts to edit or create CSAM,” Ella Irwin, senior vice president of integrity, said in a statement. Newton-Rex told Forbes he resigned because he disagreed with Stability’s position that training AI on copyrighted work without consent is fair use. Melnicki and Penna declined to comment. Avrunin and Onder could not be reached for comment. None of the researchers responded to requests for comment. The Stable Diffusion researchers’ departure as a cohort says a lot about the state of Stability AI. The company’s researchers were widely viewed as its crown jewels, their work subsidized with a firehose of pricey compute power that was even extended to people outside the company. Martino Russi, an artificial intelligence researcher, told Forbes that though he was never formally employed by Stability, the company provided him a “staggering” amount of compute between January and April 2023 to play around with developing an AI video generator that Stability might someday use. “It was Candy Land or Coney Island,” said Russi, who estimates that his experiment, which was ultimately shelved, cost the company $2.5 million. Stable Diffusion was simultaneously Stability’s marquee product and its existential cash crisis. One current employee described it to Forbes as “a giant vacuum that absorbed everything: money, compute, people.” While the software was widely used, with Mostaque claiming downloads reaching into the hundreds of millions, Stability struggled to translate that wild success into revenue. Mostaque knew it could be done — peers at Databricks, Elastic and MongoDB had all turned a free product into a lucrative business — he just couldn’t figure out how. His first attempt was Stability’s API, which allowed paying customers to integrate Stable Diffusion into their own products. In early 2023, a handful of small companies, like art generator app NightCafe and presentation software startup Tome, signed on, according to four people with knowledge of the deals. But Stability’s poor account management services soured many, and in a matter of months NightCafe and Tome canceled their contracts, three people said. NightCafe founder Angus Russell told Forbes that his company switched to a competitor which “offered much cheaper inference costs and a broader service.” Tome did not respond to a request for comment. Meanwhile, Mostaque’s efforts to court larger companies like Samsung and Snapchat were failing, according to five people familiar with the effort. Canva, which was already one of the heaviest users of open-sourced Stable Diffusion, had multiple discussions with Stability, which was angling for a contract it hoped would generate several millions in annual revenue. But the deal never materialized, four sources said. “These three companies wanted and needed us,” one former employee told Forbes. “They would have been the perfect customers.” (Samsung, Snap and Canva declined to comment.) “It’s not that there was not an appetite to pay Stability — there were tons of companies that would have that wanted to,” the former employee said. “There was a huge opportunity and demand, but just a resistance to execution.” Mostaque’s other big idea was to provide governments with bespoke national AI models that would invigorate their economies and citizenry. “Emad envisions a world where AI through 100 national models serves not as a tool of the few, but as a benefactor to all promising to confront great adversaries, cancer, autism, and the sands of time itself,” the AI avatar of Aristotle said in his intro at the conference. Mostaque told several prospective customers that he could deliver such models within 60 days — an untenable timeline, according to two people in position to know. Stability attempted to develop a model for the Singaporean government over the protestation of employees who questioned its technical feasibility, three sources familiar with the effort told Forbes. But it couldn’t pull it off and Singapore never became a customer. (The government of Singapore confirmed it did not enter into a deal with Stability, but declined to answer additional questions.) As Stability careened from one new business idea to another, resources were abruptly reallocated and researchers reassigned. The whiplash shifts in a largely siloed organization demoralized and infuriated employees. “There were ‘urgent’ things, ‘urgent urgent’ things and ‘most urgent,’” one former employee complained. “None of these things seem important if everything is important.” Another former Stability executive was far more pointed in their assessment. “Emad is the most disorganized leader I have ever worked with in my career,” this person told Forbes. “He has no vision, and changes directions every week, often based on what he sees on Twitter.” In a video interview posted shortly before this story was published, Mostaque explained his leadership style: “I'm particularly great at taking creatives, developers, researchers, others, and achieving their full potential in designing systems. But I should not be dealing with, you know, HR and operations and business development and other elements. There are far better people than me to do that.” By December 2023, Stability had partially abandoned its open-source roots and announced that any commercial use of Stable Diffusion would cost customers at least $20 per month (non-commercial and research use of Stable Diffusion would remain free). But privately, Stability was considering a potentially more lucrative source of revenue: reselling the compute it was leasing from providers like AWS, according to six people familiar with the effort. Though it was essentially GPU arbitrage, Stability framed the strategy to investors as a “managed services” offering. Its damning October financial report projected optimistically that such an offering would bring in $139 million in 2024 — 98% of its revenue. Multiple employees at the time told Forbes they feared reselling compute, even if the company called it “managed services,” would violate the terms of Stability’s contract with AWS. Amazon declined to comment. “The line internally was that we are not reselling compute,” one former employee said. “This was some of the dirtiest feeling stuff.” Stability also discussed reselling a cluster of Nvidia A100 chips, leased via CoreWeave, to the venture capital firm Andreessen Horowitz, three sources said. “It was under the guise of managed services, but there wasn’t any management happening,” one of these people told Forbes. Andreessen Horowitz and CoreWeave declined to comment. Stability did not respond to questions about if it plans to continue this strategy now that Mostaque is out of the picture. Regardless, interim co-CEOs Wong and Laforte are on a tight timeline to clean up his mess. Board chairman Jim O’Shaughnessy said in a statement that he was confident the pair “will adeptly steer the company forward in developing and commercializing industry-leading generative AI products.” But burn continues to far outpace revenue. The Financial Times reported Friday that the company made $5.4 million of revenue in February, against $8 million in costs. Several sources said there are ongoing concerns about making payroll for the roughly 150 remaining employees. Leadership roles have gone vacant for months amid the disarray, leaving the company increasingly directionless. Meanwhile, a potentially catastrophic legal threat looms over the company: A trio of copyright infringement lawsuits brought by Getty Images and a group of artists in the U.S. and U.K., who claim Stability illegally used their art and photography to train the AI models powering Stable Diffusion. A London-based court has already rejected the company’s bid to throw out one of the lawsuits on the basis that none of its researchers were based in the U.K. And Stability’s claim that Getty’s Delaware lawsuit should be blocked because it's a U.K.-based company was rejected. (Stability did not respond to questions about the litigation.) AI-related copyright litigation “could go on for years,” according to Eric Goldman, a law professor at Santa Clara University. He told Forbes that though plaintiffs suing AI firms face an uphill battle overcoming the existing legal precedent on copyright infringement, the quantity of arguments available to make are virtually inexhaustible. “Like in military theory, if there’s a gap in your lines, that’s where the enemy pours through — if any one of those arguments succeeds, it could completely change the generative AI environment,” he said. “In some sense, generative AI as an industry has to win everything.” Stability, which had more than $100 million in the bank just a year and a half ago, is in a deep hole. Not only does it need more funding, it needs a viable business model — or a buyer with the vision and chops to make it successful in a fast-moving and highly competitive sector. At an all hands meeting this past Monday, Stability’s new leaders detailed a path forward. One point of emphasis: a plan to better manage resources and expenses, according to one person in attendance. It’s a start, but Mostaque’s meddling has left them with little runway to execute. His resignation, though, has given some employees hope. “A few people are 100% going to reconsider leaving after today,” said one current employee. “And the weird gloomy aura of hearing Emad talking nonsense for an hour is gone.” Shortly before Mostaque resigned, one current Stability executive told Forbes that they were optimistic his departure could make Stability appealing enough to receive a small investment or sale to a friendly party. “There are companies that have raised hundreds of millions of dollars that have much less intrinsic value than Stability,” the person said. “A white knight may still appear.”

[D] AI Agents: too early, too expensive, too unreliable

madredditscientist•This week

[D] AI Agents: too early, too expensive, too unreliable

Reference: Full blog post There has been a lot of hype about the promise of autonomous agent-based LLM workflows. By now, all major LLMs are capable of interacting with external tools and functions, letting the LLM perform sequences of tasks automatically. But reality is proving more challenging than anticipated. The WebArena leaderboard, which benchmarks LLMs agents against real-world tasks, shows that even the best-performing models have a success rate of only 35.8%. Challenges in Practice After seeing many attempts to AI agents, I believe it's too early, too expensive, too slow, too unreliable. It feels like many AI agent startups are waiting for a model breakthrough that will start the race to productize agents. Reliability: As we all know, LLMs are prone to hallucinations and inconsistencies. Chaining multiple AI steps compounds these issues, especially for tasks requiring exact outputs. Performance and costs: GPT-4o, Gemini-1.5, and Claude Opus are working quite well with tool usage/function calling, but they are still slow and expensive, particularly if you need to do loops and automatic retries. Legal concerns: Companies may be held liable for the mistakes of their agents. A recent example is Air Canada being ordered to pay a customer who was misled by the airline's chatbot. User trust: The "black box" nature of AI agents and stories like the above makes it hard for users to understand and trust their outputs. Gaining user trust for sensitive tasks involving payments or personal information will be hard (paying bills, shopping, etc.). Real-World Attempts Several startups are tackling the AI agent space, but most are still experimental or invite-only: adept.ai - $350M funding, but access is still very limited MultiOn - funding unknown, their API-first approach seems promising HypeWrite - $2.8M funding, started with an AI writing assistant and expanded into the agent space minion.ai - created some initial buzz but has gone quiet now, waitlist only Only MultiOn seems to be pursuing the "give it instructions and watch it go" approach, which is more in line with the promise of AI agents. All others are going down the record-and-replay RPA route, which may be necessary for reliability at this stage. Large players are also bringing AI capabilities to desktops and browsers, and it looks like we'll get native AI integrations on a system level: OpenAI announced their Mac desktop app that can interact with the OS screen. At Google I/O, Google demonstrated Gemini automatically processing a shopping return. Microsoft announced Copilot Studio, which will let developers build AI agent bots. Screenshot Screenshot These tech demos are impressive, but we'll see how well these agent capabilities will work when released publicly and tested against real-world scenarios instead of hand-picked demo cases. The Path Forward AI agents overhyped and it's too early. However, the underlying models continue to advance quickly, and we can expect to see more successful real-world applications. Instead of trying to have one large general purpose agent that is hard to control and test, we can use many smaller agents that basically just pick the right strategy for a specific sub-task in our workflows. These "agents" can be thought of as medium-sized LLM prompts with a) context and b) a set of functions available to call. The most promising path forward likely looks like this: Narrowly scoped, well testable automations that use AI as an augmentation tool rather than pursuing full autonomy Human-in-the-loop approaches that keep humans involved for oversight and handling edge cases Setting realistic expectations about current capabilities and limitations By combining tightly constrained agents, good evaluation data, human-in-the-loop oversight, and traditional engineering methods, we can achieve reliably good results for automating medium-complex tasks. Will AI agents automate tedious repetitive work, such as web scraping, form filling, and data entry? Yes, absolutely. Will AI agents autonomously book your vacation without your intervention? Unlikely, at least in the near future.

#reddit #agents:#early,

[N] How Stability AI’s Founder Tanked His Billion-Dollar Startup

forbes article: https://www.forbes.com/sites/kenrickcai/2024/03/29/how-stability-ais-founder-tanked-his-billion-dollar-startup/ archive no paywall: https://archive.is/snbeV How Stability AI’s Founder Tanked His Billion-Dollar Startup Mar 29, 2024 Stability AI founder Emad Mostaque took the stage last week at the Terranea Resort in Palos Verdes, California to roaring applause and an introduction from an AI-generated Aristotle who announced him as “a modern Prometheus” with “the astuteness of Athena and the vision of Daedalus.” “Under his stewardship, AI becomes the Herculean force poised to vanquish the twin serpents of illness and ailment and extend the olive branch of longevity,” the faux Aristotle proclaimed. “I think that’s the best intro I’ve ever had,” Mostaque said. But behind Mostaque's hagiographic introduction lay a grim and fast metastasizing truth. Stability, once one of AI’s buzziest startups, was floundering. It had been running out of money for months and Mostaque had been unable to secure enough additional funding. It had defaulted on payments to Amazon whose cloud service undergirded Stability’s core offerings. The star research team behind its flagship text-to-image generator Stable Diffusion had tendered their resignations just three days before — as Forbes would first report — and other senior leaders had issued him an ultimatum: resign, or we walk too. Still, onstage before a massive audience of peers and acolytes, Mostaque talked a big game. “AI is jet planes for the mind,” he opined. “AI is our collective intelligence. It's the human Colossus.” He claimed a new, faster version of the Stable Diffusion image generator released earlier this month could generate “200 cats with hats per second.” But later, when he was asked about Stability’s financial model, Mostaque fumbled. “I can’t say that publicly,” he replied. “But it’s going well. We’re ahead of forecast.” Four days later, Mostaque stepped down as CEO of Stability, as Forbes first reported. In a post to X, the service formerly known as Twitter, he claimed he’d voluntarily abdicated his role to decentralize “the concentration of power in AI.” But sources told Forbes that was hardly the case. Behind the scenes, Mostaque had fought to maintain his position and control despite mounting pressure externally and internally to step down. Company documents and interviews with 32 current and former employees, investors, collaborators and industry observers suggest his abrupt exit was the result of poor business judgment and wild overspending that undermined confidence in his vision and leadership, and ultimately kneecapped the company. Mostaque, through his attorneys, declined to comment on record on a detailed list of questions about the reporting in this story. But in an email to Forbes earlier this week he broadly disputed the allegations. “Nobody tells you how hard it is to be a CEO and there are better CEOs than me to scale a business,” he said in a statement. “I am not sure anyone else would have been able to build and grow the research team to build the best and most widely used models out there and I’m very proud of the team there. I look forward to moving onto the next problem to handle and hopefully move the needle.” In an emailed statement, Christian Laforte and Shan Shan Wong, the interim co-CEOs who replaced Mostaque, said, "the company remains focused on commercializing its world leading technology” and providing it “to partners across the creative industries." After starting Stability in 2019, Mostaque built the company into an early AI juggernaut by seizing upon a promising research project that would become Stable Diffusion and funding it into a business reality. The ease with which the software generated detailed images from the simplest text prompts immediately captivated the public: 10 million people used it on any given day, the company told Forbes in early 2023. For some true believers, Mostaque was a crucial advocate for open-source AI development in a space dominated by the closed systems of OpenAI, Google and Anthropic. But his startup’s rise to one of the buzziest in generative AI was in part built on a series of exaggerations and misleading claims, as Forbes first reported last year (Mostaque disputed some points at the time). And they continued after he raised $100 million at a $1 billion valuation just days after launching Stable Diffusion in 2022. His failure to deliver on an array of grand promises, like building bespoke AI models for nation states, and his decision to pour tens of millions into research without a sustainable business plan, eroded Stability’s foundations and jeopardized its future. "He was just giving shit away,” one former employee told Forbes. “That man legitimately wanted to transform the world. He actually wanted to train AI models for kids in Malawi. Was it practical? Absolutely not." By October 2023, Stability would have less than $4 million left in the bank, according to an internal memo prepared for a board meeting and reviewed by Forbes. And mounting debt, including months of overdue Amazon Web Services payments, had already left it in the red. To avoid legal penalties for skipping Americans staff’s payroll, the document explained, the London-based startup was considering delaying tax payments to the U.K. government. It was Stability’s armada of GPUs, the wildly powerful and equally expensive chips undergirding AI, that were so taxing the company’s finances. Hosted by AWS, they had long been one of Mostaque’s bragging points; he often touted them as one of the world’s 10 largest supercomputers. They were responsible for helping Stability’s researchers build and maintain one of the top AI image generators, as well as break important new ground on generative audio, video and 3D models. “Undeniably, Stability has continued to ship a lot of models,” said one former employee. “They may not have profited off of it, but the broader ecosystem benefitted in a huge, huge way.” But the costs associated with so much compute were now threatening to sink the company. According to an internal October financial forecast seen by Forbes, Stability was on track to spend $99 million on compute in 2023. It noted as well that Stability was “underpaying AWS bills for July (by $1M)” and “not planning to pay AWS at the end of October for August usage ($7M).” Then there were the September and October bills, plus $1 million owed to Google Cloud and $600,000 to GPU cloud data center CoreWeave. (Amazon, Google and CoreWeave declined to comment.) With an additional $54 million allocated to wages and operating expenses, Stability’s total projected costs for 2023 were $153 million. But according to its October financial report, its projected revenue for the calendar year was just $11 million. Stability was on track to lose more money per month than it made in an entire year. The company’s dire financial position had thoroughly soured Stability’s current investors, including Coatue, which had invested tens of millions in the company during its $101 million funding round in 2022. In the middle of 2023, Mostaque agreed to an independent audit after Coatue raised a series of concerns, according to a source with direct knowledge of the matter. The outcome of the investigation is unclear. Coatue declined to comment. Within a week of an early October board meeting where Mostaque shared that financial forecast, Lightspeed Venture Partners, another major investor, sent a letter to the board urging them to sell the company. The distressing numbers had “severely undermined” the firm’s confidence in Mostaque’s ability to lead the company. “In particular, we are surprised and deeply concerned by a cash position just now disclosed to us that is inconsistent with prior discussions on this topic,” Lightspeed’s general counsel Brett Nissenberg wrote in the letter, a copy of which was viewed by Forbes. “Lightspeed believes that the company is not likely financeable on terms that would assure the company’s long term sound financial position.” (Lightspeed declined a request for comment.) The calls for a sale led Stability to quietly begin looking for a buyer. Bloomberg reported in November that Stability approached AI startups Cohere and Jasper to gauge their interest. Stability denied this, and Jasper CEO Timothy Young did the same when reached for comment by Forbes. A Cohere representative declined to comment. But one prominent AI company confirmed that Mostaque’s representatives had reached out to them to test the waters. Those talks did not advance because “the numbers didn’t add up,” this person, who declined to be named due to the confidential nature of the talks, told Forbes. Stability also tried to court Samsung as a buyer, going so far as to redecorate its office in advance of a planned meeting with the Korean electronics giant. (Samsung said that it invested in Stability in 2023 and that it does not comment on M&A discussions.) Coatue had been calling for Mostaque’s resignation for months, according to a source with direct knowledge. But it and other investors were unable to oust him because he was the company’s majority shareholder. When they tried a different tact by rallying other investors to offer him a juicy equity package to resign, Mostaque refused, said two sources. By October, Coatue and Lightspeed had had enough. Coatue left the board and Lightspeed resigned its observer seat. “Emad infuriated our initial investors so much it’s just making it impossible for us to raise more money under acceptable terms,” one current Stability executive told Forbes. The early months of 2024 saw Stability’s already precarious position eroding further still. Employees were quietly laid off. Three people in a position to know estimated that at least 10% of staff were cut. And cash reserves continued to dwindle. Mostaque mentioned a lifeline at the October board meeting: $95 million in tentative funding from new investors, pending due diligence. But in the end, only a fraction of it was wired, two sources say, much of it from Intel, which Forbes has learned invested $20 million, a fraction of what was reported. (Intel did not return a request for comment by publication time.) Two hours after Forbes broke the news of Mostaque’s plans to step down as CEO, Stability issued a press release confirming his resignation. Chief operating officer Wong and chief technology officer Laforte have taken over in the interim. Mostaque, who said on X that he still owns a majority of the company, also stepped down from the board, which has now initiated a search for a permanent CEO. There is a lot of work to be done to turn things around, and very little time in which to do it. Said the current Stability executive, “There’s still a possibility of a turnaround story, but the odds drop by the day.” In July of 2023, Mostaque still thought he could pull it off. Halfway through the month, he shared a fundraising plan with his lieutenants. It was wildly optimistic, detailing the raise of $500 million in cash and another $750 million in computing facilities from marquee investors like Nvidia, Google, Intel and the World Bank (Nvidia and Google declined comment. Intel did not respond. The World Bank said it did not invest in Stability). In a Slack message reviewed by Forbes, Mostaque said Google was “willing to move fast” and the round was “likely to be oversubscribed.” It wasn’t. Three people with direct knowledge of these fundraising efforts told Forbes that while there was some interest in Stability, talks often stalled when it came time to disclose financials. Two of them noted that earlier in the year, Mostaque had simply stopped engaging with VCs who asked for numbers. Only one firm invested around that time: actor Ashton Kutcher’s Sound Ventures, which invested $35 million in the form of a convertible SAFE note during the second quarter, according to an internal document. (Sound Ventures did not respond to a request for comment.) And though he’d managed to score a meeting with Nvidia and its CEO Jensen Huang, it ended in disaster, according to two sources. “Under Jensen's microscopic questions, Emad just fell apart,” a source in position to know told Forbes. Huang quickly concluded Stability wasn’t ready for an investment from Nvidia, the sources said. Mostaque told Forbes in an email that he had not met with Huang since 2022, except to say “hello and what’s up a few times after.” His July 2023 message references a plan to raise $150 million from Nvidia. (Nvidia declined to comment.) After a June Forbes investigation citing more than 30 sources revealed Mostaque’s history of misleading claims, Mostaque struggled to raise funding, a Stability investor told Forbes. (Mostaque disputed the story at the time and called it "coordinated lies" in his email this week to Forbes). Increasingly, investors scrutinized his assertions and pressed for data. And Young, now the CEO of Jasper, turned down a verbal offer to be Stability’s president after reading the article, according to a source with direct knowledge of the matter. The collapse of the talks aggravated the board and other executives, who had hoped Young would compensate for the sales and business management skills that Mostaque lacked, according to four people in a position to know. (Young declined to comment.) When Stability’s senior leadership convened in London for the CogX conference in September, the financing had still not closed. There, a group of executives confronted Mostaque asking questions about the company’s cash position and runway, according to three people with direct knowledge of the incident. They did not get the clarity they’d hoped for. By October, Mostaque had reduced his fundraising target by more than 80%. The months that followed saw a steady drumbeat of departures — general counsel Adam Avrunin, vice presidents Mike Melnicki, Ed Newton-Rex and Joe Penna, chief people officer Ozden Onder — culminating in the demoralizing March exit of Stable Diffusion’s primary developers Robin Rombach, Andreas Blattmann, Patrick Esser and Dominik Lorenz. Rombach, who led the team, had been angling to leave for months, two sources said, first threatening to resign last summer because of the fundraising failures. Others left over concerns about cash flow, as well as liabilities — including what four people described as Mostaque’s lax approach to ensuring that Stability products could not be used to produce child sexual abuse imagery. “Stability AI is committed to preventing the misuse of AI and prohibits the use of our image models and services for unlawful activity, including attempts to edit or create CSAM,” Ella Irwin, senior vice president of integrity, said in a statement. Newton-Rex told Forbes he resigned because he disagreed with Stability’s position that training AI on copyrighted work without consent is fair use. Melnicki and Penna declined to comment. Avrunin and Onder could not be reached for comment. None of the researchers responded to requests for comment. The Stable Diffusion researchers’ departure as a cohort says a lot about the state of Stability AI. The company’s researchers were widely viewed as its crown jewels, their work subsidized with a firehose of pricey compute power that was even extended to people outside the company. Martino Russi, an artificial intelligence researcher, told Forbes that though he was never formally employed by Stability, the company provided him a “staggering” amount of compute between January and April 2023 to play around with developing an AI video generator that Stability might someday use. “It was Candy Land or Coney Island,” said Russi, who estimates that his experiment, which was ultimately shelved, cost the company $2.5 million. Stable Diffusion was simultaneously Stability’s marquee product and its existential cash crisis. One current employee described it to Forbes as “a giant vacuum that absorbed everything: money, compute, people.” While the software was widely used, with Mostaque claiming downloads reaching into the hundreds of millions, Stability struggled to translate that wild success into revenue. Mostaque knew it could be done — peers at Databricks, Elastic and MongoDB had all turned a free product into a lucrative business — he just couldn’t figure out how. His first attempt was Stability’s API, which allowed paying customers to integrate Stable Diffusion into their own products. In early 2023, a handful of small companies, like art generator app NightCafe and presentation software startup Tome, signed on, according to four people with knowledge of the deals. But Stability’s poor account management services soured many, and in a matter of months NightCafe and Tome canceled their contracts, three people said. NightCafe founder Angus Russell told Forbes that his company switched to a competitor which “offered much cheaper inference costs and a broader service.” Tome did not respond to a request for comment. Meanwhile, Mostaque’s efforts to court larger companies like Samsung and Snapchat were failing, according to five people familiar with the effort. Canva, which was already one of the heaviest users of open-sourced Stable Diffusion, had multiple discussions with Stability, which was angling for a contract it hoped would generate several millions in annual revenue. But the deal never materialized, four sources said. “These three companies wanted and needed us,” one former employee told Forbes. “They would have been the perfect customers.” (Samsung, Snap and Canva declined to comment.) “It’s not that there was not an appetite to pay Stability — there were tons of companies that would have that wanted to,” the former employee said. “There was a huge opportunity and demand, but just a resistance to execution.” Mostaque’s other big idea was to provide governments with bespoke national AI models that would invigorate their economies and citizenry. “Emad envisions a world where AI through 100 national models serves not as a tool of the few, but as a benefactor to all promising to confront great adversaries, cancer, autism, and the sands of time itself,” the AI avatar of Aristotle said in his intro at the conference. Mostaque told several prospective customers that he could deliver such models within 60 days — an untenable timeline, according to two people in position to know. Stability attempted to develop a model for the Singaporean government over the protestation of employees who questioned its technical feasibility, three sources familiar with the effort told Forbes. But it couldn’t pull it off and Singapore never became a customer. (The government of Singapore confirmed it did not enter into a deal with Stability, but declined to answer additional questions.) As Stability careened from one new business idea to another, resources were abruptly reallocated and researchers reassigned. The whiplash shifts in a largely siloed organization demoralized and infuriated employees. “There were ‘urgent’ things, ‘urgent urgent’ things and ‘most urgent,’” one former employee complained. “None of these things seem important if everything is important.” Another former Stability executive was far more pointed in their assessment. “Emad is the most disorganized leader I have ever worked with in my career,” this person told Forbes. “He has no vision, and changes directions every week, often based on what he sees on Twitter.” In a video interview posted shortly before this story was published, Mostaque explained his leadership style: “I'm particularly great at taking creatives, developers, researchers, others, and achieving their full potential in designing systems. But I should not be dealing with, you know, HR and operations and business development and other elements. There are far better people than me to do that.” By December 2023, Stability had partially abandoned its open-source roots and announced that any commercial use of Stable Diffusion would cost customers at least $20 per month (non-commercial and research use of Stable Diffusion would remain free). But privately, Stability was considering a potentially more lucrative source of revenue: reselling the compute it was leasing from providers like AWS, according to six people familiar with the effort. Though it was essentially GPU arbitrage, Stability framed the strategy to investors as a “managed services” offering. Its damning October financial report projected optimistically that such an offering would bring in $139 million in 2024 — 98% of its revenue. Multiple employees at the time told Forbes they feared reselling compute, even if the company called it “managed services,” would violate the terms of Stability’s contract with AWS. Amazon declined to comment. “The line internally was that we are not reselling compute,” one former employee said. “This was some of the dirtiest feeling stuff.” Stability also discussed reselling a cluster of Nvidia A100 chips, leased via CoreWeave, to the venture capital firm Andreessen Horowitz, three sources said. “It was under the guise of managed services, but there wasn’t any management happening,” one of these people told Forbes. Andreessen Horowitz and CoreWeave declined to comment. Stability did not respond to questions about if it plans to continue this strategy now that Mostaque is out of the picture. Regardless, interim co-CEOs Wong and Laforte are on a tight timeline to clean up his mess. Board chairman Jim O’Shaughnessy said in a statement that he was confident the pair “will adeptly steer the company forward in developing and commercializing industry-leading generative AI products.” But burn continues to far outpace revenue. The Financial Times reported Friday that the company made $5.4 million of revenue in February, against $8 million in costs. Several sources said there are ongoing concerns about making payroll for the roughly 150 remaining employees. Leadership roles have gone vacant for months amid the disarray, leaving the company increasingly directionless. Meanwhile, a potentially catastrophic legal threat looms over the company: A trio of copyright infringement lawsuits brought by Getty Images and a group of artists in the U.S. and U.K., who claim Stability illegally used their art and photography to train the AI models powering Stable Diffusion. A London-based court has already rejected the company’s bid to throw out one of the lawsuits on the basis that none of its researchers were based in the U.K. And Stability’s claim that Getty’s Delaware lawsuit should be blocked because it's a U.K.-based company was rejected. (Stability did not respond to questions about the litigation.) AI-related copyright litigation “could go on for years,” according to Eric Goldman, a law professor at Santa Clara University. He told Forbes that though plaintiffs suing AI firms face an uphill battle overcoming the existing legal precedent on copyright infringement, the quantity of arguments available to make are virtually inexhaustible. “Like in military theory, if there’s a gap in your lines, that’s where the enemy pours through — if any one of those arguments succeeds, it could completely change the generative AI environment,” he said. “In some sense, generative AI as an industry has to win everything.” Stability, which had more than $100 million in the bank just a year and a half ago, is in a deep hole. Not only does it need more funding, it needs a viable business model — or a buyer with the vision and chops to make it successful in a fast-moving and highly competitive sector. At an all hands meeting this past Monday, Stability’s new leaders detailed a path forward. One point of emphasis: a plan to better manage resources and expenses, according to one person in attendance. It’s a start, but Mostaque’s meddling has left them with little runway to execute. His resignation, though, has given some employees hope. “A few people are 100% going to reconsider leaving after today,” said one current employee. “And the weird gloomy aura of hearing Emad talking nonsense for an hour is gone.” Shortly before Mostaque resigned, one current Stability executive told Forbes that they were optimistic his departure could make Stability appealing enough to receive a small investment or sale to a friendly party. “There are companies that have raised hundreds of millions of dollars that have much less intrinsic value than Stability,” the person said. “A white knight may still appear.”

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

0.778

ballerburg9005•This week

[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.

#reddit #playing #league

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

#reddit #evaluating #several

gravenbirdman•This week

[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

[N] How Stability AI’s Founder Tanked His Billion-Dollar Startup

forbes article: https://www.forbes.com/sites/kenrickcai/2024/03/29/how-stability-ais-founder-tanked-his-billion-dollar-startup/ archive no paywall: https://archive.is/snbeV How Stability AI’s Founder Tanked His Billion-Dollar Startup Mar 29, 2024 Stability AI founder Emad Mostaque took the stage last week at the Terranea Resort in Palos Verdes, California to roaring applause and an introduction from an AI-generated Aristotle who announced him as “a modern Prometheus” with “the astuteness of Athena and the vision of Daedalus.” “Under his stewardship, AI becomes the Herculean force poised to vanquish the twin serpents of illness and ailment and extend the olive branch of longevity,” the faux Aristotle proclaimed. “I think that’s the best intro I’ve ever had,” Mostaque said. But behind Mostaque's hagiographic introduction lay a grim and fast metastasizing truth. Stability, once one of AI’s buzziest startups, was floundering. It had been running out of money for months and Mostaque had been unable to secure enough additional funding. It had defaulted on payments to Amazon whose cloud service undergirded Stability’s core offerings. The star research team behind its flagship text-to-image generator Stable Diffusion had tendered their resignations just three days before — as Forbes would first report — and other senior leaders had issued him an ultimatum: resign, or we walk too. Still, onstage before a massive audience of peers and acolytes, Mostaque talked a big game. “AI is jet planes for the mind,” he opined. “AI is our collective intelligence. It's the human Colossus.” He claimed a new, faster version of the Stable Diffusion image generator released earlier this month could generate “200 cats with hats per second.” But later, when he was asked about Stability’s financial model, Mostaque fumbled. “I can’t say that publicly,” he replied. “But it’s going well. We’re ahead of forecast.” Four days later, Mostaque stepped down as CEO of Stability, as Forbes first reported. In a post to X, the service formerly known as Twitter, he claimed he’d voluntarily abdicated his role to decentralize “the concentration of power in AI.” But sources told Forbes that was hardly the case. Behind the scenes, Mostaque had fought to maintain his position and control despite mounting pressure externally and internally to step down. Company documents and interviews with 32 current and former employees, investors, collaborators and industry observers suggest his abrupt exit was the result of poor business judgment and wild overspending that undermined confidence in his vision and leadership, and ultimately kneecapped the company. Mostaque, through his attorneys, declined to comment on record on a detailed list of questions about the reporting in this story. But in an email to Forbes earlier this week he broadly disputed the allegations. “Nobody tells you how hard it is to be a CEO and there are better CEOs than me to scale a business,” he said in a statement. “I am not sure anyone else would have been able to build and grow the research team to build the best and most widely used models out there and I’m very proud of the team there. I look forward to moving onto the next problem to handle and hopefully move the needle.” In an emailed statement, Christian Laforte and Shan Shan Wong, the interim co-CEOs who replaced Mostaque, said, "the company remains focused on commercializing its world leading technology” and providing it “to partners across the creative industries." After starting Stability in 2019, Mostaque built the company into an early AI juggernaut by seizing upon a promising research project that would become Stable Diffusion and funding it into a business reality. The ease with which the software generated detailed images from the simplest text prompts immediately captivated the public: 10 million people used it on any given day, the company told Forbes in early 2023. For some true believers, Mostaque was a crucial advocate for open-source AI development in a space dominated by the closed systems of OpenAI, Google and Anthropic. But his startup’s rise to one of the buzziest in generative AI was in part built on a series of exaggerations and misleading claims, as Forbes first reported last year (Mostaque disputed some points at the time). And they continued after he raised $100 million at a $1 billion valuation just days after launching Stable Diffusion in 2022. His failure to deliver on an array of grand promises, like building bespoke AI models for nation states, and his decision to pour tens of millions into research without a sustainable business plan, eroded Stability’s foundations and jeopardized its future. "He was just giving shit away,” one former employee told Forbes. “That man legitimately wanted to transform the world. He actually wanted to train AI models for kids in Malawi. Was it practical? Absolutely not." By October 2023, Stability would have less than $4 million left in the bank, according to an internal memo prepared for a board meeting and reviewed by Forbes. And mounting debt, including months of overdue Amazon Web Services payments, had already left it in the red. To avoid legal penalties for skipping Americans staff’s payroll, the document explained, the London-based startup was considering delaying tax payments to the U.K. government. It was Stability’s armada of GPUs, the wildly powerful and equally expensive chips undergirding AI, that were so taxing the company’s finances. Hosted by AWS, they had long been one of Mostaque’s bragging points; he often touted them as one of the world’s 10 largest supercomputers. They were responsible for helping Stability’s researchers build and maintain one of the top AI image generators, as well as break important new ground on generative audio, video and 3D models. “Undeniably, Stability has continued to ship a lot of models,” said one former employee. “They may not have profited off of it, but the broader ecosystem benefitted in a huge, huge way.” But the costs associated with so much compute were now threatening to sink the company. According to an internal October financial forecast seen by Forbes, Stability was on track to spend $99 million on compute in 2023. It noted as well that Stability was “underpaying AWS bills for July (by $1M)” and “not planning to pay AWS at the end of October for August usage ($7M).” Then there were the September and October bills, plus $1 million owed to Google Cloud and $600,000 to GPU cloud data center CoreWeave. (Amazon, Google and CoreWeave declined to comment.) With an additional $54 million allocated to wages and operating expenses, Stability’s total projected costs for 2023 were $153 million. But according to its October financial report, its projected revenue for the calendar year was just $11 million. Stability was on track to lose more money per month than it made in an entire year. The company’s dire financial position had thoroughly soured Stability’s current investors, including Coatue, which had invested tens of millions in the company during its $101 million funding round in 2022. In the middle of 2023, Mostaque agreed to an independent audit after Coatue raised a series of concerns, according to a source with direct knowledge of the matter. The outcome of the investigation is unclear. Coatue declined to comment. Within a week of an early October board meeting where Mostaque shared that financial forecast, Lightspeed Venture Partners, another major investor, sent a letter to the board urging them to sell the company. The distressing numbers had “severely undermined” the firm’s confidence in Mostaque’s ability to lead the company. “In particular, we are surprised and deeply concerned by a cash position just now disclosed to us that is inconsistent with prior discussions on this topic,” Lightspeed’s general counsel Brett Nissenberg wrote in the letter, a copy of which was viewed by Forbes. “Lightspeed believes that the company is not likely financeable on terms that would assure the company’s long term sound financial position.” (Lightspeed declined a request for comment.) The calls for a sale led Stability to quietly begin looking for a buyer. Bloomberg reported in November that Stability approached AI startups Cohere and Jasper to gauge their interest. Stability denied this, and Jasper CEO Timothy Young did the same when reached for comment by Forbes. A Cohere representative declined to comment. But one prominent AI company confirmed that Mostaque’s representatives had reached out to them to test the waters. Those talks did not advance because “the numbers didn’t add up,” this person, who declined to be named due to the confidential nature of the talks, told Forbes. Stability also tried to court Samsung as a buyer, going so far as to redecorate its office in advance of a planned meeting with the Korean electronics giant. (Samsung said that it invested in Stability in 2023 and that it does not comment on M&A discussions.) Coatue had been calling for Mostaque’s resignation for months, according to a source with direct knowledge. But it and other investors were unable to oust him because he was the company’s majority shareholder. When they tried a different tact by rallying other investors to offer him a juicy equity package to resign, Mostaque refused, said two sources. By October, Coatue and Lightspeed had had enough. Coatue left the board and Lightspeed resigned its observer seat. “Emad infuriated our initial investors so much it’s just making it impossible for us to raise more money under acceptable terms,” one current Stability executive told Forbes. The early months of 2024 saw Stability’s already precarious position eroding further still. Employees were quietly laid off. Three people in a position to know estimated that at least 10% of staff were cut. And cash reserves continued to dwindle. Mostaque mentioned a lifeline at the October board meeting: $95 million in tentative funding from new investors, pending due diligence. But in the end, only a fraction of it was wired, two sources say, much of it from Intel, which Forbes has learned invested $20 million, a fraction of what was reported. (Intel did not return a request for comment by publication time.) Two hours after Forbes broke the news of Mostaque’s plans to step down as CEO, Stability issued a press release confirming his resignation. Chief operating officer Wong and chief technology officer Laforte have taken over in the interim. Mostaque, who said on X that he still owns a majority of the company, also stepped down from the board, which has now initiated a search for a permanent CEO. There is a lot of work to be done to turn things around, and very little time in which to do it. Said the current Stability executive, “There’s still a possibility of a turnaround story, but the odds drop by the day.” In July of 2023, Mostaque still thought he could pull it off. Halfway through the month, he shared a fundraising plan with his lieutenants. It was wildly optimistic, detailing the raise of $500 million in cash and another $750 million in computing facilities from marquee investors like Nvidia, Google, Intel and the World Bank (Nvidia and Google declined comment. Intel did not respond. The World Bank said it did not invest in Stability). In a Slack message reviewed by Forbes, Mostaque said Google was “willing to move fast” and the round was “likely to be oversubscribed.” It wasn’t. Three people with direct knowledge of these fundraising efforts told Forbes that while there was some interest in Stability, talks often stalled when it came time to disclose financials. Two of them noted that earlier in the year, Mostaque had simply stopped engaging with VCs who asked for numbers. Only one firm invested around that time: actor Ashton Kutcher’s Sound Ventures, which invested $35 million in the form of a convertible SAFE note during the second quarter, according to an internal document. (Sound Ventures did not respond to a request for comment.) And though he’d managed to score a meeting with Nvidia and its CEO Jensen Huang, it ended in disaster, according to two sources. “Under Jensen's microscopic questions, Emad just fell apart,” a source in position to know told Forbes. Huang quickly concluded Stability wasn’t ready for an investment from Nvidia, the sources said. Mostaque told Forbes in an email that he had not met with Huang since 2022, except to say “hello and what’s up a few times after.” His July 2023 message references a plan to raise $150 million from Nvidia. (Nvidia declined to comment.) After a June Forbes investigation citing more than 30 sources revealed Mostaque’s history of misleading claims, Mostaque struggled to raise funding, a Stability investor told Forbes. (Mostaque disputed the story at the time and called it "coordinated lies" in his email this week to Forbes). Increasingly, investors scrutinized his assertions and pressed for data. And Young, now the CEO of Jasper, turned down a verbal offer to be Stability’s president after reading the article, according to a source with direct knowledge of the matter. The collapse of the talks aggravated the board and other executives, who had hoped Young would compensate for the sales and business management skills that Mostaque lacked, according to four people in a position to know. (Young declined to comment.) When Stability’s senior leadership convened in London for the CogX conference in September, the financing had still not closed. There, a group of executives confronted Mostaque asking questions about the company’s cash position and runway, according to three people with direct knowledge of the incident. They did not get the clarity they’d hoped for. By October, Mostaque had reduced his fundraising target by more than 80%. The months that followed saw a steady drumbeat of departures — general counsel Adam Avrunin, vice presidents Mike Melnicki, Ed Newton-Rex and Joe Penna, chief people officer Ozden Onder — culminating in the demoralizing March exit of Stable Diffusion’s primary developers Robin Rombach, Andreas Blattmann, Patrick Esser and Dominik Lorenz. Rombach, who led the team, had been angling to leave for months, two sources said, first threatening to resign last summer because of the fundraising failures. Others left over concerns about cash flow, as well as liabilities — including what four people described as Mostaque’s lax approach to ensuring that Stability products could not be used to produce child sexual abuse imagery. “Stability AI is committed to preventing the misuse of AI and prohibits the use of our image models and services for unlawful activity, including attempts to edit or create CSAM,” Ella Irwin, senior vice president of integrity, said in a statement. Newton-Rex told Forbes he resigned because he disagreed with Stability’s position that training AI on copyrighted work without consent is fair use. Melnicki and Penna declined to comment. Avrunin and Onder could not be reached for comment. None of the researchers responded to requests for comment. The Stable Diffusion researchers’ departure as a cohort says a lot about the state of Stability AI. The company’s researchers were widely viewed as its crown jewels, their work subsidized with a firehose of pricey compute power that was even extended to people outside the company. Martino Russi, an artificial intelligence researcher, told Forbes that though he was never formally employed by Stability, the company provided him a “staggering” amount of compute between January and April 2023 to play around with developing an AI video generator that Stability might someday use. “It was Candy Land or Coney Island,” said Russi, who estimates that his experiment, which was ultimately shelved, cost the company $2.5 million. Stable Diffusion was simultaneously Stability’s marquee product and its existential cash crisis. One current employee described it to Forbes as “a giant vacuum that absorbed everything: money, compute, people.” While the software was widely used, with Mostaque claiming downloads reaching into the hundreds of millions, Stability struggled to translate that wild success into revenue. Mostaque knew it could be done — peers at Databricks, Elastic and MongoDB had all turned a free product into a lucrative business — he just couldn’t figure out how. His first attempt was Stability’s API, which allowed paying customers to integrate Stable Diffusion into their own products. In early 2023, a handful of small companies, like art generator app NightCafe and presentation software startup Tome, signed on, according to four people with knowledge of the deals. But Stability’s poor account management services soured many, and in a matter of months NightCafe and Tome canceled their contracts, three people said. NightCafe founder Angus Russell told Forbes that his company switched to a competitor which “offered much cheaper inference costs and a broader service.” Tome did not respond to a request for comment. Meanwhile, Mostaque’s efforts to court larger companies like Samsung and Snapchat were failing, according to five people familiar with the effort. Canva, which was already one of the heaviest users of open-sourced Stable Diffusion, had multiple discussions with Stability, which was angling for a contract it hoped would generate several millions in annual revenue. But the deal never materialized, four sources said. “These three companies wanted and needed us,” one former employee told Forbes. “They would have been the perfect customers.” (Samsung, Snap and Canva declined to comment.) “It’s not that there was not an appetite to pay Stability — there were tons of companies that would have that wanted to,” the former employee said. “There was a huge opportunity and demand, but just a resistance to execution.” Mostaque’s other big idea was to provide governments with bespoke national AI models that would invigorate their economies and citizenry. “Emad envisions a world where AI through 100 national models serves not as a tool of the few, but as a benefactor to all promising to confront great adversaries, cancer, autism, and the sands of time itself,” the AI avatar of Aristotle said in his intro at the conference. Mostaque told several prospective customers that he could deliver such models within 60 days — an untenable timeline, according to two people in position to know. Stability attempted to develop a model for the Singaporean government over the protestation of employees who questioned its technical feasibility, three sources familiar with the effort told Forbes. But it couldn’t pull it off and Singapore never became a customer. (The government of Singapore confirmed it did not enter into a deal with Stability, but declined to answer additional questions.) As Stability careened from one new business idea to another, resources were abruptly reallocated and researchers reassigned. The whiplash shifts in a largely siloed organization demoralized and infuriated employees. “There were ‘urgent’ things, ‘urgent urgent’ things and ‘most urgent,’” one former employee complained. “None of these things seem important if everything is important.” Another former Stability executive was far more pointed in their assessment. “Emad is the most disorganized leader I have ever worked with in my career,” this person told Forbes. “He has no vision, and changes directions every week, often based on what he sees on Twitter.” In a video interview posted shortly before this story was published, Mostaque explained his leadership style: “I'm particularly great at taking creatives, developers, researchers, others, and achieving their full potential in designing systems. But I should not be dealing with, you know, HR and operations and business development and other elements. There are far better people than me to do that.” By December 2023, Stability had partially abandoned its open-source roots and announced that any commercial use of Stable Diffusion would cost customers at least $20 per month (non-commercial and research use of Stable Diffusion would remain free). But privately, Stability was considering a potentially more lucrative source of revenue: reselling the compute it was leasing from providers like AWS, according to six people familiar with the effort. Though it was essentially GPU arbitrage, Stability framed the strategy to investors as a “managed services” offering. Its damning October financial report projected optimistically that such an offering would bring in $139 million in 2024 — 98% of its revenue. Multiple employees at the time told Forbes they feared reselling compute, even if the company called it “managed services,” would violate the terms of Stability’s contract with AWS. Amazon declined to comment. “The line internally was that we are not reselling compute,” one former employee said. “This was some of the dirtiest feeling stuff.” Stability also discussed reselling a cluster of Nvidia A100 chips, leased via CoreWeave, to the venture capital firm Andreessen Horowitz, three sources said. “It was under the guise of managed services, but there wasn’t any management happening,” one of these people told Forbes. Andreessen Horowitz and CoreWeave declined to comment. Stability did not respond to questions about if it plans to continue this strategy now that Mostaque is out of the picture. Regardless, interim co-CEOs Wong and Laforte are on a tight timeline to clean up his mess. Board chairman Jim O’Shaughnessy said in a statement that he was confident the pair “will adeptly steer the company forward in developing and commercializing industry-leading generative AI products.” But burn continues to far outpace revenue. The Financial Times reported Friday that the company made $5.4 million of revenue in February, against $8 million in costs. Several sources said there are ongoing concerns about making payroll for the roughly 150 remaining employees. Leadership roles have gone vacant for months amid the disarray, leaving the company increasingly directionless. Meanwhile, a potentially catastrophic legal threat looms over the company: A trio of copyright infringement lawsuits brought by Getty Images and a group of artists in the U.S. and U.K., who claim Stability illegally used their art and photography to train the AI models powering Stable Diffusion. A London-based court has already rejected the company’s bid to throw out one of the lawsuits on the basis that none of its researchers were based in the U.K. And Stability’s claim that Getty’s Delaware lawsuit should be blocked because it's a U.K.-based company was rejected. (Stability did not respond to questions about the litigation.) AI-related copyright litigation “could go on for years,” according to Eric Goldman, a law professor at Santa Clara University. He told Forbes that though plaintiffs suing AI firms face an uphill battle overcoming the existing legal precedent on copyright infringement, the quantity of arguments available to make are virtually inexhaustible. “Like in military theory, if there’s a gap in your lines, that’s where the enemy pours through — if any one of those arguments succeeds, it could completely change the generative AI environment,” he said. “In some sense, generative AI as an industry has to win everything.” Stability, which had more than $100 million in the bank just a year and a half ago, is in a deep hole. Not only does it need more funding, it needs a viable business model — or a buyer with the vision and chops to make it successful in a fast-moving and highly competitive sector. At an all hands meeting this past Monday, Stability’s new leaders detailed a path forward. One point of emphasis: a plan to better manage resources and expenses, according to one person in attendance. It’s a start, but Mostaque’s meddling has left them with little runway to execute. His resignation, though, has given some employees hope. “A few people are 100% going to reconsider leaving after today,” said one current employee. “And the weird gloomy aura of hearing Emad talking nonsense for an hour is gone.” Shortly before Mostaque resigned, one current Stability executive told Forbes that they were optimistic his departure could make Stability appealing enough to receive a small investment or sale to a friendly party. “There are companies that have raised hundreds of millions of dollars that have much less intrinsic value than Stability,” the person said. “A white knight may still appear.”

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

#reddit #interview #juergen

0.765

hardmaru•This week

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.

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

EsotericaCapital•This week

[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.

#reddit #trends #power

[D] AI regulation: a review of NTIA's "AI Accountability Policy" doc

#reddit #regulation:#review

elehman839•This week

[D] AI regulation: a review of NTIA's "AI Accountability Policy" doc

How will governments respond to the rapid rise of AI? How can sensible regulation keep pace with AI technology? These questions interest many of us! One early US government response has come from the National Telecommunications and Information Administration (NTIA). Specifically, the NTIA published an "AI Accountability Policy Request for Comment" on April 11, 2023. I read the NTIA document carefully, and I'm sharing my observations here for others interested in AI regulation. You can, of course, read the original materials and form your own opinions. Moreover, you can share those opinions not only on this post, but also with the NTIA itself until June 12, 2023. As background, the NTIA (homepage, Wikipedia) consists of a few hundred people within the Department of Commerce. The official mission of the NTIA is "advising the President on telecommunications and information policy issues". Topics covered by NTIA include broadband internet access, spectrum management, internet health, and now artificial intelligence. I do not know whether the NTIA will ultimately drive thinking around AI regulation in the United States or they are just a spunky lot who got something on paper early. The NTIA document is not a specific policy proposal, but rather a thoughtful discussion of AI regulation, followed by a long list of questions on which the NTIA seeks input. This format seems appropriate right now, as we're all trying to make sense of a fast-changing world. The NTIA document leans heavily on two others: the Blueprint for an AI Bill of Rights from the White House Office of Science and Technology and the AI Risk Management Framework from the National Institute of Standards and Technology (NIST). Without going into these two in depth, even tiny snippets convey their differing audiences and flavors: White House Blueprint: "You should be protected from safe and ineffective systems." NIST Framework: "Risk refers to the composite measure of an event’s probability of occurring and the magnitude or degree of the consequences of the corresponding event." Now, turning back to the NTIA document itself, I'll comment on three aspects (1) scope, (2) problems addressed, and (3) solutions contemplated. Scope is critical to understanding the NTIA document, and is probably worth keeping in mind in all near-term discussion of AI regulation. Over the past several years, at least two different technologies have been called "AI". The document mentions both, but the emphasis is NOT on the one you're probably thinking about. In more detail: A few years ago, regulators began scrutinizing "automated decisions systems", which passed as "AI" in those ancient times. An example would be an ML model used by a bank to decide whether or not you get a loan. That model might take in all sorts of information about you, combine it in mysterious ML ways, and reject your loan request. Then you might wonder, "Did that system effectively use my address and name to deduce that I am black and then reject my loan request on the basis of race?" There is some evidence of that happening, and this seems like an injustice. So perhaps such systems should be audited and certified so people know this won't happen. This is the focus of the document. These days, AI more commonly refers to open-ended systems that can engage on a wide range of topics and approximate human intelligence. The document briefly mentions generative AI models, large language models, ChatGPT, and "foundational models" (sic), but this is not the focus. The passing mentions may obscure this, unfortunately. In my opinion, these two notions of "AI" are radically different, and many of the differences matter from a regulatory perspective. Yet NTIA lumps both under a sweeping definition of an "AI system" as "an engineered or machine-based system that can, for a given set of objectives, generate outputs such as predictions, recommendations, or decisions influencing real or virtual environments." (Hmm, this includes my Magic 8-Ball…) Keep scope in mind as we turn to the next aspect: the problems under discussion. Now, NTIA's goal is to solicit input, so considering a wide range of potential problems associated with AI makes sense. Consistent with that, the document refers to democratic values, civil rights, civil liberties, and privacy. And citing the NIST doc, NTIA vaguely notes "a wide range of potential AI risks". Also, AI systems should be "valid and reliable, safe, secure and resilient, accountable and transparent, explainable and interpretable, privacy-enhanced, and fair with their harmful bias managed". And they should call their mothers \every\ week. (Okay, I made that one up.) A few comments on this formulation of the problem. First, these concerns feel more applicable to older-style AI. This includes automated decisions systems, like for a bank loan or for a prison parole recommendation. Sure, I believe such systems should operate in ways consistent with our consensus societal values, and further regulation may be needed to achieve that. But, hello! There's also another, newer class of AI that poses additional challenges. And I don't see those discussed in the NTIA document. Such challenges might include: People losing jobs because AI takes their work. Ensuring malicious people don't use AI tools to wreak havoc on the world. Sorting out intellectual property issues around AI to ensure both rapid progress in the field and respect for creators' rights. Ensuring laws appropriately assign culpability to humans when AIs cause harm. Planning for an incident analogous to the first internet worm, where an AI goes rogue, wreaks some havoc, and everyone is shocked (before it happens 28,385 more times). Bottom line: when I cntrl-F the doc for "robotic overlords", I get zero hits. ZERO. This is why I now believe scope is so important when considering efforts to regulate AI: are we talking about old-school AI or 2023-era AI or what? Because they are pretty different. The last aspect I'll address is the solutions contemplated. Again, NTIA's goal is to stimulate discussion, not propose something specific. Nevertheless, there is a strong push in one particular direction: unlike, "robotic overlord", the word "audit" appears more than 100 times along with many instances of "assessment" and "certification". On one hand, this approach makes sense. Suppose you want to ensure that a bank loan system is fair, that a social media platform isn't spreading misinformation, that a search engine is returning accurate results, etc. Then someone, somewhere has to assess or audit that system and look for problems. That audit might be done by the creator of the system or a third-party auditing agency. Such audits could be incentivized by mandates, prizes, or shiny gold stars. The government might help by fostering development of auditing tools and data. The NTIA is open to all such possibilities and seeks input on how to proceed. On the other hand, this seems like a tactic best suited to automated decision systems operated by financial institutions, government agencies, and the like. Such formal processes seem a poor fit for the current AI wave. For example: Auditing will take time and money. That's something a bank might pay for a system that will run for years. For something fine-tuned over the weekend at a startup or by some guy living in his mother's basement, that's probably not going to happen. Auditing a straightforward decision system seems far easier than assessing an open-ended AI. Beyond basic practicality, the AI could be taught to lie when it senses an audit. Also, auditing procedures (like the NTIA doc itself) will presumably be online, which means that AIs will read them and could potentially respond. Most current ML models fix parameters after training, but I think we'll soon see some models whose parameters evolve as they engage with the world. Auditing such a system that varies continuously over time seems especially difficult. Auditing a foundation model probably tells you little about derivative models. A sweet-hearted model can surely be made into monster with moderate additional training; you don't need to teach the model new cognitive skills, just repurpose existing ones to new ends. More generally, auditing doesn't address many of my concerns about AI regulation (see list above). For example, auditing sort of assumes a basically responsible actor (bank, government agency, big tech company), but AI could be misused by malicious people who, naturally, will not seek a responsible outside assessment. In any case, for both old-school and modern AI, auditing is only one line of defense, and that's not enough. You can audit until you're blue in the face, stuff will still get through, and AI systems will still cause some harm. So what's the next line of defense? For example, is our legal system ready to sensibly assign culpability to humans for AI-related incidents? In summary, the critical problem with the NTIA document is that it creates a largely false appearance of US government engagement with the new class of AI technology. As a result, people could wrongly believe that the US government is already responding to the rise of AI, and fail to advocate for actual, effective engagement. That said, the NTIA document does address important issues around a prominent technology sometimes (formerly?) called "AI". Even there, however, the proposed approach (auditing) seems like an overly-fragile, single line of defense.

#reddit #interview #juergen

0.765

hardmaru•This week

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.

[N] How Stability AI’s Founder Tanked His Billion-Dollar Startup

forbes article: https://www.forbes.com/sites/kenrickcai/2024/03/29/how-stability-ais-founder-tanked-his-billion-dollar-startup/ archive no paywall: https://archive.is/snbeV How Stability AI’s Founder Tanked His Billion-Dollar Startup Mar 29, 2024 Stability AI founder Emad Mostaque took the stage last week at the Terranea Resort in Palos Verdes, California to roaring applause and an introduction from an AI-generated Aristotle who announced him as “a modern Prometheus” with “the astuteness of Athena and the vision of Daedalus.” “Under his stewardship, AI becomes the Herculean force poised to vanquish the twin serpents of illness and ailment and extend the olive branch of longevity,” the faux Aristotle proclaimed. “I think that’s the best intro I’ve ever had,” Mostaque said. But behind Mostaque's hagiographic introduction lay a grim and fast metastasizing truth. Stability, once one of AI’s buzziest startups, was floundering. It had been running out of money for months and Mostaque had been unable to secure enough additional funding. It had defaulted on payments to Amazon whose cloud service undergirded Stability’s core offerings. The star research team behind its flagship text-to-image generator Stable Diffusion had tendered their resignations just three days before — as Forbes would first report — and other senior leaders had issued him an ultimatum: resign, or we walk too. Still, onstage before a massive audience of peers and acolytes, Mostaque talked a big game. “AI is jet planes for the mind,” he opined. “AI is our collective intelligence. It's the human Colossus.” He claimed a new, faster version of the Stable Diffusion image generator released earlier this month could generate “200 cats with hats per second.” But later, when he was asked about Stability’s financial model, Mostaque fumbled. “I can’t say that publicly,” he replied. “But it’s going well. We’re ahead of forecast.” Four days later, Mostaque stepped down as CEO of Stability, as Forbes first reported. In a post to X, the service formerly known as Twitter, he claimed he’d voluntarily abdicated his role to decentralize “the concentration of power in AI.” But sources told Forbes that was hardly the case. Behind the scenes, Mostaque had fought to maintain his position and control despite mounting pressure externally and internally to step down. Company documents and interviews with 32 current and former employees, investors, collaborators and industry observers suggest his abrupt exit was the result of poor business judgment and wild overspending that undermined confidence in his vision and leadership, and ultimately kneecapped the company. Mostaque, through his attorneys, declined to comment on record on a detailed list of questions about the reporting in this story. But in an email to Forbes earlier this week he broadly disputed the allegations. “Nobody tells you how hard it is to be a CEO and there are better CEOs than me to scale a business,” he said in a statement. “I am not sure anyone else would have been able to build and grow the research team to build the best and most widely used models out there and I’m very proud of the team there. I look forward to moving onto the next problem to handle and hopefully move the needle.” In an emailed statement, Christian Laforte and Shan Shan Wong, the interim co-CEOs who replaced Mostaque, said, "the company remains focused on commercializing its world leading technology” and providing it “to partners across the creative industries." After starting Stability in 2019, Mostaque built the company into an early AI juggernaut by seizing upon a promising research project that would become Stable Diffusion and funding it into a business reality. The ease with which the software generated detailed images from the simplest text prompts immediately captivated the public: 10 million people used it on any given day, the company told Forbes in early 2023. For some true believers, Mostaque was a crucial advocate for open-source AI development in a space dominated by the closed systems of OpenAI, Google and Anthropic. But his startup’s rise to one of the buzziest in generative AI was in part built on a series of exaggerations and misleading claims, as Forbes first reported last year (Mostaque disputed some points at the time). And they continued after he raised $100 million at a $1 billion valuation just days after launching Stable Diffusion in 2022. His failure to deliver on an array of grand promises, like building bespoke AI models for nation states, and his decision to pour tens of millions into research without a sustainable business plan, eroded Stability’s foundations and jeopardized its future. "He was just giving shit away,” one former employee told Forbes. “That man legitimately wanted to transform the world. He actually wanted to train AI models for kids in Malawi. Was it practical? Absolutely not." By October 2023, Stability would have less than $4 million left in the bank, according to an internal memo prepared for a board meeting and reviewed by Forbes. And mounting debt, including months of overdue Amazon Web Services payments, had already left it in the red. To avoid legal penalties for skipping Americans staff’s payroll, the document explained, the London-based startup was considering delaying tax payments to the U.K. government. It was Stability’s armada of GPUs, the wildly powerful and equally expensive chips undergirding AI, that were so taxing the company’s finances. Hosted by AWS, they had long been one of Mostaque’s bragging points; he often touted them as one of the world’s 10 largest supercomputers. They were responsible for helping Stability’s researchers build and maintain one of the top AI image generators, as well as break important new ground on generative audio, video and 3D models. “Undeniably, Stability has continued to ship a lot of models,” said one former employee. “They may not have profited off of it, but the broader ecosystem benefitted in a huge, huge way.” But the costs associated with so much compute were now threatening to sink the company. According to an internal October financial forecast seen by Forbes, Stability was on track to spend $99 million on compute in 2023. It noted as well that Stability was “underpaying AWS bills for July (by $1M)” and “not planning to pay AWS at the end of October for August usage ($7M).” Then there were the September and October bills, plus $1 million owed to Google Cloud and $600,000 to GPU cloud data center CoreWeave. (Amazon, Google and CoreWeave declined to comment.) With an additional $54 million allocated to wages and operating expenses, Stability’s total projected costs for 2023 were $153 million. But according to its October financial report, its projected revenue for the calendar year was just $11 million. Stability was on track to lose more money per month than it made in an entire year. The company’s dire financial position had thoroughly soured Stability’s current investors, including Coatue, which had invested tens of millions in the company during its $101 million funding round in 2022. In the middle of 2023, Mostaque agreed to an independent audit after Coatue raised a series of concerns, according to a source with direct knowledge of the matter. The outcome of the investigation is unclear. Coatue declined to comment. Within a week of an early October board meeting where Mostaque shared that financial forecast, Lightspeed Venture Partners, another major investor, sent a letter to the board urging them to sell the company. The distressing numbers had “severely undermined” the firm’s confidence in Mostaque’s ability to lead the company. “In particular, we are surprised and deeply concerned by a cash position just now disclosed to us that is inconsistent with prior discussions on this topic,” Lightspeed’s general counsel Brett Nissenberg wrote in the letter, a copy of which was viewed by Forbes. “Lightspeed believes that the company is not likely financeable on terms that would assure the company’s long term sound financial position.” (Lightspeed declined a request for comment.) The calls for a sale led Stability to quietly begin looking for a buyer. Bloomberg reported in November that Stability approached AI startups Cohere and Jasper to gauge their interest. Stability denied this, and Jasper CEO Timothy Young did the same when reached for comment by Forbes. A Cohere representative declined to comment. But one prominent AI company confirmed that Mostaque’s representatives had reached out to them to test the waters. Those talks did not advance because “the numbers didn’t add up,” this person, who declined to be named due to the confidential nature of the talks, told Forbes. Stability also tried to court Samsung as a buyer, going so far as to redecorate its office in advance of a planned meeting with the Korean electronics giant. (Samsung said that it invested in Stability in 2023 and that it does not comment on M&A discussions.) Coatue had been calling for Mostaque’s resignation for months, according to a source with direct knowledge. But it and other investors were unable to oust him because he was the company’s majority shareholder. When they tried a different tact by rallying other investors to offer him a juicy equity package to resign, Mostaque refused, said two sources. By October, Coatue and Lightspeed had had enough. Coatue left the board and Lightspeed resigned its observer seat. “Emad infuriated our initial investors so much it’s just making it impossible for us to raise more money under acceptable terms,” one current Stability executive told Forbes. The early months of 2024 saw Stability’s already precarious position eroding further still. Employees were quietly laid off. Three people in a position to know estimated that at least 10% of staff were cut. And cash reserves continued to dwindle. Mostaque mentioned a lifeline at the October board meeting: $95 million in tentative funding from new investors, pending due diligence. But in the end, only a fraction of it was wired, two sources say, much of it from Intel, which Forbes has learned invested $20 million, a fraction of what was reported. (Intel did not return a request for comment by publication time.) Two hours after Forbes broke the news of Mostaque’s plans to step down as CEO, Stability issued a press release confirming his resignation. Chief operating officer Wong and chief technology officer Laforte have taken over in the interim. Mostaque, who said on X that he still owns a majority of the company, also stepped down from the board, which has now initiated a search for a permanent CEO. There is a lot of work to be done to turn things around, and very little time in which to do it. Said the current Stability executive, “There’s still a possibility of a turnaround story, but the odds drop by the day.” In July of 2023, Mostaque still thought he could pull it off. Halfway through the month, he shared a fundraising plan with his lieutenants. It was wildly optimistic, detailing the raise of $500 million in cash and another $750 million in computing facilities from marquee investors like Nvidia, Google, Intel and the World Bank (Nvidia and Google declined comment. Intel did not respond. The World Bank said it did not invest in Stability). In a Slack message reviewed by Forbes, Mostaque said Google was “willing to move fast” and the round was “likely to be oversubscribed.” It wasn’t. Three people with direct knowledge of these fundraising efforts told Forbes that while there was some interest in Stability, talks often stalled when it came time to disclose financials. Two of them noted that earlier in the year, Mostaque had simply stopped engaging with VCs who asked for numbers. Only one firm invested around that time: actor Ashton Kutcher’s Sound Ventures, which invested $35 million in the form of a convertible SAFE note during the second quarter, according to an internal document. (Sound Ventures did not respond to a request for comment.) And though he’d managed to score a meeting with Nvidia and its CEO Jensen Huang, it ended in disaster, according to two sources. “Under Jensen's microscopic questions, Emad just fell apart,” a source in position to know told Forbes. Huang quickly concluded Stability wasn’t ready for an investment from Nvidia, the sources said. Mostaque told Forbes in an email that he had not met with Huang since 2022, except to say “hello and what’s up a few times after.” His July 2023 message references a plan to raise $150 million from Nvidia. (Nvidia declined to comment.) After a June Forbes investigation citing more than 30 sources revealed Mostaque’s history of misleading claims, Mostaque struggled to raise funding, a Stability investor told Forbes. (Mostaque disputed the story at the time and called it "coordinated lies" in his email this week to Forbes). Increasingly, investors scrutinized his assertions and pressed for data. And Young, now the CEO of Jasper, turned down a verbal offer to be Stability’s president after reading the article, according to a source with direct knowledge of the matter. The collapse of the talks aggravated the board and other executives, who had hoped Young would compensate for the sales and business management skills that Mostaque lacked, according to four people in a position to know. (Young declined to comment.) When Stability’s senior leadership convened in London for the CogX conference in September, the financing had still not closed. There, a group of executives confronted Mostaque asking questions about the company’s cash position and runway, according to three people with direct knowledge of the incident. They did not get the clarity they’d hoped for. By October, Mostaque had reduced his fundraising target by more than 80%. The months that followed saw a steady drumbeat of departures — general counsel Adam Avrunin, vice presidents Mike Melnicki, Ed Newton-Rex and Joe Penna, chief people officer Ozden Onder — culminating in the demoralizing March exit of Stable Diffusion’s primary developers Robin Rombach, Andreas Blattmann, Patrick Esser and Dominik Lorenz. Rombach, who led the team, had been angling to leave for months, two sources said, first threatening to resign last summer because of the fundraising failures. Others left over concerns about cash flow, as well as liabilities — including what four people described as Mostaque’s lax approach to ensuring that Stability products could not be used to produce child sexual abuse imagery. “Stability AI is committed to preventing the misuse of AI and prohibits the use of our image models and services for unlawful activity, including attempts to edit or create CSAM,” Ella Irwin, senior vice president of integrity, said in a statement. Newton-Rex told Forbes he resigned because he disagreed with Stability’s position that training AI on copyrighted work without consent is fair use. Melnicki and Penna declined to comment. Avrunin and Onder could not be reached for comment. None of the researchers responded to requests for comment. The Stable Diffusion researchers’ departure as a cohort says a lot about the state of Stability AI. The company’s researchers were widely viewed as its crown jewels, their work subsidized with a firehose of pricey compute power that was even extended to people outside the company. Martino Russi, an artificial intelligence researcher, told Forbes that though he was never formally employed by Stability, the company provided him a “staggering” amount of compute between January and April 2023 to play around with developing an AI video generator that Stability might someday use. “It was Candy Land or Coney Island,” said Russi, who estimates that his experiment, which was ultimately shelved, cost the company $2.5 million. Stable Diffusion was simultaneously Stability’s marquee product and its existential cash crisis. One current employee described it to Forbes as “a giant vacuum that absorbed everything: money, compute, people.” While the software was widely used, with Mostaque claiming downloads reaching into the hundreds of millions, Stability struggled to translate that wild success into revenue. Mostaque knew it could be done — peers at Databricks, Elastic and MongoDB had all turned a free product into a lucrative business — he just couldn’t figure out how. His first attempt was Stability’s API, which allowed paying customers to integrate Stable Diffusion into their own products. In early 2023, a handful of small companies, like art generator app NightCafe and presentation software startup Tome, signed on, according to four people with knowledge of the deals. But Stability’s poor account management services soured many, and in a matter of months NightCafe and Tome canceled their contracts, three people said. NightCafe founder Angus Russell told Forbes that his company switched to a competitor which “offered much cheaper inference costs and a broader service.” Tome did not respond to a request for comment. Meanwhile, Mostaque’s efforts to court larger companies like Samsung and Snapchat were failing, according to five people familiar with the effort. Canva, which was already one of the heaviest users of open-sourced Stable Diffusion, had multiple discussions with Stability, which was angling for a contract it hoped would generate several millions in annual revenue. But the deal never materialized, four sources said. “These three companies wanted and needed us,” one former employee told Forbes. “They would have been the perfect customers.” (Samsung, Snap and Canva declined to comment.) “It’s not that there was not an appetite to pay Stability — there were tons of companies that would have that wanted to,” the former employee said. “There was a huge opportunity and demand, but just a resistance to execution.” Mostaque’s other big idea was to provide governments with bespoke national AI models that would invigorate their economies and citizenry. “Emad envisions a world where AI through 100 national models serves not as a tool of the few, but as a benefactor to all promising to confront great adversaries, cancer, autism, and the sands of time itself,” the AI avatar of Aristotle said in his intro at the conference. Mostaque told several prospective customers that he could deliver such models within 60 days — an untenable timeline, according to two people in position to know. Stability attempted to develop a model for the Singaporean government over the protestation of employees who questioned its technical feasibility, three sources familiar with the effort told Forbes. But it couldn’t pull it off and Singapore never became a customer. (The government of Singapore confirmed it did not enter into a deal with Stability, but declined to answer additional questions.) As Stability careened from one new business idea to another, resources were abruptly reallocated and researchers reassigned. The whiplash shifts in a largely siloed organization demoralized and infuriated employees. “There were ‘urgent’ things, ‘urgent urgent’ things and ‘most urgent,’” one former employee complained. “None of these things seem important if everything is important.” Another former Stability executive was far more pointed in their assessment. “Emad is the most disorganized leader I have ever worked with in my career,” this person told Forbes. “He has no vision, and changes directions every week, often based on what he sees on Twitter.” In a video interview posted shortly before this story was published, Mostaque explained his leadership style: “I'm particularly great at taking creatives, developers, researchers, others, and achieving their full potential in designing systems. But I should not be dealing with, you know, HR and operations and business development and other elements. There are far better people than me to do that.” By December 2023, Stability had partially abandoned its open-source roots and announced that any commercial use of Stable Diffusion would cost customers at least $20 per month (non-commercial and research use of Stable Diffusion would remain free). But privately, Stability was considering a potentially more lucrative source of revenue: reselling the compute it was leasing from providers like AWS, according to six people familiar with the effort. Though it was essentially GPU arbitrage, Stability framed the strategy to investors as a “managed services” offering. Its damning October financial report projected optimistically that such an offering would bring in $139 million in 2024 — 98% of its revenue. Multiple employees at the time told Forbes they feared reselling compute, even if the company called it “managed services,” would violate the terms of Stability’s contract with AWS. Amazon declined to comment. “The line internally was that we are not reselling compute,” one former employee said. “This was some of the dirtiest feeling stuff.” Stability also discussed reselling a cluster of Nvidia A100 chips, leased via CoreWeave, to the venture capital firm Andreessen Horowitz, three sources said. “It was under the guise of managed services, but there wasn’t any management happening,” one of these people told Forbes. Andreessen Horowitz and CoreWeave declined to comment. Stability did not respond to questions about if it plans to continue this strategy now that Mostaque is out of the picture. Regardless, interim co-CEOs Wong and Laforte are on a tight timeline to clean up his mess. Board chairman Jim O’Shaughnessy said in a statement that he was confident the pair “will adeptly steer the company forward in developing and commercializing industry-leading generative AI products.” But burn continues to far outpace revenue. The Financial Times reported Friday that the company made $5.4 million of revenue in February, against $8 million in costs. Several sources said there are ongoing concerns about making payroll for the roughly 150 remaining employees. Leadership roles have gone vacant for months amid the disarray, leaving the company increasingly directionless. Meanwhile, a potentially catastrophic legal threat looms over the company: A trio of copyright infringement lawsuits brought by Getty Images and a group of artists in the U.S. and U.K., who claim Stability illegally used their art and photography to train the AI models powering Stable Diffusion. A London-based court has already rejected the company’s bid to throw out one of the lawsuits on the basis that none of its researchers were based in the U.K. And Stability’s claim that Getty’s Delaware lawsuit should be blocked because it's a U.K.-based company was rejected. (Stability did not respond to questions about the litigation.) AI-related copyright litigation “could go on for years,” according to Eric Goldman, a law professor at Santa Clara University. He told Forbes that though plaintiffs suing AI firms face an uphill battle overcoming the existing legal precedent on copyright infringement, the quantity of arguments available to make are virtually inexhaustible. “Like in military theory, if there’s a gap in your lines, that’s where the enemy pours through — if any one of those arguments succeeds, it could completely change the generative AI environment,” he said. “In some sense, generative AI as an industry has to win everything.” Stability, which had more than $100 million in the bank just a year and a half ago, is in a deep hole. Not only does it need more funding, it needs a viable business model — or a buyer with the vision and chops to make it successful in a fast-moving and highly competitive sector. At an all hands meeting this past Monday, Stability’s new leaders detailed a path forward. One point of emphasis: a plan to better manage resources and expenses, according to one person in attendance. It’s a start, but Mostaque’s meddling has left them with little runway to execute. His resignation, though, has given some employees hope. “A few people are 100% going to reconsider leaving after today,” said one current employee. “And the weird gloomy aura of hearing Emad talking nonsense for an hour is gone.” Shortly before Mostaque resigned, one current Stability executive told Forbes that they were optimistic his departure could make Stability appealing enough to receive a small investment or sale to a friendly party. “There are companies that have raised hundreds of millions of dollars that have much less intrinsic value than Stability,” the person said. “A white knight may still appear.”

[R] Evaluating Video Models on Impossible Scenarios: A Benchmark for Generation and Understanding of Counterfactual Videos

Successful-Western27•This week

[R] Evaluating Video Models on Impossible Scenarios: A Benchmark for Generation and Understanding of Counterfactual Videos

IPV-Bench: Evaluating Video Generation Models with Physically Impossible Scenarios Researchers have created a new benchmark called IPV-Bench to evaluate how well video generation models understand basic physics and logic. This benchmark contains 1,000 carefully crafted prompts that test models on their ability to handle physically impossible scenarios across 9 categories including gravity violations, object permanence issues, and logical contradictions. The key methodology included: Testing models with both "create impossible" prompts (asking for impossibilities) and "avoid impossible" prompts (requesting physically plausible videos) Evaluating videos through both automated metrics and human assessment Testing across multiple state-of-the-art models including Sora, Morph-E, WALT, Show-1, Gen-2, Runway, Pika, and LaVie Developing a detailed taxonomy of impossible physics scenarios Main findings: Current SOTA models produce physically impossible content 20-40% of the time even when explicitly asked to follow physics laws Performance was worst on "change impossibilities" and "contact impossibilities" (~50% accuracy) Different models show different "impossibility profiles" - making distinct types of physical reasoning errors Strong text understanding doesn't guarantee strong physical reasoning Human evaluators easily identified these impossibilities, highlighting the gap between AI and human understanding I think this research reveals a fundamental limitation in current video generation systems - they lack the intuitive physics understanding that humans develop naturally. This matters significantly for applications where physical plausibility is important, like simulation, education, or training robotics systems. The benchmark provides a systematic way to measure progress in this area, which will be crucial as these models become more widely deployed. The taxonomy they've developed is particularly useful as it gives us a framework for thinking about different types of physical reasoning failures. I suspect we'll see this benchmark become an important tool for improving the next generation of video models. TLDR: IPV-Bench is a new benchmark testing video models' understanding of physical impossibilities. Current models frequently generate physically impossible content even when instructed not to, showing they lack true understanding of how the physical world works. Full summary is here. Paper here.

#reddit #evaluating #video

0.333

[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

#reddit #misuse #deep

madredditscientist•This week

[D] AI Agents: too early, too expensive, too unreliable

Reference: Full blog post There has been a lot of hype about the promise of autonomous agent-based LLM workflows. By now, all major LLMs are capable of interacting with external tools and functions, letting the LLM perform sequences of tasks automatically. But reality is proving more challenging than anticipated. The WebArena leaderboard, which benchmarks LLMs agents against real-world tasks, shows that even the best-performing models have a success rate of only 35.8%. Challenges in Practice After seeing many attempts to AI agents, I believe it's too early, too expensive, too slow, too unreliable. It feels like many AI agent startups are waiting for a model breakthrough that will start the race to productize agents. Reliability: As we all know, LLMs are prone to hallucinations and inconsistencies. Chaining multiple AI steps compounds these issues, especially for tasks requiring exact outputs. Performance and costs: GPT-4o, Gemini-1.5, and Claude Opus are working quite well with tool usage/function calling, but they are still slow and expensive, particularly if you need to do loops and automatic retries. Legal concerns: Companies may be held liable for the mistakes of their agents. A recent example is Air Canada being ordered to pay a customer who was misled by the airline's chatbot. User trust: The "black box" nature of AI agents and stories like the above makes it hard for users to understand and trust their outputs. Gaining user trust for sensitive tasks involving payments or personal information will be hard (paying bills, shopping, etc.). Real-World Attempts Several startups are tackling the AI agent space, but most are still experimental or invite-only: adept.ai - $350M funding, but access is still very limited MultiOn - funding unknown, their API-first approach seems promising HypeWrite - $2.8M funding, started with an AI writing assistant and expanded into the agent space minion.ai - created some initial buzz but has gone quiet now, waitlist only Only MultiOn seems to be pursuing the "give it instructions and watch it go" approach, which is more in line with the promise of AI agents. All others are going down the record-and-replay RPA route, which may be necessary for reliability at this stage. Large players are also bringing AI capabilities to desktops and browsers, and it looks like we'll get native AI integrations on a system level: OpenAI announced their Mac desktop app that can interact with the OS screen. At Google I/O, Google demonstrated Gemini automatically processing a shopping return. Microsoft announced Copilot Studio, which will let developers build AI agent bots. Screenshot Screenshot These tech demos are impressive, but we'll see how well these agent capabilities will work when released publicly and tested against real-world scenarios instead of hand-picked demo cases. The Path Forward AI agents overhyped and it's too early. However, the underlying models continue to advance quickly, and we can expect to see more successful real-world applications. Instead of trying to have one large general purpose agent that is hard to control and test, we can use many smaller agents that basically just pick the right strategy for a specific sub-task in our workflows. These "agents" can be thought of as medium-sized LLM prompts with a) context and b) a set of functions available to call. The most promising path forward likely looks like this: Narrowly scoped, well testable automations that use AI as an augmentation tool rather than pursuing full autonomy Human-in-the-loop approaches that keep humans involved for oversight and handling edge cases Setting realistic expectations about current capabilities and limitations By combining tightly constrained agents, good evaluation data, human-in-the-loop oversight, and traditional engineering methods, we can achieve reliably good results for automating medium-complex tasks. Will AI agents automate tedious repetitive work, such as web scraping, form filling, and data entry? Yes, absolutely. Will AI agents autonomously book your vacation without your intervention? Unlikely, at least in the near future.

#reddit #agents:#early,

The delicate balance of building an online community business

#reddit #delicate #balance

0.895

matthewbarby•This week

The delicate balance of building an online community business

Hey /r/Entrepreneur 👋 Just under two years ago I launched an online community business called Traffic Think Tank with two other co-founders, Nick Eubanks and Ian Howells. As a Traffic Think Tank customer you (currently) pay $119 a month to get access to our online community, which is run through Slack. The community is focused on helping you learn various aspects of marketing, with a particular focus on search engine optimization (SEO). Alongside access to the Slack community, we publish new educational video content from outside experts every week that all customers have access to. At the time of writing, Traffic Think Tank has around 650 members spanning across 17 of the 24 different global time zones. I was on a business trip over in Sydney recently, and during my time there I met up with some of our Australia-based community members. During dinner I was asked by several of them how the idea for Traffic Think Tank came about and what steps we took to validate that the idea was worth pursuing. This is what I told them… How it all began It all started with a personal need. Nick, an already successful entrepreneur and owner of a marketing agency, had tested out an early version Traffic Think Tank in early 2017. He offered real-time consulting for around ten customers that he ran from Slack. He would publish some educational videos and offer his advice on projects that the members were running. The initial test went well, but it was tough to maintain on his own and he had to charge a fairly high price to make it worth his time. That’s when he spoke to me and Ian about turning this idea into something much bigger. Both Ian and I offered something slightly different to Nick. We’ve both spent time in senior positions at marketing agencies, but currently hold senior director positions in 2,000+ public employee companies (HubSpot and LendingTree). Alongside this, as a trio we could really ramp up the quality and quantity of content within the community, spread out the administrative workload and just generally have more resources to throw at getting this thing off the ground. Admittedly, Nick was much more optimistic about the potential of Traffic Think Tank – something I’m very thankful for now – whereas Ian and I were in the camp of “you’re out of your mind if you think hundreds of people are going to pay us to be a part of a Slack channel”. To validate the idea at scale, we decided that we’d get an initial MVP of the community up and running with a goal of reaching 100 paying customers in the first six months. If we achieved that, we’d validated that it was a viable business and we would continue to pursue it. If not, we’d kill it. We spent the next month building out the initial tech stack that enabled us to accept payments, do basic user management to the Slack channel, and get a one-page website up and running with information on what Traffic Think Tank was all about. After this was ready, we doubled down on getting some initial content created for members – I mean, we couldn’t have people just land in an empty Slack channel, could we? We created around ten initial videos, 20 or so articles and then some long threads full of useful information within the Slack channel so that members would have some content to pour into right from the beginning. Then, it was time to go live. The first 100 customers Fortunately, both Nick and I had built a somewhat substantial following in the SEO space over the previous 5-10 years, so we at least had a large email list to tap into (a total of around 40,000 people). We queued up some launch emails, set an initial price of $99 per month and pressed send. [\[LINK\] The launch email I sent to my subscribers announcing Traffic Think Tank](https://mailchi.mp/matthewbarby/future-of-marketing-1128181) What we didn’t expect was to sell all of the initial 100 membership spots in the first 72 hours. “Shit. What do we do now? Are we ready for this many people? Are we providing them with enough value? What if something breaks in our tech stack? What if they don’t like the content? What if everyone hates Slack?” All of these were thoughts running through my head. This brings me to the first great decision we made: we closed down new membership intake for 3 months so that we could focus completely on adding value to the first cohort of users. The right thing at the right time SEO is somewhat of a dark art to many people that are trying to learn about it for the first time. There’s hundreds of thousands (possibly millions) of articles and videos online that talk about how to do SEO. Some of it’s good advice; a lot of it is very bad advice. Add to this that the barrier to entry of claiming to be an “expert” in SEO is practically non-existent and you have a recipe for disaster. This is why, for a long time, individuals involved in SEO have flocked in their masses to online communities for information and to bounce ideas off of others in the space. Forums like SEObook, Black Hat World, WickedFire, Inbound.org, /r/BigSEO, and many more have, at one time, been called home by many SEOs. In recent times, these communities have either been closed down or just simply haven’t adapted to the changing needs of the community – one of those needs being real-time feedback on real-world problems. The other big need that we all spotted and personally had was the ability to openly share the things that are working – and the things that aren’t – in SEO within a private forum. Not everyone wanted to share their secret sauce with the world. One of the main reasons we chose Slack as the platform to run our community on was the fact that it solved these two core needs. It gave the ability to communicate in real-time across multiple devices, and all of the information shared within it was outside of the public domain. The other problem that plagued a lot of these early communities was spam. Most of them were web-based forums that were free to access. That meant they became a breeding ground for people trying to either sell their services or promote their own content – neither of which is conducive to building a thriving community. This was our main motivation for charging a monthly fee to access Traffic Think Tank. We spent a lot of time thinking through pricing. It needed to be enough money that people would be motivated to really make use of their membership and act in a way that’s beneficial to the community, but not too much money that it became cost prohibitive to the people that would benefit from it the most. Considering that most of our members would typically spend between $200-800 per month on SEO software, $99 initially felt like the perfect balance. Growing pains The first three months of running the community went by without any major hiccups. Members were incredibly patient with us, gave us great feedback and were incredibly helpful and accommodating to other members. Messages were being posted every day, with Nick, Ian and myself seeding most of the engagement at this stage. With everything going smoothly, we decided that it was time to open the doors to another intake of new members. At this point we’d accumulated a backlog of people on our waiting list, so we knew that simply opening our doors would result in another large intake. Adding more members to a community has a direct impact on the value that each member receives. For Traffic Think Tank in particular, the value for members comes from three areas: The ability to have your questions answered by me, Nick and Ian, as well as other members of the community. The access to a large library of exclusive content. The ability to build connections with the wider community. In the early stages of membership growth, there was a big emphasis on the first of those three points. We didn’t have an enormous content library, nor did we have a particularly large community of members, so a lot of the value came from getting a lot of one-to-one time with the community founders. [\[IMAGE\] Screenshot of engagement within the Traffic Think Tank Slack community](https://cdn.shortpixel.ai/client/qglossy,retimg,w_1322/https://www.matthewbarby.com/wp-content/uploads/2019/08/Community-Engagement-in-Traffic-Think-Tank.png) The good thing about having 100 members was that it was just about feasible to give each and every member some one-to-one time within the month, which really helped us to deliver those moments of delight that the community needed early on. Two-and-a-half months after we launched Traffic Think Tank, we opened the doors to another 250 people, taking our total number of members to 350. This is where we experienced our first growing pains. Our original members had become used to being able to drop us direct messages and expect an almost instant response, but this wasn’t feasible anymore. There were too many people, and we needed to create a shift in behavior. We needed more value to come from the community engaging with one another or we’d never be able to scale beyond this level. We started to really pay attention to engagement metrics; how many people were logging in every day, and of those, how many were actually posting messages within public channels. We asked members that were logging in a lot but weren’t posting (the “lurkers”) why that was the case. We also asked the members that engaged in the community the most what motivated them to post regularly. We learned a lot from doing this. We found that the large majority of highly-engaged members had much more experience in SEO, whereas most of the “lurkers” were beginners. This meant that most of the information being shared in the community was very advanced, with a lot of feedback from the beginners in the group being that they “didn’t want to ask a stupid question”. As managers of the community, we needed to facilitate conversations that catered to all of our members, not just those at a certain level of skill. To tackle this problem, we created a number of new channels that had a much deeper focus on beginner topics so novice members had a safe place to ask questions without judgment. We also started running live video Q&As each month where we’d answer questions submitted by the community. This gave our members one-on-one time with me, Nick and Ian, but spread the value of these conversations across the whole community rather than them being hidden within private messages. As a result of these changes, we found that the more experienced members in the community were really enjoying sharing their knowledge with those with less experience. The number of replies within each question thread was really starting to increase, and the community started to shift away from just being a bunch of threads created by me, Nick and Ian to a thriving forum of diverse topics compiled by a diverse set of individuals. This is what we’d always wanted. A true community. It was starting to happen. [\[IMAGE\] Chart showing community engagement vs individual member value](https://cdn.shortpixel.ai/client/qglossy,retimg,w_1602/https://www.matthewbarby.com/wp-content/uploads/2019/08/Community-Engagement-Balance-Graph.jpg) At the same time, we started to realize that we’ll eventually reach a tipping point where there’ll be too much content for us to manage and our members to engage with. When we reach this point, the community will be tough to follow and the quality of any given post will go down. Not only that, but the community will become increasingly difficult to moderate. We’re not there yet, but we recognize that this will come, and we’ll have to adjust our model again. Advocating advocacy As we started to feel more comfortable about the value that members were receiving, we made the decision to indefinitely open for new members. At the same time, we increased the price of membership (from $99 a month to $119) in a bid to strike the right balance between profitability as a business and to slow down the rate at which we were reaching the tipping point of community size. We also made the decision to repay all of our early adopters by grandfathering them in to the original pricing – and committing to always do this in the future. Despite the price increase, we saw a continued flow of new members come into the community. The craziest part about this was that we were doing practically no marketing activities to encourage new members– this was all coming from word of mouth. Our members were getting enough value from the community that they were recommending it to their friends, colleagues and business partners. The scale at which this was happening really took us by surprise and it told us one thing very clearly: delivering more value to members resulted in more value being delivered to the business. This is a wonderful dynamic to have because it perfectly aligns the incentives on both sides. We’d said from the start that we wouldn’t sacrifice value to members for more revenue – this is something that all three of us felt very strongly about. First and foremost, we wanted to create a community that delivered value to its members and was run in a way that aligned with our values as people. If we could find a way to stimulate brand advocacy, while also tightening the bonds between all of our individual community members, we’d be boosting both customer retention and customer acquisition in the same motion. This became our next big focus. [\[TWEET\] Adam, one of our members wore his Traffic Think Tank t-shirt in the Sahara desert](https://twitter.com/AdamGSteele/status/1130892481099382784) We started with some simple things: We shipped out Traffic Think Tank branded T-shirts to all new members. We’d call out each of the individuals that would submit questions to our live Q&A sessions and thank them live on air. We set up a new channel that was dedicated to sharing a quick introduction to who you are, what you do and where you’re based for all new members. We’d created a jobs channel and a marketplace for selling, buying and trading services with other members. Our monthly “blind dates” calls were started where you’d be randomly grouped with 3-4 other community members so that you could hop on a call to get to know each other better. The Traffic Think Tank In Real Life (IRL)* channel was born, which enabled members to facilitate in-person meetups with each other. In particular, we saw that as members started to meet in person or via calls the community itself was feeling more and more like a family. It became much closer knit and some members started to build up a really positive reputation for being particularly helpful to other members, or for having really strong knowledge in a specific area. [\[TWEET\] Dinner with some of the Traffic Think Tank members in Brighton, UK](https://twitter.com/matthewbarby/status/1117175584080134149) Nick, Ian and I would go out of our way to try and meet with members in real life wherever we could. I was taken aback by how appreciative people were for us doing this, and it also served as an invaluable way to gain honest feedback from members. There was another trend that we’d observed that we didn’t really expect to happen. More and more members were doing business with each another. We’ve had people find new jobs through the community, sell businesses to other members, launch joint ventures together and bring members in as consultants to their business. This has probably been the most rewarding thing to watch, and it was clear that the deeper relationships that our members were forming were resulting in an increased level of trust to work with each other. We wanted to harness this and take it to a new level. This brought us to arguably the best decision we’ve made so far running Traffic Think Tank… we were going to run a big live event for our members. I have no idea what I’m doing It’s the first week of January 2019 and we’re less than three weeks away from Traffic Think Tank LIVE, our first ever in-person event hosting 150 people, most of which are Traffic Think Tank members. It's like an ongoing nightmare I can’t wake up from. That was Nick’s response in our private admin channel to myself and Ian when I asked if they were finding the run-up to the event as stressful as I was. I think that all three of us were riding on such a high from how the community was growing that we felt like we could do anything. Running an event? How hard can it be? Well, turns out it’s really hard. We had seven different speakers flying over from around the world to speak at the event, there was a pre- and after event party, and we’d planned a charity dinner where we would take ten attendees (picked at random via a raffle) out for a fancy meal. Oh, and Nick, Ian and I were hosting a live Q&A session on stage. It wasn’t until precisely 48 hours before the event that we’d realized we didn’t have any microphones, nor had a large amount of the swag we’d ordered arrived. Plus, a giant storm had hit Philly causing a TON of flight cancellations. Perfect. Just perfect. This was honestly the tip of the iceberg. We hadn’t thought about who was going to run the registration desk, who would be taking photos during the event and who would actually field questions from the audience while all three of us sat on stage for our live Q&A panel. Turns out that the answer to all of those questions were my wife, Laura, and Nick’s wife, Kelley. Thankfully, they were on hand to save our asses. The weeks running up to the event were honestly some of the most stressful of my life. We sold around 50% of our ticket allocation within the final two weeks before the event. All of the event organizers told us this would happen, but did we believe them? Hell no! Imagine having two weeks until the big day and as it stood half of the room would be completely empty. I was ready to fly most of my extended family over just to make it look remotely busy. [\[IMAGE\] One of our speakers, Ryan Stewart, presenting at Traffic Think Tank LIVE](https://cdn.shortpixel.ai/client/qglossy,retimg,w_1920/https://www.matthewbarby.com/wp-content/uploads/2019/08/Traffic-Think-Tank-LIVE-Ryan-Presenting.jpg) Thankfully, if all came together. We managed to acquire some microphones, the swag arrived on the morning of the event, all of our speakers were able to make it on time and the weather just about held up so that our entire allocation of ticket holders was able to make it to the event. We pooled together and I’m proud to say that the event was a huge success. While we made a substantial financial loss on the event itself, January saw a huge spike in new members, which more than recouped our losses. Not only that, but we got to hang out with a load of our members all day while they said really nice things about the thing we’d built. It was both exhausting and incredibly rewarding. Bring on Traffic Think Tank LIVE 2020! (This time we’re hiring an event manager...) The road ahead Fast forward to today (August 2019) and Traffic Think Tank has over 650 members. The biggest challenges that we’re tackling right now include making sure the most interesting conversations and best content surfaces to the top of the community, making Slack more searchable (this is ultimately one of its flaws as a platform) and giving members a quicker way to find the exclusive content that we create. You’ll notice there’s a pretty clear theme here. In the past 30 days, 4,566 messages were posted in public channels inside Traffic Think Tank. If you add on any messages posted inside private direct messages, this number rises to 21,612. That’s a lot of messages. To solve these challenges and enable further scale in the future, we’ve invested a bunch of cash and our time into building out a full learning management system (LMS) that all members will get access to alongside the Slack community. The LMS will be a web-based portal that houses all of the video content we produce. It will also provide an account admin section where users can update or change their billing information (they have to email us to do this right now, which isn’t ideal), a list of membership perks and discounts with our partners, and a list of links to some of the best threads within Slack – when clicked, these will drop you directly into Slack. [\[IMAGE\] Designs for the new learning management system (LMS)](https://cdn.shortpixel.ai/client/qglossy,retimg,w_2378/https://www.matthewbarby.com/wp-content/uploads/2019/08/Traffic-Think-Tank-LMS.png) It’s not been easy, but we’re 95% of the way through this and I’m certain that it will have a hugely positive impact on the experience for our members. Alongside this we hired a community manager, Liz, who supports with any questions that our members have, coordinates with external experts to arrange webinars for the community, helps with new member onboarding, and has tightened up some of our processes around billing and general accounts admin. This was a great decision. Finally, we’ve started planning next year’s live event, which we plan to more than double in size to 350 attendees, and we decided to pick a slightly warmer location in Miami this time out. Stay tuned for me to have a complete meltdown 3 weeks from the event. Final thoughts When I look back on the journey we’ve had so far building Traffic Think Tank, there’s one very important piece to this puzzle that’s made all of this work that I’ve failed to mention so far: co-founder alignment. Building a community is a balancing act that relies heavily on those in charge being completely aligned. Nick, Ian and I completely trust each other and more importantly, are philosophically aligned on how we want to run and grow the community. If we didn’t have this, the friction between us could tear apart the entire community. Picking the right people to work with is important in any company, but when your business is literally about bringing people together, there’s no margin for error here. While I’m sure there will be many more challenges ahead, knowing that we all trust each other to make decisions that fall in line with each of our core values makes these challenges dramatically easier to overcome. Finally, I’d like to thank all of our members for making the community what it is today – it’d be nothing without you and I promise that we’ll never take that for granted.  I originally posted this on my blog here. Welcoming all of your thoughts, comments, questions and I'll do my best to answer them :)

How a Small Startup in Asia Secured a Contract with the US Department of Homeland Security

Royal_Rest8409•This week

How a Small Startup in Asia Secured a Contract with the US Department of Homeland Security

Uzair Javaid, a Ph.D. with a passion for data privacy, co-founded Betterdata to tackle one of AI's most pressing challenges: protecting privacy while enabling innovation. Recently, Betterdata secured a lucrative contract with the US Department of Homeland Security, 1 of only 4 companies worldwide to do so and the only one in Asia. Here's how he did it: The Story So what's your story? I grew up in Peshawar, Pakistan, excelling in coding despite studying electrical engineering. Inspired by my professors, I set my sights on studying abroad and eventually earned a Ph.D. scholarship at NUS Singapore, specializing in data security and privacy. During my research, I ethically hacked Ethereum and published 15 papers—three times the requirement. While wrapping up my Ph.D., I explored startup ideas and joined Entrepreneur First, where I met Kevin Yee. With his expertise in generative models and mine in privacy, we founded Betterdata. Now, nearly three years in, we’ve secured a major contract with the U.S. Department of Homeland Security—one of only four companies globally and the only one from Asia. The Startup In a nutshell, what does your startup do? Betterdata is a startup that uses AI and synthetic data generation to address two major challenges: data privacy and the scarcity of high-quality data for training AI models. By leveraging generative models and privacy-enhancing technologies, Betterdata enables businesses, such as banks, to use customer data without breaching privacy regulations. The platform trains AI on real data, learns its patterns, and generates synthetic data that mimics the real thing without containing any personal or sensitive information. This allows companies to innovate and develop AI solutions safely and ethically, all while tackling the growing need for diverse, high-quality data in AI development. How did you conduct ideation and validation for your startup? The initial idea for Betterdata came from personal experience. During my Ph.D., I ethically hacked Ethereum’s blockchain, exposing flaws in encryption-based data sharing. This led me to explore AI-driven deep synthesis technology—similar to deepfakes but for structured data privacy. With GDPR impacting 28M+ businesses, I saw a massive opportunity to help enterprises securely share data while staying compliant. To validate the idea, I spoke to 50 potential customers—a number that strikes the right balance. Some say 100, but that’s impractical for early-stage founders. At 50, patterns emerge: if 3 out of 10 mention the same problem, and this repeats across 50, you have 10–15 strong signals, making it a solid foundation for an MVP. Instead of outbound sales, which I dislike, we used three key methods: Account-Based Marketing (ABM)—targeting technically savvy users with solutions for niche problems, like scaling synthetic data for banks. Targeted Content Marketing—regular customer conversations shaped our thought leadership and outreach. Raising Awareness Through Partnerships—collaborating with NUS, Singapore’s PDPC, and Plug and Play to build credibility and educate the market. These strategies attracted serious customers willing to pay, guiding Betterdata’s product development and market fit. How did you approach the initial building and ongoing product development? In the early stages, we built synthetic data generation algorithms and a basic UI for proof-of-concept, using open-source datasets to engage with banks. We quickly learned that banks wouldn't share actual customer data due to privacy concerns, so we had to conduct on-site installations and gather feedback to refine our MVP. Through continuous consultation with customers, we discovered real enterprise data posed challenges, such as missing values, which led us to adapt our prototype accordingly. This iterative approach of listening to customer feedback and observing their usage allowed us to improve our product, enhance UX, and address unmet needs while building trust and loyalty. Working closely with our customers also gives us a data advantage. Our solution’s effectiveness depends on customer data, which we can't fully access, but bridging this knowledge gap gives us a competitive edge. The more customers we test on, the more our algorithms adapt to diverse use cases, making it harder for competitors to replicate our insights. My approach to iteration is simple: focus solely on customer feedback and ignore external noise like trends or advice. The key question for the team is: which customer is asking for this feature or solution? As long as there's a clear answer, we move forward. External influences, such as AI hype, often bring more confusion than clarity. True long-term success comes from solving real customer problems, not chasing trends. Customers may not always know exactly what they want, but they understand their problems. Our job is to identify these problems and solve them in innovative ways. While customers may suggest specific features, we stay focused on solving the core issue rather than just fulfilling their exact requests. The idea aligns with the quote often attributed to Henry Ford: "If I asked people what they wanted, they would have said faster horses." The key is understanding their problems, not just taking requests at face value. How do you assess product-market fit? To assess product-market fit, we track two key metrics: Customers' Willingness to Pay: We measure both the quantity and quality of meetings with potential customers. A high number of meetings with key decision-makers signals genuine interest. At Betterdata, we focused on getting meetings with people in banks and large enterprises to gauge our product's resonance with the target market. How Much Customers Are Willing to Pay: We monitor the price customers are willing to pay, especially in the early stages. For us, large enterprises, like banks, were willing to pay a premium for our synthetic data platform due to the growing need for privacy tech. This feedback guided our product refinement and scaling strategy. By focusing on these metrics, we refined our product and positioned it for scaling. What is your business model? We employ a structured, phase-driven approach for out business model, as a B2B startup. I initially struggled with focusing on the core value proposition in sales, often becoming overly educational. Eventually, we developed a product roadmap with models that allowed us to match customer needs to specific offerings and justify our pricing. Our pricing structure includes project-based pilots and annual contracts for successful deployments. At Betterdata, our customer engagement unfolds across three phases: Phase 1: Trial and Benchmarking \- We start with outreach and use open-source datasets to showcase results, offering customers a trial period to evaluate the solution. Phase 2: Pilot or PoC \- After positive trial results, we conduct a PoC or pilot using the customer’s private data, with the understanding that successful pilots lead to an annual contract. Phase 3: Multi-Year Contracts \- Following a successful pilot, we transition to long-term commercial contracts, focusing on multi-year agreements to ensure stability and ongoing partnerships. How do you do marketing for your brand? We take a non-conventional approach to marketing, focusing on answering one key question: Which customers are willing to pay, and how much? This drives our messaging to show how our solution meets their needs. Our strategy centers around two main components: Building a network of lead magnets \- These are influential figures like senior advisors, thought leaders, and strategic partners. Engaging with institutions like IMDA, SUTD, and investors like Plug and Play helps us gain access to the right people and foster warm introductions, which shorten our sales cycle and ensure we’re reaching the right audience. Thought leadership \- We build our brand through customer traction, technology evidence, and regulatory guidelines. This helps us establish credibility in the market and position ourselves as trusted leaders in our field. This holistic approach has enabled us to navigate diverse market conditions in Asia and grow our B2B relationships. By focusing on these areas, we drive business growth and establish strong trust with stakeholders. What's your advice for fundraising? Here are my key takeaways for other founders when it comes to fundraising: Fundraise When You Don’t Need To We closed our seed round in April 2023, a time when we weren't actively raising. Founders should always be in fundraising mode, even when they're not immediately in need of capital. Don’t wait until you have only a few months of runway left. Keep the pipeline open and build relationships. When the timing is right, execution becomes much easier. For us, our investment came through a combination of referrals and inbound interest. Even our lead investor initially rejected us, but after re-engaging, things eventually fell into place. It’s crucial to stay humble, treat everyone with respect, and maintain those relationships for when the time is right. Be Mindful of How You Present Information When fundraising, how you present information matters a lot. We created a comprehensive, easily digestible investment memo, hosted on Notion, which included everything an investor might need—problem, solution, market, team, risks, opportunities, and data. The goal was for investors to be able to get the full picture within 30 minutes without chasing down extra details. We also focused on making our financial model clear and meaningful, even though a 5-year forecast might be overkill at the seed stage. The key was clarity and conciseness, and making it as easy as possible for investors to understand the opportunity. I learned that brevity and simplicity are often the best ways to make a memorable impact. For the pitch itself, keep it simple and focus on 4 things: problem, solution, team, and market. If you can summarize each of these clearly and concisely, you’ll have a compelling pitch. Later on, you can expand into market segments, traction, and other metrics, but for seed-stage, focus on those four areas, and make sure you’re strong in at least three of them. If you do, you'll have a compelling case. How do you run things day-to-day? i.e what's your operational workflow and team structure? Here's an overview of our team structure and process: Internally: Our team is divided into two main areas: backend (internal team) and frontend (market-facing team). There's no formal hierarchy within the backend team. We all operate as equals, defining our goals based on what needs to be developed, assigning tasks, and meeting weekly to share updates and review progress. The focus is on full ownership of tasks and accountability for getting things done. I also contribute to product development, identifying challenges and clearing obstacles to help the team move forward. Backend Team: We approach tasks based on the scope defined by customers, with no blame or hierarchy. It's like a sports team—sometimes someone excels, and other times they struggle, but we support each other and move forward together. Everyone has the creative freedom to work in the way that suits them best, but we establish regular meetings and check-ins to ensure alignment and progress. Frontend Team: For the market-facing side, we implement a hierarchy because the market expects this structure. If I present myself as "CEO," it signals authority and credibility. This distinction affects how we communicate with the market and how we build our brand. The frontend team is split into four main areas: Business Product (Software Engineering) Machine Learning Engineering R&D The C-suite sits at the top, followed by team leads, and then the executors. We distill market expectations into actionable tasks, ensuring that everyone is clear on their role and responsibilities. Process: We start by receiving market expectations and defining tasks based on them. Tasks are assigned to relevant teams, and execution happens with no communication barriers between team members. This ensures seamless collaboration and focused execution. The main goal is always effectiveness—getting things done efficiently while maintaining flexibility in how individuals approach their work. In both teams, there's an emphasis on accountability, collaboration, and clear communication, but the structure varies according to the nature of the work and external expectations.

#reddit #small #startup

How and why does Musk succeed in almost all of his ventures even when the wind is against him ?

#reddit #ai/ml #implementation/integration

FreeBirdy00•This week

How and why does Musk succeed in almost all of his ventures even when the wind is against him ?

So I saw this post somewhere and decided to ask this here too. Elon Musk has probably been involved, initiated and successfully executes more ventures in his life than any other tech-billionaire CEO. SpaceX, Tesla, Twitter, PayPal (his company was acquired by PayPal after which it boomed), Neuralink, OpenAI etc. How is it that one single person can find time to do this much in life and succeed in each and every one of them ? It almost seems unreal. And in most of his ventures, he was always very close to being done once and for all and then somehow always finds a way to climb back up ? The SpaceX's 3 failed launches (back to back), Tesla's near death condition when he took over, Twitter's entire drama with lawsuits and big companies leaving the hands etc. These are all examples of near death experiences he must've had during his journey. But how does he always climb back out of it ? Is it because of his "failure's not an option" and "never give up" attitude ? Or does he have some very foolproof strategies ? Also how does one single person do so much in such a short span and yet still have time to shitpost on twitter ? Also just to be clear I am not a Musk fanboy. I respect him for some of his work and at the same time criticize for many of his actions.

MVP + AI/ML Implementation/Integration - Done for you SaaS

In today’s fast-paced world, businesses need to stay ahead of the curve. Leveraging AI, ML, and Cloud technologies isn't just an option—it's a necessity. We specialize in providing cutting-edge AI/ML solutions and Cloud services that empower businesses to innovate, automate, and scale like never before. Why AI and ML Matter Artificial Intelligence (AI) and Machine Learning (ML) are revolutionizing industries by enabling systems to learn, adapt, and improve over time. Whether it's predicting customer behavior, automating tasks, or enhancing decision-making, AI and ML open up a world of possibilities. Key Benefits of AI and ML: Enhanced Decision-Making: Harness predictive analytics to make data-driven decisions. Automation: Streamline operations with intelligent automation. Personalization: Deliver tailored experiences to your customers, increasing engagement and loyalty. Efficiency: Reduce costs and time through optimized processes. How Cloud Services Drive Innovation The Cloud is the backbone of modern business infrastructure. It allows companies to be more agile, scalable, and resilient. With Cloud computing, businesses can access powerful tools and resources on-demand, without the need for significant upfront investment. Advantages of Cloud Services: Scalability: Easily scale up or down based on your business needs. Cost Efficiency: Pay only for the resources you use, minimizing overhead. Security: Benefit from the highest standards of data security and compliance. Flexibility: Access your applications and data from anywhere, anytime. Our Services We offer comprehensive services to help you harness the full potential of AI, ML, and Cloud technologies: AI and ML Solutions: We design and deploy custom AI/ML models that solve your specific business challenges. From natural language processing (NLP) to computer vision, we cover all aspects of AI/ML. Cloud Integration: We help you migrate to the Cloud, ensuring a smooth transition with minimal disruption. Whether it’s AWS, Azure, or Google Cloud, our experts have you covered. Data Analytics: Transform your data into actionable insights with advanced analytics tools and platforms. Custom Software Development: We build robust, scalable applications that integrate AI/ML capabilities and leverage the Cloud. DevOps: Automate your development pipeline and ensure continuous integration and delivery with our DevOps expertise. Why Choose Us? Expert Team: Our team of experienced professionals is well-versed in AI/ML, Cloud computing, and data analytics. End-to-End Solutions: From ideation to deployment, we offer full-cycle development services. Tailored Approach: We understand that every business is unique. We provide customized solutions that align with your specific goals. Proven Track Record: We’ve helped numerous businesses across industries to innovate and grow. Success Stories Retail Industry: Implemented an AI-driven recommendation engine that increased sales by 30%. Healthcare Sector: Developed an ML-based diagnostic tool that improved accuracy by 20%. Finance: Integrated Cloud-based AI solutions that reduced operational costs by 25%.

Royal_Rest8409•This week

How a Small Startup in Asia Secured a Contract with the US Department of Homeland Security

Uzair Javaid, a Ph.D. with a passion for data privacy, co-founded Betterdata to tackle one of AI's most pressing challenges: protecting privacy while enabling innovation. Recently, Betterdata secured a lucrative contract with the US Department of Homeland Security, 1 of only 4 companies worldwide to do so and the only one in Asia. Here's how he did it: The Story So what's your story? I grew up in Peshawar, Pakistan, excelling in coding despite studying electrical engineering. Inspired by my professors, I set my sights on studying abroad and eventually earned a Ph.D. scholarship at NUS Singapore, specializing in data security and privacy. During my research, I ethically hacked Ethereum and published 15 papers—three times the requirement. While wrapping up my Ph.D., I explored startup ideas and joined Entrepreneur First, where I met Kevin Yee. With his expertise in generative models and mine in privacy, we founded Betterdata. Now, nearly three years in, we’ve secured a major contract with the U.S. Department of Homeland Security—one of only four companies globally and the only one from Asia. The Startup In a nutshell, what does your startup do? Betterdata is a startup that uses AI and synthetic data generation to address two major challenges: data privacy and the scarcity of high-quality data for training AI models. By leveraging generative models and privacy-enhancing technologies, Betterdata enables businesses, such as banks, to use customer data without breaching privacy regulations. The platform trains AI on real data, learns its patterns, and generates synthetic data that mimics the real thing without containing any personal or sensitive information. This allows companies to innovate and develop AI solutions safely and ethically, all while tackling the growing need for diverse, high-quality data in AI development. How did you conduct ideation and validation for your startup? The initial idea for Betterdata came from personal experience. During my Ph.D., I ethically hacked Ethereum’s blockchain, exposing flaws in encryption-based data sharing. This led me to explore AI-driven deep synthesis technology—similar to deepfakes but for structured data privacy. With GDPR impacting 28M+ businesses, I saw a massive opportunity to help enterprises securely share data while staying compliant. To validate the idea, I spoke to 50 potential customers—a number that strikes the right balance. Some say 100, but that’s impractical for early-stage founders. At 50, patterns emerge: if 3 out of 10 mention the same problem, and this repeats across 50, you have 10–15 strong signals, making it a solid foundation for an MVP. Instead of outbound sales, which I dislike, we used three key methods: Account-Based Marketing (ABM)—targeting technically savvy users with solutions for niche problems, like scaling synthetic data for banks. Targeted Content Marketing—regular customer conversations shaped our thought leadership and outreach. Raising Awareness Through Partnerships—collaborating with NUS, Singapore’s PDPC, and Plug and Play to build credibility and educate the market. These strategies attracted serious customers willing to pay, guiding Betterdata’s product development and market fit. How did you approach the initial building and ongoing product development? In the early stages, we built synthetic data generation algorithms and a basic UI for proof-of-concept, using open-source datasets to engage with banks. We quickly learned that banks wouldn't share actual customer data due to privacy concerns, so we had to conduct on-site installations and gather feedback to refine our MVP. Through continuous consultation with customers, we discovered real enterprise data posed challenges, such as missing values, which led us to adapt our prototype accordingly. This iterative approach of listening to customer feedback and observing their usage allowed us to improve our product, enhance UX, and address unmet needs while building trust and loyalty. Working closely with our customers also gives us a data advantage. Our solution’s effectiveness depends on customer data, which we can't fully access, but bridging this knowledge gap gives us a competitive edge. The more customers we test on, the more our algorithms adapt to diverse use cases, making it harder for competitors to replicate our insights. My approach to iteration is simple: focus solely on customer feedback and ignore external noise like trends or advice. The key question for the team is: which customer is asking for this feature or solution? As long as there's a clear answer, we move forward. External influences, such as AI hype, often bring more confusion than clarity. True long-term success comes from solving real customer problems, not chasing trends. Customers may not always know exactly what they want, but they understand their problems. Our job is to identify these problems and solve them in innovative ways. While customers may suggest specific features, we stay focused on solving the core issue rather than just fulfilling their exact requests. The idea aligns with the quote often attributed to Henry Ford: "If I asked people what they wanted, they would have said faster horses." The key is understanding their problems, not just taking requests at face value. How do you assess product-market fit? To assess product-market fit, we track two key metrics: Customers' Willingness to Pay: We measure both the quantity and quality of meetings with potential customers. A high number of meetings with key decision-makers signals genuine interest. At Betterdata, we focused on getting meetings with people in banks and large enterprises to gauge our product's resonance with the target market. How Much Customers Are Willing to Pay: We monitor the price customers are willing to pay, especially in the early stages. For us, large enterprises, like banks, were willing to pay a premium for our synthetic data platform due to the growing need for privacy tech. This feedback guided our product refinement and scaling strategy. By focusing on these metrics, we refined our product and positioned it for scaling. What is your business model? We employ a structured, phase-driven approach for out business model, as a B2B startup. I initially struggled with focusing on the core value proposition in sales, often becoming overly educational. Eventually, we developed a product roadmap with models that allowed us to match customer needs to specific offerings and justify our pricing. Our pricing structure includes project-based pilots and annual contracts for successful deployments. At Betterdata, our customer engagement unfolds across three phases: Phase 1: Trial and Benchmarking \- We start with outreach and use open-source datasets to showcase results, offering customers a trial period to evaluate the solution. Phase 2: Pilot or PoC \- After positive trial results, we conduct a PoC or pilot using the customer’s private data, with the understanding that successful pilots lead to an annual contract. Phase 3: Multi-Year Contracts \- Following a successful pilot, we transition to long-term commercial contracts, focusing on multi-year agreements to ensure stability and ongoing partnerships. How do you do marketing for your brand? We take a non-conventional approach to marketing, focusing on answering one key question: Which customers are willing to pay, and how much? This drives our messaging to show how our solution meets their needs. Our strategy centers around two main components: Building a network of lead magnets \- These are influential figures like senior advisors, thought leaders, and strategic partners. Engaging with institutions like IMDA, SUTD, and investors like Plug and Play helps us gain access to the right people and foster warm introductions, which shorten our sales cycle and ensure we’re reaching the right audience. Thought leadership \- We build our brand through customer traction, technology evidence, and regulatory guidelines. This helps us establish credibility in the market and position ourselves as trusted leaders in our field. This holistic approach has enabled us to navigate diverse market conditions in Asia and grow our B2B relationships. By focusing on these areas, we drive business growth and establish strong trust with stakeholders. What's your advice for fundraising? Here are my key takeaways for other founders when it comes to fundraising: Fundraise When You Don’t Need To We closed our seed round in April 2023, a time when we weren't actively raising. Founders should always be in fundraising mode, even when they're not immediately in need of capital. Don’t wait until you have only a few months of runway left. Keep the pipeline open and build relationships. When the timing is right, execution becomes much easier. For us, our investment came through a combination of referrals and inbound interest. Even our lead investor initially rejected us, but after re-engaging, things eventually fell into place. It’s crucial to stay humble, treat everyone with respect, and maintain those relationships for when the time is right. Be Mindful of How You Present Information When fundraising, how you present information matters a lot. We created a comprehensive, easily digestible investment memo, hosted on Notion, which included everything an investor might need—problem, solution, market, team, risks, opportunities, and data. The goal was for investors to be able to get the full picture within 30 minutes without chasing down extra details. We also focused on making our financial model clear and meaningful, even though a 5-year forecast might be overkill at the seed stage. The key was clarity and conciseness, and making it as easy as possible for investors to understand the opportunity. I learned that brevity and simplicity are often the best ways to make a memorable impact. For the pitch itself, keep it simple and focus on 4 things: problem, solution, team, and market. If you can summarize each of these clearly and concisely, you’ll have a compelling pitch. Later on, you can expand into market segments, traction, and other metrics, but for seed-stage, focus on those four areas, and make sure you’re strong in at least three of them. If you do, you'll have a compelling case. How do you run things day-to-day? i.e what's your operational workflow and team structure? Here's an overview of our team structure and process: Internally: Our team is divided into two main areas: backend (internal team) and frontend (market-facing team). There's no formal hierarchy within the backend team. We all operate as equals, defining our goals based on what needs to be developed, assigning tasks, and meeting weekly to share updates and review progress. The focus is on full ownership of tasks and accountability for getting things done. I also contribute to product development, identifying challenges and clearing obstacles to help the team move forward. Backend Team: We approach tasks based on the scope defined by customers, with no blame or hierarchy. It's like a sports team—sometimes someone excels, and other times they struggle, but we support each other and move forward together. Everyone has the creative freedom to work in the way that suits them best, but we establish regular meetings and check-ins to ensure alignment and progress. Frontend Team: For the market-facing side, we implement a hierarchy because the market expects this structure. If I present myself as "CEO," it signals authority and credibility. This distinction affects how we communicate with the market and how we build our brand. The frontend team is split into four main areas: Business Product (Software Engineering) Machine Learning Engineering R&D The C-suite sits at the top, followed by team leads, and then the executors. We distill market expectations into actionable tasks, ensuring that everyone is clear on their role and responsibilities. Process: We start by receiving market expectations and defining tasks based on them. Tasks are assigned to relevant teams, and execution happens with no communication barriers between team members. This ensures seamless collaboration and focused execution. The main goal is always effectiveness—getting things done efficiently while maintaining flexibility in how individuals approach their work. In both teams, there's an emphasis on accountability, collaboration, and clear communication, but the structure varies according to the nature of the work and external expectations.

#reddit #small #startup

Obliterate my app idea before I bet my life savings on it (AI lead-gen tool)

r_hussy•This week

Obliterate my app idea before I bet my life savings on it (AI lead-gen tool)

So I have this app idea on my mind for months now, but I’m 95% sure it’ll flop. Can you help me figure it out? The Problem: Many agencies struggle to stand out in a crowded marketplace and waste time on discovery calls. Current lead generation tools often feel impersonal and don’t showcase how an agency’s expertise can solve specific problems of clients. The Idea: A lead generation tool for agency owners that uses AI to create personalized recommendations for prospects (potential customers) early in the sales process. These recommendations are sent as custom reports (aka lead magnet) to the prospect. This would showcase how the agency can address the unique needs and requirements of the potential client without requiring a discovery call right away. The whole process will be 100% automated, allowing agency owners to focus on closing deals. Target audience: Agency owners/marketers who want to focus on acquiring qualified leads online. In the future, I’d love to explore niches like SaaS and real estate. How it works in 4 steps: Prospect Input: Prospects visit an agency’s landing page (generated by my app) and submit their goals and challenges. AI Matching: The custom-trained AI processes their input and combines it with the agency’s data to generate a customized, actionable report. Delivery: The report is instantly emailed to the prospect, highlighting how the agency can address his/her challenges. Follow-Up: With the prospect warmed up, the agency can follow up and (hopefully) convert them into a client. For example, a digital marketing agency could use the app to create a landing page offering a free ‘Personalized Marketing Strategy Report.’ When a prospect submits his goals and challenges, the AI instantly generates and emails a tailored report, showcasing the agency’s expertise. Why It Might Fail: Maybe agencies won’t see the value in automation, or AI-generated reports might feel impersonal. Could this idea fill a real gap? Why It Might Work: It’s a way for agencies to stand out with personalized lead magnets that feel unique and interactive. It could help agencies attract and convert qualified leads in an automated way. Your Honest Feedback: Would this help agencies improve their lead-generation process, or is it just flashy nonsense? What flaws or challenges do you see in this idea? Is this worth pursuing, or should I stick to spending time with my family 😂? Thank you guys, your honesty might save me from myself! PS: I won’t link to my tool because I don’t want to come off as a spammer.

How to get that big idea for your next business? Use trends!

IRemember123•This week

How to get that big idea for your next business? Use trends!

Hello entrepreneurs and aspiring business owners, I am Mikael and I want to share a post about how to spot business ideas. If you're wondering who the owl is, it's Agent O, my sidekick (please bear with him... or me, if you can). Let's get on to it. So, there are basically two ways of getting ideas for your new business: Find a service, product or experience that's already working. Identify and ride a trend. 🦉 : Third, have a rich relative pass you their business and sip margaritas by the sea while scrolling Reddit for the rest of your life! 🕵️ : Refrain yourself, I just got started ffs, I don't want to get banned! So, what are trends? Trends are patterns of adoption of a product, service or experience by people who want to satisfy a common need. Cool, huh? How trends start Trends emerge and evolve as temporary or permanent solutions to human needs. All products, services and experiences are the expression of human needs manifested through a perceived lack, which we humans interpret as problems. Let me make this more clear. Humans have needs: from basic (food, shelter, safety) to advanced (community, knowledge) to evolved (self actualization, spirituality) and everything in between. Don’t see this as a hierarchy, as it’s usually depicted with Maslow’s pyramid. See it as cycles with different degrees of impact on humans that vary in time and intensity. 🦉 : WHAT!?? 🕵️ : Hear me out… How Trends Affect Society Human needs are physical, emotional, intellectual and spiritual. Every day we feel the impact of those needs with different degrees of required fulfillment. You can’t go on without air for more than a few minutes. You can’t live without food and water for more than a few days. So, when it comes to the needs of the body, these have a shorter timeframe in which they need to be addressed. 🦉 : Ahh, I see what you did there… \\🕵️ \\: Thanks! But you can also live with an unfulfilled need for love or friends for a long time. You can live with a decaying health as well. And you also can live your entire life without finding out if there is a God or not. Humans perceive needs as something they lack within, which in turn is expressed as a problem on the outside. I lack food or water, this will create a problem for my survival. So I need to find food and water in my environment. This lack creates a behavior seeking a product, service or experience to fulfill that need. Makes sense? 🦉 : I just went out and got me a “Mice à la Forest” dinner! 🕵️: Bon appétit! See, Agent O fulfilled a bodily need. That’s what animals do, as they’re driven by instinct and are governed by natural laws (survive, reproduce, sleep, repeat). Humans are driven by more complex needs, as our intellect and emotions allow us to override those basic primary instincts. Why Trends Are Important What an entrepreneur does is to shift the perspective: instead of seeing a lack, he/she sees an opportunity by asking the question: how can I fulfill this need? Or, even better put: how can I help people by solving their problem? That’s the first step to solving a problem: asking a question. That is why the best products are actually problems solved by entrepreneurs who work to solve their own need for a product, service or experience. They then provide it to other people for a cost. Easy, right? That’s what entrepreneurship is: solving a problem. The bigger the problem, the bigger the impact. The bigger the impact, the higher the revenue. It’s easier to understand trends now, isn’t it? You can see that trends are nothing more than the initial adoption of a product, service or experience by a group of people who are looking for a solution to their common need. 🦉 : Did you get that from a book? 🕵️ : You snore when you sleep… ¯\\(\ツ)/\¯ 🦉 : $@#&\*! Hooman! Needs are the foundation on which the modern world is built. Once you understand needs, you fundamentally change your perception of problems into opportunities. This mental shift is the entrepreneurial mindset: where others see problems, you see solutions. Where Do Trends Start So, to recap: human needs are translated into problems. Founders understand the root of the problem (the need) and create products, services, experiences as solutions to those needs. They offer the solution to the public through startups and companies, which belong to a specific niche in a particular industry. 🦉 : Aaah, so that’s why it’s called venture capital? 🕵️ : Yeah, because you’re venturing into a new endeavor to let people know about your solution to their (and ideally your) problem. 🦉 : So if you use ads to market your venture, it’s an adventure? 🕵️ : I see what you did there… If the need behind the adoption is strong and real enough, that trend will translate into a niche within an industry. If the adoption isn’t driven by strong fundamental needs, it will turn into a fad and disappear from the perception of the public, no matter how much marketing money is thrown at it. This happens because the solution (product/service/experience) to the need didn’t create the physical, intellectual or emotional response required to create a recurring behavior around it. Remember this: Problem (why) -> Behavior (how) -> Solution (what) Understand this: there are multiple types of trends. There are product or service trends. There are industry driven trends. There are tendency driven trends, like the emergence of a new paradigm that improves a lot of industries (yes, I’m looking at you, AI). Where Do Trends Come From So now you can see that trends are patterns of adoption related to a specific human need that is addressed through one or multiple products or services. This is a bottom up direction coming from evolution. Multiple trends in different industries also emerge from a theme, which is a bigger vision of a human effort to address a high level problem. This is a top down direction, coming from implementation (by governments, different organizations or other interested parties with the power to influence changes at mass level). Conclusion Now you have a better understanding of trends by looking at them through the lens of human needs. Also, you might also understand time better because you realize that human needs have different degrees of impact in time and intensity. So you now see that trends don’t only relate to individuals, but also to groups of people, from the smallest community to countries and even global needs. That is the reason you’ll sometimes hear some say that time is a flat circle: because clothes change, but humans are quite the same. Needs don’t change a lot in time, just the way we address and solve them. Here’s an interesting game for you: take a look at some behaviors in your life. Which of them are driven by a bodily need, which by an intellectual or emotional one? Which ones are completely automated and you had no idea you were doing? How are these behaviors controlling parts of your life that you were unaware of until now? If you made it this far, thank you for taking the time to read this. I hope you enjoyed it, found it useful and entertaining. Ofc, I value your opinion and welcome it in the comments. Thank you!

#reddit #idea #your

IRemember123•This week

How to get that big idea for your next business? Use trends!

Hello entrepreneurs and aspiring business owners, I am Mikael and I want to share a post about how to spot business ideas. If you're wondering who the owl is, it's Agent O, my sidekick (please bear with him... or me, if you can). Let's get on to it. So, there are basically two ways of getting ideas for your new business: Find a service, product or experience that's already working. Identify and ride a trend. 🦉 : Third, have a rich relative pass you their business and sip margaritas by the sea while scrolling Reddit for the rest of your life! 🕵️ : Refrain yourself, I just got started ffs, I don't want to get banned! So, what are trends? Trends are patterns of adoption of a product, service or experience by people who want to satisfy a common need. Cool, huh? How trends start Trends emerge and evolve as temporary or permanent solutions to human needs. All products, services and experiences are the expression of human needs manifested through a perceived lack, which we humans interpret as problems. Let me make this more clear. Humans have needs: from basic (food, shelter, safety) to advanced (community, knowledge) to evolved (self actualization, spirituality) and everything in between. Don’t see this as a hierarchy, as it’s usually depicted with Maslow’s pyramid. See it as cycles with different degrees of impact on humans that vary in time and intensity. 🦉 : WHAT!?? 🕵️ : Hear me out… How Trends Affect Society Human needs are physical, emotional, intellectual and spiritual. Every day we feel the impact of those needs with different degrees of required fulfillment. You can’t go on without air for more than a few minutes. You can’t live without food and water for more than a few days. So, when it comes to the needs of the body, these have a shorter timeframe in which they need to be addressed. 🦉 : Ahh, I see what you did there… \\🕵️ \\: Thanks! But you can also live with an unfulfilled need for love or friends for a long time. You can live with a decaying health as well. And you also can live your entire life without finding out if there is a God or not. Humans perceive needs as something they lack within, which in turn is expressed as a problem on the outside. I lack food or water, this will create a problem for my survival. So I need to find food and water in my environment. This lack creates a behavior seeking a product, service or experience to fulfill that need. Makes sense? 🦉 : I just went out and got me a “Mice à la Forest” dinner! 🕵️: Bon appétit! See, Agent O fulfilled a bodily need. That’s what animals do, as they’re driven by instinct and are governed by natural laws (survive, reproduce, sleep, repeat). Humans are driven by more complex needs, as our intellect and emotions allow us to override those basic primary instincts. Why Trends Are Important What an entrepreneur does is to shift the perspective: instead of seeing a lack, he/she sees an opportunity by asking the question: how can I fulfill this need? Or, even better put: how can I help people by solving their problem? That’s the first step to solving a problem: asking a question. That is why the best products are actually problems solved by entrepreneurs who work to solve their own need for a product, service or experience. They then provide it to other people for a cost. Easy, right? That’s what entrepreneurship is: solving a problem. The bigger the problem, the bigger the impact. The bigger the impact, the higher the revenue. It’s easier to understand trends now, isn’t it? You can see that trends are nothing more than the initial adoption of a product, service or experience by a group of people who are looking for a solution to their common need. 🦉 : Did you get that from a book? 🕵️ : You snore when you sleep… ¯\\(\ツ)/\¯ 🦉 : $@#&\*! Hooman! Needs are the foundation on which the modern world is built. Once you understand needs, you fundamentally change your perception of problems into opportunities. This mental shift is the entrepreneurial mindset: where others see problems, you see solutions. Where Do Trends Start So, to recap: human needs are translated into problems. Founders understand the root of the problem (the need) and create products, services, experiences as solutions to those needs. They offer the solution to the public through startups and companies, which belong to a specific niche in a particular industry. 🦉 : Aaah, so that’s why it’s called venture capital? 🕵️ : Yeah, because you’re venturing into a new endeavor to let people know about your solution to their (and ideally your) problem. 🦉 : So if you use ads to market your venture, it’s an adventure? 🕵️ : I see what you did there… If the need behind the adoption is strong and real enough, that trend will translate into a niche within an industry. If the adoption isn’t driven by strong fundamental needs, it will turn into a fad and disappear from the perception of the public, no matter how much marketing money is thrown at it. This happens because the solution (product/service/experience) to the need didn’t create the physical, intellectual or emotional response required to create a recurring behavior around it. Remember this: Problem (why) -> Behavior (how) -> Solution (what) Understand this: there are multiple types of trends. There are product or service trends. There are industry driven trends. There are tendency driven trends, like the emergence of a new paradigm that improves a lot of industries (yes, I’m looking at you, AI). Where Do Trends Come From So now you can see that trends are patterns of adoption related to a specific human need that is addressed through one or multiple products or services. This is a bottom up direction coming from evolution. Multiple trends in different industries also emerge from a theme, which is a bigger vision of a human effort to address a high level problem. This is a top down direction, coming from implementation (by governments, different organizations or other interested parties with the power to influence changes at mass level). Conclusion Now you have a better understanding of trends by looking at them through the lens of human needs. Also, you might also understand time better because you realize that human needs have different degrees of impact in time and intensity. So you now see that trends don’t only relate to individuals, but also to groups of people, from the smallest community to countries and even global needs. That is the reason you’ll sometimes hear some say that time is a flat circle: because clothes change, but humans are quite the same. Needs don’t change a lot in time, just the way we address and solve them. Here’s an interesting game for you: take a look at some behaviors in your life. Which of them are driven by a bodily need, which by an intellectual or emotional one? Which ones are completely automated and you had no idea you were doing? How are these behaviors controlling parts of your life that you were unaware of until now? If you made it this far, thank you for taking the time to read this. I hope you enjoyed it, found it useful and entertaining. Ofc, I value your opinion and welcome it in the comments. Thank you!

Obliterate my app idea before I bet my life savings on it (AI lead-gen tool)

So I have this app idea on my mind for months now, but I’m 95% sure it’ll flop. Can you help me figure it out? The Problem: Many agencies struggle to stand out in a crowded marketplace and waste time on discovery calls. Current lead generation tools often feel impersonal and don’t showcase how an agency’s expertise can solve specific problems of clients. The Idea: A lead generation tool for agency owners that uses AI to create personalized recommendations for prospects (potential customers) early in the sales process. These recommendations are sent as custom reports (aka lead magnet) to the prospect. This would showcase how the agency can address the unique needs and requirements of the potential client without requiring a discovery call right away. The whole process will be 100% automated, allowing agency owners to focus on closing deals. Target audience: Agency owners/marketers who want to focus on acquiring qualified leads online. In the future, I’d love to explore niches like SaaS and real estate. How it works in 4 steps: Prospect Input: Prospects visit an agency’s landing page (generated by my app) and submit their goals and challenges. AI Matching: The custom-trained AI processes their input and combines it with the agency’s data to generate a customized, actionable report. Delivery: The report is instantly emailed to the prospect, highlighting how the agency can address his/her challenges. Follow-Up: With the prospect warmed up, the agency can follow up and (hopefully) convert them into a client. For example, a digital marketing agency could use the app to create a landing page offering a free ‘Personalized Marketing Strategy Report.’ When a prospect submits his goals and challenges, the AI instantly generates and emails a tailored report, showcasing the agency’s expertise. Why It Might Fail: Maybe agencies won’t see the value in automation, or AI-generated reports might feel impersonal. Could this idea fill a real gap? Why It Might Work: It’s a way for agencies to stand out with personalized lead magnets that feel unique and interactive. It could help agencies attract and convert qualified leads in an automated way. Your Honest Feedback: Would this help agencies improve their lead-generation process, or is it just flashy nonsense? What flaws or challenges do you see in this idea? Is this worth pursuing, or should I stick to spending time with my family 😂? Thank you guys, your honesty might save me from myself! PS: I won’t link to my tool because I don’t want to come off as a spammer.

Comfortable_Mud1233•This week

An honest opinion about start-up idea

You will be helpful to us especially if you have worked with a lot of data (whether in a corporation or somewhere else). We aim to develop a document library platform that aggregates data from various storage services such as Amazon S3 (AWS) and Google Cloud Storage (GCP). The platform serves as a centralized interface or "panel" where users within an organization can access and display documents stored across different sources. Key features include: Data aggregation without storage: The platform pulls data from multiple sources but does not store it locally. This approach minimizes data redundancy and storage costs. AI-powered semantic search: Utilizes artificial intelligence to perform semantic searches across files, enabling users to find documents based on context and meaning rather than just keywords. Tagging and versioning: Supports the addition of tags for better categorization and tracking of different versions of files. The solution targets companies handling large volumes of data and documents dispersed across various storage services. Strengths we found: Non-invasive integration: Eliminates the need for data migration, reducing setup time and complexity. Enhanced search capabilities: AI-driven semantic search outperforms basic keyword searches, saving time. Cross-platform functionality: Provides a level of interoperability that competitors lack. Cost efficiency: Avoids additional storage costs and reduces time spent searching for documents. Weaknesses that we see: Limited feature set compared to ECMs: May lack some advanced features like workflow automation, collaboration tools, and compliance auditing provided by ECMs. We're new: so no trust. Is this something that companies would want to integrate and pay for? Thanks a lot, it can save us a lot of time :)

#reddit #honest #opinion

r_hussy•This week

Obliterate my app idea before I bet my life savings on it (AI lead-gen tool)

So I have this app idea on my mind for months now, but I’m 95% sure it’ll flop. Can you help me figure it out? The Problem: Many agencies struggle to stand out in a crowded marketplace and waste time on discovery calls. Current lead generation tools often feel impersonal and don’t showcase how an agency’s expertise can solve specific problems of clients. The Idea: A lead generation tool for agency owners that uses AI to create personalized recommendations for prospects (potential customers) early in the sales process. These recommendations are sent as custom reports (aka lead magnet) to the prospect. This would showcase how the agency can address the unique needs and requirements of the potential client without requiring a discovery call right away. The whole process will be 100% automated, allowing agency owners to focus on closing deals. Target audience: Agency owners/marketers who want to focus on acquiring qualified leads online. In the future, I’d love to explore niches like SaaS and real estate. How it works in 4 steps: Prospect Input: Prospects visit an agency’s landing page (generated by my app) and submit their goals and challenges. AI Matching: The custom-trained AI processes their input and combines it with the agency’s data to generate a customized, actionable report. Delivery: The report is instantly emailed to the prospect, highlighting how the agency can address his/her challenges. Follow-Up: With the prospect warmed up, the agency can follow up and (hopefully) convert them into a client. For example, a digital marketing agency could use the app to create a landing page offering a free ‘Personalized Marketing Strategy Report.’ When a prospect submits his goals and challenges, the AI instantly generates and emails a tailored report, showcasing the agency’s expertise. Why It Might Fail: Maybe agencies won’t see the value in automation, or AI-generated reports might feel impersonal. Could this idea fill a real gap? Why It Might Work: It’s a way for agencies to stand out with personalized lead magnets that feel unique and interactive. It could help agencies attract and convert qualified leads in an automated way. Your Honest Feedback: Would this help agencies improve their lead-generation process, or is it just flashy nonsense? What flaws or challenges do you see in this idea? Is this worth pursuing, or should I stick to spending time with my family 😂? Thank you guys, your honesty might save me from myself! PS: I won’t link to my tool because I don’t want to come off as a spammer.

r_hussy•This week

Obliterate my app idea before I bet my life savings on it (AI lead-gen tool)

So I have this app idea on my mind for months now, but I’m 95% sure it’ll flop. Can you help me figure it out? The Problem: Many agencies struggle to stand out in a crowded marketplace and waste time on discovery calls. Current lead generation tools often feel impersonal and don’t showcase how an agency’s expertise can solve specific problems of clients. The Idea: A lead generation tool for agency owners that uses AI to create personalized recommendations for prospects (potential customers) early in the sales process. These recommendations are sent as custom reports (aka lead magnet) to the prospect. This would showcase how the agency can address the unique needs and requirements of the potential client without requiring a discovery call right away. The whole process will be 100% automated, allowing agency owners to focus on closing deals. Target audience: Agency owners/marketers who want to focus on acquiring qualified leads online. In the future, I’d love to explore niches like SaaS and real estate. How it works in 4 steps: Prospect Input: Prospects visit an agency’s landing page (generated by my app) and submit their goals and challenges. AI Matching: The custom-trained AI processes their input and combines it with the agency’s data to generate a customized, actionable report. Delivery: The report is instantly emailed to the prospect, highlighting how the agency can address his/her challenges. Follow-Up: With the prospect warmed up, the agency can follow up and (hopefully) convert them into a client. For example, a digital marketing agency could use the app to create a landing page offering a free ‘Personalized Marketing Strategy Report.’ When a prospect submits his goals and challenges, the AI instantly generates and emails a tailored report, showcasing the agency’s expertise. Why It Might Fail: Maybe agencies won’t see the value in automation, or AI-generated reports might feel impersonal. Could this idea fill a real gap? Why It Might Work: It’s a way for agencies to stand out with personalized lead magnets that feel unique and interactive. It could help agencies attract and convert qualified leads in an automated way. Your Honest Feedback: Would this help agencies improve their lead-generation process, or is it just flashy nonsense? What flaws or challenges do you see in this idea? Is this worth pursuing, or should I stick to spending time with my family 😂? Thank you guys, your honesty might save me from myself! PS: I won’t link to my tool because I don’t want to come off as a spammer.

Artificial Intelligence for Small and Medium Businesses

google_results

#google_results #artificial #intelligence

AWS•Apr 9, 2025

Artificial Intelligence for Small and Medium Businesses

Learn how AWS artificial intelligence AI and machine learning ML can help small and medium businesses SMBs innovate and grow

0.66

activepieces•Mar 28, 2025

activepieces

An open source replacement for Zapier Documentation 🌪️ Create a Piece 🖉 Deploy 🔥 Join Discord 🤯 Welcome to Activepieces Your friendliest open source all-in-one automation tool, designed to be extensible through a type-safe pieces framework written in Typescript. 🔥 Why Activepieces is Different: 💖 Loved by Everyone: Intuitive interface and great experience for both technical and non-technical users with a quick learning curve. 🌐 Open Ecosystem: All pieces are open source and available on npmjs.com, 60% of the pieces are contributed by the community. 🛠️ Pieces are written in Typescript: Pieces are npm packages in TypeScript, offering full customization with the best developer experience, including hot reloading for local piece development on your machine. 😎 🤖 AI-Ready: Native AI pieces let you experiment with various providers, or create your own agents using our AI SDK, and there is Copilot to help you build flows inside the builder. 🏢 Enterprise-Ready: Developers set up the tools, and anyone in the organization can use the no-code builder. Full customization from branding to control. 🔒 Secure by Design: Self-hosted and network-gapped for maximum security and control over your data. 🧠 Human in the Loop: Delay execution for a period of time or require approval. These are just pieces built on top of the piece framework, and you can build many pieces like that. 🎨 💻 Human Input Interfaces: Built-in support for human input triggers like "Chat Interface" 💬 and "Form Interface" 📝 🛠️ Builder Features: [x] Loops [x] Branches [x] Auto Retries [x] HTTP [x] Code with NPM [x] ASK AI in Code Piece (Non technical user can clean data without knowing to code) [x] Flows are fully versioned. [x] Languages Translations [x] Customizable Templates [X] 200+ Pieces, check https://www.activepieces.com/pieces We release updates frequently. Check the product changelog for the latest features. 🔌 Create Your Own Piece Activepieces supports integrations with Google Sheets, OpenAI, Discord, RSS, and over 200 other services. Check out the full list of supported integrations, which is constantly expanding thanks to our community's contributions. As an open ecosystem, all integration source code is accessible in our repository. These integrations are versioned and published directly to npmjs.com upon contribution. You can easily create your own integration using our TypeScript framework. For detailed instructions, please refer to our Contributor's Guide. License Activepieces' Community Edition is released as open source under the MIT license and enterprise features are released under Commercial License Read more about the feature comparison here https://www.activepieces.com/docs/about/editions 💭 Join Our Community 🌐 Contributions We welcome contributions big or small and in different directions. The best way to do this is to check this document and we are always up to talk on our Discord Server. 📚 Translations Not into coding but still interested in contributing? Come join our Discord and visit https://www.activepieces.com/docs/about/i18n for more information. !fr translation].data.translationProgress&url=https%3A%2F%2Fbadges.awesome-crowdin.com%2Fstats-16093902-626364-update.json) !it translation].data.translationProgress&url=https%3A%2F%2Fbadges.awesome-crowdin.com%2Fstats-16093902-626364-update.json) !de translation].data.translationProgress&url=https%3A%2F%2Fbadges.awesome-crowdin.com%2Fstats-16093902-626364-update.json) !ja translation].data.translationProgress&url=https%3A%2F%2Fbadges.awesome-crowdin.com%2Fstats-16093902-626364-update.json) !pt-BR translation].data.translationProgress&url=https%3A%2F%2Fbadges.awesome-crowdin.com%2Fstats-16093902-626364-update.json) 🦫 Contributors ShahedAlMashni🔌 AbdulTheActivePiecer🚧 Khaled Mashaly🚧 Mohammed Abu Aboud🚧 Abdulrahman Zeineddin🔌 ahmad jaber🔌 ashrafsamhouri🔌 Mohammad Abu Musa📆 Mukewa Wekalao🔌 Osama Abdallah Essa Haikal🔌 Arman🛡️ Oskar Krämer📖 Thibaut Patel🤔 🔌 Applesaucesomer🤔 crazyTweek🤔 Muhammad Tabaza🔌 Shay Punter📖 🔌 abaza738🔌 Jona Boeddinghaus🔌 fomojola💻 Alexander Storozhevsky💻 J0LGER🛡️ Patrick Veverka🐛 Berk Sümbül📖 Willian Guedes🔌 Abdullah Ranginwala💻 Dennis Tychsen🔌 MyWay🔌 Bibhuti Bhusan Panda🔌 Tarun Samanta🐛 Herman Kudria🔌 [NULL] Dev🔌 Jan Bebendorf🔌 Nilesh🔌 Vraj Gohil🔌 BastienMe🔌 Stephen Foskett📖 Nathan📖 Marcin Natanek🔌 Mark van Bellen🔌 Olivier Guzzi🔌 Osama Zakarneh🔌 phestvik🤔 Rajdeep Pal📖 Camilo Usuga🔌 Kishan Parmar📖 🔌 BBND🔌 Haseeb Rehman🔌 Rita Gorokhod🔌 Fábio Ferreira🔌 Florin Buffet📖 Drew Lewis🔌 Benjamin André-Micolon🔌 Denis Gurskij🔌 Nefer Lopez📖 fardeenpanjwani-codeglo📖 Landon Moir🔌 Diego Nijboer🔌 Tân Một Nắng🔌 Gavin Foley📖 Dennis Trautwein🐛 Andrew Rosenblatt🐛 rika🔌 Cyril Selasi🔌 Franck Nijimbere🔌 Aleksandr Denisov🔌 Reuben Swartz📖 joselupianez🔌 Awais Manzoor🐛 💻 Andrei🐛 derbbre📖 Maor Rozenfeld💻 Michael Huynh📖 Filip Dunđer💻 Don Thorp📖 Joe Workman🔌 Aykut Akgün💻 Yann Petitjean🔌 🐛 pfernandez98🔌 Daniel O.🔌 Meng-Yuan Huang📖 Leyla🐛 i-nithin🔌 la3rence🔌 Dennis Rongo🐛 🔌 Kartik Mehta📖 💻 Zakher Masri📖 💻 AbdullahBitar🔌 Mario Meyer🔌 Karim Khaleel🔌 CPonchet🐛 Olivier Sambourg🔌 Ahmad(Ed)🔌 leenmashni🔌 M Abdul Rauf📖 Vincent Barrier🔌 John💻 🔌 Joost de Valk🔌 MJ🔌 ShravanShenoy💻 Jon Kristian📖 cr0fters🐛 Bibek Timsina🐛 Viktor Szépe💻 Rendy Tan📖 🔌 Islam Abdelfattah🐛 Yoonjae Choi💻 Javier HM🔌 Mohamed Hassan🐛 Christian Schab🔌 Pratik Kinage🔌 Abdelrahman Mostafa 🔌 Hamza Zagha🐛 Lasse Schuirmann🔌 Cyril Duchon-Doris🔌 Javiink🔌 Harshit Harchani🔌 MrAkber📖 marek-slavicek🔌 hugh-codes🔌 Alex Lewis🐛 Yuanlin Lin📖 Ala Shiban📖 hamsh💻 Anne Mariel Catapang🔌 Carlo Gino Catapang🔌 Aditya Rathore🔌 coderbob2🔌 Ramy Gamal🔌 Alexandru-Dan Pop💻 Frank Micheal 🔌 Emmanuel Ferdman📖 Sany A🔌 Niels Swimberghe🐛 lostinbug🔌 gushkool🔌 Omar Sayed🔌 rSnapkoOpenOps🐛 ahronshor🔌 Cezar🐛 Shawn Lim🔌 Shawn Lim🔌 pavloDeshko🐛 abc💻 manoj kumar d🔌 Feli🔌 Miguel🔌 Instasent DEV🔌 Matthieu Lombard🔌 beyondlevi🔌 Rafal Zawadzki🔌 Simon Courtois🔌 alegria-solutions🔌 D-Rowe-FS🔌 张晟杰🔌 Ashot🔌 Amr Abu Aza🔌 John Goodliff🔌 Diwash Dev🔌 André🔌 Lou | Digital Marketing🔌 Maarten Coppens🔌 Mahmoud Hamed🔌 Theo Dammaretz🔌 s31w4n📖 Abdul Rahman🔌 Kent Smith🔌 Arvind Ramesh💻 valentin-mourtialon🔌 psgpsg16🔌 Mariia Shyn🔌 Joshua Heslin🔌 Ahmad🔌 you💻 Daniel Poon💻 Kévin Yu🔌 노영은🔌 reemayoush🔌 Brice🛡️ Mg Wunna🔌 This project follows the all-contributors specification. Contributions of any kind are welcome!

#github #activepieces

Mintplex-Labs•Mar 28, 2025

0.572

0.4703504093656464

anything-llm

AnythingLLM: The all-in-one AI app you were looking for. Chat with your docs, use AI Agents, hyper-configurable, multi-user, & no frustrating set up required. | | Docs | Hosted Instance English · 简体中文 · 日本語 👉 AnythingLLM for desktop (Mac, Windows, & Linux)! Download Now A full-stack application that enables you to turn any document, resource, or piece of content into context that any LLM can use as references during chatting. This application allows you to pick and choose which LLM or Vector Database you want to use as well as supporting multi-user management and permissions. !Chatting Watch the demo! Product Overview AnythingLLM is a full-stack application where you can use commercial off-the-shelf LLMs or popular open source LLMs and vectorDB solutions to build a private ChatGPT with no compromises that you can run locally as well as host remotely and be able to chat intelligently with any documents you provide it. AnythingLLM divides your documents into objects called workspaces. A Workspace functions a lot like a thread, but with the addition of containerization of your documents. Workspaces can share documents, but they do not talk to each other so you can keep your context for each workspace clean. Cool features of AnythingLLM 🆕 Custom AI Agents 🆕 No-code AI Agent builder 🖼️ Multi-modal support (both closed and open-source LLMs!) 👤 Multi-user instance support and permissioning Docker version only 🦾 Agents inside your workspace (browse the web, etc) 💬 Custom Embeddable Chat widget for your website Docker version only 📖 Multiple document type support (PDF, TXT, DOCX, etc) Simple chat UI with Drag-n-Drop funcitonality and clear citations. 100% Cloud deployment ready. Works with all popular closed and open-source LLM providers. Built-in cost & time-saving measures for managing very large documents compared to any other chat UI. Full Developer API for custom integrations! Much more...install and find out! Supported LLMs, Embedder Models, Speech models, and Vector Databases Large Language Models (LLMs): Any open-source llama.cpp compatible model OpenAI OpenAI (Generic) Azure OpenAI AWS Bedrock Anthropic NVIDIA NIM (chat models) Google Gemini Pro Hugging Face (chat models) Ollama (chat models) LM Studio (all models) LocalAi (all models) Together AI (chat models) Fireworks AI (chat models) Perplexity (chat models) OpenRouter (chat models) DeepSeek (chat models) Mistral Groq Cohere KoboldCPP LiteLLM Text Generation Web UI Apipie xAI Novita AI (chat models) PPIO Embedder models: AnythingLLM Native Embedder (default) OpenAI Azure OpenAI LocalAi (all) Ollama (all) LM Studio (all) Cohere Audio Transcription models: AnythingLLM Built-in (default) OpenAI TTS (text-to-speech) support: Native Browser Built-in (default) PiperTTSLocal - runs in browser OpenAI TTS ElevenLabs Any OpenAI Compatible TTS service. STT (speech-to-text) support: Native Browser Built-in (default) Vector Databases: LanceDB (default) Astra DB Pinecone Chroma Weaviate Qdrant Milvus Zilliz Technical Overview This monorepo consists of three main sections: frontend: A viteJS + React frontend that you can run to easily create and manage all your content the LLM can use. server: A NodeJS express server to handle all the interactions and do all the vectorDB management and LLM interactions. collector: NodeJS express server that process and parses documents from the UI. docker: Docker instructions and build process + information for building from source. embed: Submodule for generation & creation of the web embed widget. browser-extension: Submodule for the chrome browser extension. 🛳 Self Hosting Mintplex Labs & the community maintain a number of deployment methods, scripts, and templates that you can use to run AnythingLLM locally. Refer to the table below to read how to deploy on your preferred environment or to automatically deploy. | Docker | AWS | GCP | Digital Ocean | Render.com | |----------------------------------------|----|-----|---------------|------------| | [![Deploy on Docker][docker-btn]][docker-deploy] | [![Deploy on AWS][aws-btn]][aws-deploy] | [![Deploy on GCP][gcp-btn]][gcp-deploy] | [![Deploy on DigitalOcean][do-btn]][do-deploy] | [![Deploy on Render.com][render-btn]][render-deploy] | | Railway | RepoCloud | Elestio | | --- | --- | --- | | [![Deploy on Railway][railway-btn]][railway-deploy] | [![Deploy on RepoCloud][repocloud-btn]][repocloud-deploy] | [![Deploy on Elestio][elestio-btn]][elestio-deploy] | or set up a production AnythingLLM instance without Docker → How to setup for development yarn setup To fill in the required .env files you'll need in each of the application sections (from root of repo). Go fill those out before proceeding. Ensure server/.env.development is filled or else things won't work right. yarn dev:server To boot the server locally (from root of repo). yarn dev:frontend To boot the frontend locally (from root of repo). yarn dev:collector To then run the document collector (from root of repo). Learn about documents Learn about vector caching External Apps & Integrations These are apps that are not maintained by Mintplex Labs, but are compatible with AnythingLLM. A listing here is not an endorsement. Midori AI Subsystem Manager - A streamlined and efficient way to deploy AI systems using Docker container technology. Coolify - Deploy AnythingLLM with a single click. GPTLocalhost for Microsoft Word - A local Word Add-in for you to use AnythingLLM in Microsoft Word. Telemetry & Privacy AnythingLLM by Mintplex Labs Inc contains a telemetry feature that collects anonymous usage information. More about Telemetry & Privacy for AnythingLLM Why? We use this information to help us understand how AnythingLLM is used, to help us prioritize work on new features and bug fixes, and to help us improve AnythingLLM's performance and stability. Opting out Set DISABLE_TELEMETRY in your server or docker .env settings to "true" to opt out of telemetry. You can also do this in-app by going to the sidebar > Privacy and disabling telemetry. What do you explicitly track? We will only track usage details that help us make product and roadmap decisions, specifically: Type of your installation (Docker or Desktop) When a document is added or removed. No information about the document. Just that the event occurred. This gives us an idea of use. Type of vector database in use. Let's us know which vector database provider is the most used to prioritize changes when updates arrive for that provider. Type of LLM in use. Let's us know the most popular choice and prioritize changes when updates arrive for that provider. Chat is sent. This is the most regular "event" and gives us an idea of the daily-activity of this project across all installations. Again, only the event is sent - we have no information on the nature or content of the chat itself. You can verify these claims by finding all locations Telemetry.sendTelemetry is called. Additionally these events are written to the output log so you can also see the specific data which was sent - if enabled. No IP or other identifying information is collected. The Telemetry provider is PostHog - an open-source telemetry collection service. View all telemetry events in source code 👋 Contributing create issue create PR with branch name format of - LGTM from core-team 🌟 Contributors 🔗 More Products [VectorAdmin][vector-admin]: An all-in-one GUI & tool-suite for managing vector databases. [OpenAI Assistant Swarm][assistant-swarm]: Turn your entire library of OpenAI assistants into one single army commanded from a single agent. [![][back-to-top]](#readme-top) Copyright © 2025 [Mintplex Labs][profile-link]. This project is MIT licensed. [back-to-top]: https://img.shields.io/badge/-BACKTOTOP-222628?style=flat-square [profile-link]: https://github.com/mintplex-labs [vector-admin]: https://github.com/mintplex-labs/vector-admin [assistant-swarm]: https://github.com/Mintplex-Labs/openai-assistant-swarm [docker-btn]: ./images/deployBtns/docker.png [docker-deploy]: ./docker/HOWTOUSE_DOCKER.md [aws-btn]: ./images/deployBtns/aws.png [aws-deploy]: ./cloud-deployments/aws/cloudformation/DEPLOY.md [gcp-btn]: https://deploy.cloud.run/button.svg [gcp-deploy]: ./cloud-deployments/gcp/deployment/DEPLOY.md [do-btn]: https://www.deploytodo.com/do-btn-blue.svg [do-deploy]: ./cloud-deployments/digitalocean/terraform/DEPLOY.md [render-btn]: https://render.com/images/deploy-to-render-button.svg [render-deploy]: https://render.com/deploy?repo=https://github.com/Mintplex-Labs/anything-llm&branch=render [render-btn]: https://render.com/images/deploy-to-render-button.svg [render-deploy]: https://render.com/deploy?repo=https://github.com/Mintplex-Labs/anything-llm&branch=render [railway-btn]: https://railway.app/button.svg [railway-deploy]: https://railway.app/template/HNSCS1?referralCode=WFgJkn [repocloud-btn]: https://d16t0pc4846x52.cloudfront.net/deploylobe.svg [repocloud-deploy]: https://repocloud.io/details/?app_id=276 [elestio-btn]: https://elest.io/images/logos/deploy-to-elestio-btn.png [elestio-deploy]: https://elest.io/open-source/anythingllm

#github #anything-llm

0.447

0.1014145151561518

superiorlu•Mar 28, 2025

AITreasureBox

AI TreasureBox English | 中文 Collect practical AI repos, tools, websites, papers and tutorials on AI. Translated from ChatGPT, picture from Midjourney. Catalog Repos Tools Websites Report&Paper Tutorials Repos updated repos and stars every 2 hours and re-ranking automatically. | No. | Repos | Description | | ----:|:-----------------------------------------|:------------------------------------------------------------------------------------------------------| | 1|🔥codecrafters-io/build-your-own-x !2025-03-28364681428|Master programming by recreating your favorite technologies from scratch.| | 2|sindresorhus/awesome !2025-03-28353614145|😎 Awesome lists about all kinds of interesting topics| | 3|public-apis/public-apis !2025-03-28334299125|A collective list of free APIs| | 4|kamranahmedse/developer-roadmap !2025-03-2831269540|Interactive roadmaps, guides and other educational content to help developers grow in their careers.| | 5|vinta/awesome-python !2025-03-28238581114|A curated list of awesome Python frameworks, libraries, software and resources| | 6|practical-tutorials/project-based-learning !2025-03-28222661124|Curated list of project-based tutorials| | 7|tensorflow/tensorflow !2025-03-281888714|An Open Source Machine Learning Framework for Everyone| | 8|Significant-Gravitas/AutoGPT !2025-03-2817391338|An experimental open-source attempt to make GPT-4 fully autonomous.| | 9|jackfrued/Python-100-Days !2025-03-2816305141|Python - 100天从新手到大师| | 10|AUTOMATIC1111/stable-diffusion-webui !2025-03-2815011553|Stable Diffusion web UI| | 11|huggingface/transformers !2025-03-2814207850|🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.| | 12|ollama/ollama !2025-03-28135166151|Get up and running with Llama 2, Mistral, Gemma, and other large language models.| | 13|f/awesome-chatgpt-prompts !2025-03-2812212738 |This repo includes ChatGPT prompt curation to use ChatGPT better.| | 14|justjavac/free-programming-books-zhCN !2025-03-2811316119|📚 免费的计算机编程类中文书籍，欢迎投稿| | 15|krahets/hello-algo !2025-03-2811107930|《Hello 算法》：动画图解、一键运行的数据结构与算法教程。支持 Python, Java, C++, C, C#, JS, Go, Swift, Rust, Ruby, Kotlin, TS, Dart 代码。简体版和繁体版同步更新，English version ongoing| | 16|yt-dlp/yt-dlp !2025-03-28105801114|A feature-rich command-line audio/video downloader| | 17|langchain-ai/langchain !2025-03-2810449479|⚡ Building applications with LLMs through composability ⚡| | 18|goldbergyoni/nodebestpractices !2025-03-281021629|✅ The Node.js best practices list (July 2024)| | 19|puppeteer/puppeteer !2025-03-289018212|JavaScript API for Chrome and Firefox| | 20|pytorch/pytorch !2025-03-288833938|Tensors and Dynamic neural networks in Python with strong GPU acceleration| | 21|neovim/neovim !2025-03-288781482|Vim-fork focused on extensibility and usability| | 22|🔥🔥langgenius/dify !2025-03-2887342639 |One API for plugins and datasets, one interface for prompt engineering and visual operation, all for creating powerful AI applications.| | 23|mtdvio/every-programmer-should-know !2025-03-28867069|A collection of (mostly) technical things every software developer should know about| | 24|open-webui/open-webui !2025-03-2886025159|User-friendly WebUI for LLMs (Formerly Ollama WebUI)| | 25|ChatGPTNextWeb/NextChat !2025-03-288231521|✨ Light and Fast AI Assistant. Support: Web | | 26|supabase/supabase !2025-03-287990956|The open source Firebase alternative.| | 27|openai/whisper !2025-03-287905542|Robust Speech Recognition via Large-Scale Weak Supervision| | 28|home-assistant/core !2025-03-287773219|🏡 Open source home automation that puts local control and privacy first.| | 29|tensorflow/models !2025-03-28774694|Models and examples built with TensorFlow| | 30| ggerganov/llama.cpp !2025-03-287731836 | Port of Facebook's LLaMA model in C/C++ | | 31|3b1b/manim !2025-03-287641918|Animation engine for explanatory math videos| | 32|microsoft/generative-ai-for-beginners !2025-03-287623860|12 Lessons, Get Started Building with Generative AI 🔗 https://microsoft.github.io/generative-ai-for-beginners/| | 33|nomic-ai/gpt4all !2025-03-28729285 |gpt4all: an ecosystem of open-source chatbots trained on a massive collection of clean assistant data including code, stories and dialogue| | 34|comfyanonymous/ComfyUI !2025-03-2872635111|The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.| | 35|bregman-arie/devops-exercises !2025-03-2872225209|Linux, Jenkins, AWS, SRE, Prometheus, Docker, Python, Ansible, Git, Kubernetes, Terraform, OpenStack, SQL, NoSQL, Azure, GCP, DNS, Elastic, Network, Virtualization. DevOps Interview Questions| | 36|elastic/elasticsearch !2025-03-28721419|Free and Open, Distributed, RESTful Search Engine| | 37|🔥n8n-io/n8n !2025-03-2872093495|Free and source-available fair-code licensed workflow automation tool. Easily automate tasks across different services.| | 38|fighting41love/funNLP !2025-03-287200422|The Most Powerful NLP-Weapon Arsenal| | 39|hoppscotch/hoppscotch !2025-03-287060134|Open source API development ecosystem - https://hoppscotch.io (open-source alternative to Postman, Insomnia)| | 40|abi/screenshot-to-code !2025-03-286932817|Drop in a screenshot and convert it to clean HTML/Tailwind/JS code| | 41|binary-husky/gptacademic !2025-03-28680374|Academic Optimization of GPT| | 42|d2l-ai/d2l-zh !2025-03-286774142|Targeting Chinese readers, functional and open for discussion. The Chinese and English versions are used for teaching in over 400 universities across more than 60 countries| | 43|josephmisiti/awesome-machine-learning !2025-03-286739215|A curated list of awesome Machine Learning frameworks, libraries and software.| | 44|grafana/grafana !2025-03-286725414|The open and composable observability and data visualization platform. Visualize metrics, logs, and traces from multiple sources like Prometheus, Loki, Elasticsearch, InfluxDB, Postgres and many more.| | 45|python/cpython !2025-03-286602218|The Python programming language| | 46|apache/superset !2025-03-286519020|Apache Superset is a Data Visualization and Data Exploration Platform| | 47|xtekky/gpt4free !2025-03-28639391 |decentralizing the Ai Industry, free gpt-4/3.5 scripts through several reverse engineered API's ( poe.com, phind.com, chat.openai.com etc...)| | 48|sherlock-project/sherlock !2025-03-286332536|Hunt down social media accounts by username across social networks| | 49|twitter/the-algorithm !2025-03-28630586 |Source code for Twitter's Recommendation Algorithm| | 50|keras-team/keras !2025-03-28627835|Deep Learning for humans| | 51|openai/openai-cookbook !2025-03-28625136 |Examples and guides for using the OpenAI API| | 52|immich-app/immich !2025-03-286238670|High performance self-hosted photo and video management solution.| | 53|AppFlowy-IO/AppFlowy !2025-03-286173528|Bring projects, wikis, and teams together with AI. AppFlowy is an AI collaborative workspace where you achieve more without losing control of your data. The best open source alternative to Notion.| | 54|scikit-learn/scikit-learn !2025-03-286158212|scikit-learn: machine learning in Python| | 55|binhnguyennus/awesome-scalability !2025-03-286117021|The Patterns of Scalable, Reliable, and Performant Large-Scale Systems| | 56|labmlai/annotateddeeplearningpaperimplementations !2025-03-285951726|🧑‍🏫 59 Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠| | 57|OpenInterpreter/open-interpreter !2025-03-285894710|A natural language interface for computers| | 58|lobehub/lobe-chat !2025-03-285832054|🤖 Lobe Chat - an open-source, extensible (Function Calling), high-performance chatbot framework. It supports one-click free deployment of your private ChatGPT/LLM web application.| | 59|meta-llama/llama !2025-03-28579536|Inference code for Llama models| | 60|nuxt/nuxt !2025-03-28566437|The Intuitive Vue Framework.| | 61|imartinez/privateGPT !2025-03-28555192|Interact with your documents using the power of GPT, 100% privately, no data leaks| | 62|Stirling-Tools/Stirling-PDF !2025-03-285500846|#1 Locally hosted web application that allows you to perform various operations on PDF files| | 63|PlexPt/awesome-chatgpt-prompts-zh !2025-03-285459720|ChatGPT Chinese Training Guide. Guidelines for various scenarios. Learn how to make it listen to you| | 64|dair-ai/Prompt-Engineering-Guide !2025-03-285451025 |🐙 Guides, papers, lecture, notebooks and resources for prompt engineering| | 65|ageitgey/facerecognition !2025-03-28544382|The world's simplest facial recognition api for Python and the command line| | 66|CorentinJ/Real-Time-Voice-Cloning !2025-03-285384814|Clone a voice in 5 seconds to generate arbitrary speech in real-time| | 67|geekan/MetaGPT !2025-03-285375376|The Multi-Agent Meta Programming Framework: Given one line Requirement, return PRD, Design, Tasks, Repo | | 68|gpt-engineer-org/gpt-engineer !2025-03-285367419|Specify what you want it to build, the AI asks for clarification, and then builds it.| | 69|lencx/ChatGPT !2025-03-2853653-3|🔮 ChatGPT Desktop Application (Mac, Windows and Linux)| | 70|deepfakes/faceswap !2025-03-28535672|Deepfakes Software For All| | 71|langflow-ai/langflow !2025-03-285319584|Langflow is a low-code app builder for RAG and multi-agent AI applications. It’s Python-based and agnostic to any model, API, or database.| | 72|commaai/openpilot !2025-03-28529759|openpilot is an operating system for robotics. Currently, it upgrades the driver assistance system on 275+ supported cars.| | 73|clash-verge-rev/clash-verge-rev !2025-03-2852848124|Continuation of Clash Verge - A Clash Meta GUI based on Tauri (Windows, MacOS, Linux)| | 74|All-Hands-AI/OpenHands !2025-03-285150675|🙌 OpenHands: Code Less, Make More| | 75|xai-org/grok-1 !2025-03-28502504|Grok open release| | 76|meilisearch/meilisearch !2025-03-284999122|A lightning-fast search API that fits effortlessly into your apps, websites, and workflow| | 77|🔥browser-use/browser-use !2025-03-2849910294|Make websites accessible for AI agents| | 78|jgthms/bulma !2025-03-28496783|Modern CSS framework based on Flexbox| | 79|facebookresearch/segment-anything !2025-03-284947116|The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.| |!green-up-arrow.svg 80|hacksider/Deep-Live-Cam !2025-03-2848612146|real time face swap and one-click video deepfake with only a single image (uncensored)| |!red-down-arrow 81|mlabonne/llm-course !2025-03-284860934|Course with a roadmap and notebooks to get into Large Language Models (LLMs).| | 82|PaddlePaddle/PaddleOCR !2025-03-284785530|Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and deployment among server, mobile, embedded and IoT devices)| | 83|alist-org/alist !2025-03-284732618|🗂️A file list/WebDAV program that supports multiple storages, powered by Gin and Solidjs. / 一个支持多存储的文件列表/WebDAV程序，使用 Gin 和 Solidjs。| | 84|infiniflow/ragflow !2025-03-2847027129|RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.| | 85|Avik-Jain/100-Days-Of-ML-Code !2025-03-284679312|100 Days of ML Coding| | 86|v2ray/v2ray-core !2025-03-28458706|A platform for building proxies to bypass network restrictions.| | 87|hiyouga/LLaMA-Factory !2025-03-284555881|Easy-to-use LLM fine-tuning framework (LLaMA, BLOOM, Mistral, Baichuan, Qwen, ChatGLM)| | 88|Asabeneh/30-Days-Of-Python !2025-03-284544930|30 days of Python programming challenge is a step-by-step guide to learn the Python programming language in 30 days. This challenge may take more than100 days, follow your own pace. These videos may help too: https://www.youtube.com/channel/UC7PNRuno1rzYPb1xLa4yktw| | 89|type-challenges/type-challenges !2025-03-284488511|Collection of TypeScript type challenges with online judge| | 90|lllyasviel/Fooocus !2025-03-284402716|Focus on prompting and generating| | 91|RVC-Boss/GPT-SoVITS !2025-03-284327738|1 min voice data can also be used to train a good TTS model! (few shot voice cloning)| | 92|rasbt/LLMs-from-scratch !2025-03-284320667|Implementing a ChatGPT-like LLM from scratch, step by step| | 93|oobabooga/text-generation-webui !2025-03-284302012 |A gradio web UI for running Large Language Models like LLaMA, llama.cpp, GPT-J, OPT, and GALACTICA.| | 94|vllm-project/vllm !2025-03-2842982102|A high-throughput and memory-efficient inference and serving engine for LLMs| | 95|dani-garcia/vaultwarden !2025-03-284297121|Unofficial Bitwarden compatible server written in Rust, formerly known as bitwarden_rs| | 96|microsoft/autogen !2025-03-284233049|Enable Next-Gen Large Language Model Applications. Join our Discord: https://discord.gg/pAbnFJrkgZ| | 97|jeecgboot/JeecgBoot !2025-03-284205920|🔥「企业级低代码平台」前后端分离架构SpringBoot 2.x/3.x，SpringCloud，Ant Design&Vue3，Mybatis，Shiro，JWT。强大的代码生成器让前后端代码一键生成，无需写任何代码! 引领新的开发模式OnlineCoding->代码生成->手工MERGE，帮助Java项目解决70%重复工作，让开发更关注业务，既能快速提高效率，帮助公司节省成本，同时又不失灵活性。| | 98|Mintplex-Labs/anything-llm !2025-03-284186955|A full-stack application that turns any documents into an intelligent chatbot with a sleek UI and easier way to manage your workspaces.| | 99|THUDM/ChatGLM-6B !2025-03-28410192 |ChatGLM-6B: An Open Bilingual Dialogue Language Model| | 100|hpcaitech/ColossalAI !2025-03-28406902|Making large AI models cheaper, faster and more accessible| | 101|Stability-AI/stablediffusion !2025-03-28406337|High-Resolution Image Synthesis with Latent Diffusion Models| | 102|mingrammer/diagrams !2025-03-28405063|🎨 Diagram as Code for prototyping cloud system architectures| | 103|Kong/kong !2025-03-28404616|🦍 The Cloud-Native API Gateway and AI Gateway.| | 104|getsentry/sentry !2025-03-284040913|Developer-first error tracking and performance monitoring| | 105| karpathy/nanoGPT !2025-03-284034613 |The simplest, fastest repository for training/finetuning medium-sized GPTs| | 106|fastlane/fastlane !2025-03-2840014-1|🚀 The easiest way to automate building and releasing your iOS and Android apps| | 107|psf/black !2025-03-28399765|The uncompromising Python code formatter| | 108|OpenBB-finance/OpenBBTerminal !2025-03-283972074 |Investment Research for Everyone, Anywhere.| | 109|2dust/v2rayNG !2025-03-283943415|A V2Ray client for Android, support Xray core and v2fly core| | 110|apache/airflow !2025-03-283937314|Apache Airflow - A platform to programmatically author, schedule, and monitor workflows| | 111|KRTirtho/spotube !2025-03-283902746|🎧 Open source Spotify client that doesn't require Premium nor uses Electron! Available for both desktop & mobile!| | 112|coqui-ai/TTS !2025-03-283889719 |🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production| | 113|ggerganov/whisper.cpp !2025-03-283882116|Port of OpenAI's Whisper model in C/C++| | 114|ultralytics/ultralytics !2025-03-283866951|NEW - YOLOv8 🚀 in PyTorch > ONNX > OpenVINO > CoreML > TFLite| | 115|typst/typst !2025-03-283863914|A new markup-based typesetting system that is powerful and easy to learn.| | 116|streamlit/streamlit !2025-03-283845828|Streamlit — A faster way to build and share data apps.| | 117|LC044/WeChatMsg !2025-03-283836931|提取微信聊天记录，将其导出成HTML、Word、Excel文档永久保存，对聊天记录进行分析生成年度聊天报告，用聊天数据训练专属于个人的AI聊天助手| | 118|lm-sys/FastChat !2025-03-283822112 |An open platform for training, serving, and evaluating large languages. Release repo for Vicuna and FastChat-T5.| | 119|NaiboWang/EasySpider !2025-03-283819013|A visual no-code/code-free web crawler/spider易采集：一个可视化浏览器自动化测试/数据采集/爬虫软件，可以无代码图形化的设计和执行爬虫任务。别名：ServiceWrapper面向Web应用的智能化服务封装系统。| | 120|microsoft/DeepSpeed !2025-03-283765816 |A deep learning optimization library that makes distributed training and inference easy, efficient, and effective| | 121|QuivrHQ/quivr !2025-03-28376067|Your GenAI Second Brain 🧠 A personal productivity assistant (RAG) ⚡️🤖 Chat with your docs (PDF, CSV, ...) & apps using Langchain, GPT 3.5 / 4 turbo, Private, Anthropic, VertexAI, Ollama, LLMs, that you can share with users ! Local & Private alternative to OpenAI GPTs & ChatGPT powered by retrieval-augmented generation.| | 122|freqtrade/freqtrade !2025-03-283757817 |Free, open source crypto trading bot| | 123|suno-ai/bark !2025-03-28373178 |🔊 Text-Prompted Generative Audio Model| | 124|🔥cline/cline !2025-03-2837307282|Autonomous coding agent right in your IDE, capable of creating/editing files, executing commands, and more with your permission every step of the way.| | 125|LAION-AI/Open-Assistant !2025-03-28372712 |OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.| | 126|penpot/penpot !2025-03-283716217|Penpot: The open-source design tool for design and code collaboration| | 127|gradio-app/gradio !2025-03-283713320|Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!| | 128|FlowiseAI/Flowise !2025-03-283667135 |Drag & drop UI to build your customized LLM flow using LangchainJS| | 129|SimplifyJobs/Summer2025-Internships !2025-03-28366506|Collection of Summer 2025 tech internships!| | 130|TencentARC/GFPGAN !2025-03-28365027 |GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.| | 131|ray-project/ray !2025-03-283626819|Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a toolkit of libraries (Ray AIR) for accelerating ML workloads.| | 132|babysor/MockingBird !2025-03-28360498|🚀AI拟声: 5秒内克隆您的声音并生成任意语音内容 Clone a voice in 5 seconds to generate arbitrary speech in real-time| | 133|unslothai/unsloth !2025-03-283603691|5X faster 50% less memory LLM finetuning| | 134|zhayujie/chatgpt-on-wechat !2025-03-283600124 |Wechat robot based on ChatGPT, which uses OpenAI api and itchat library| | 135|upscayl/upscayl !2025-03-283599824|🆙 Upscayl - Free and Open Source AI Image Upscaler for Linux, MacOS and Windows built with Linux-First philosophy.| | 136|freeCodeCamp/devdocs !2025-03-28359738|API Documentation Browser| | 137|XingangPan/DragGAN !2025-03-28359043 |Code for DragGAN (SIGGRAPH 2023)| | 138|2noise/ChatTTS !2025-03-283543922|ChatTTS is a generative speech model for daily dialogue.| | 139|google-research/google-research !2025-03-28352207 |Google Research| | 140|karanpratapsingh/system-design !2025-03-28351003|Learn how to design systems at scale and prepare for system design interviews| | 141|lapce/lapce !2025-03-28350855|Lightning-fast and Powerful Code Editor written in Rust| | 142| microsoft/TaskMatrix !2025-03-2834500-3 | Talking, Drawing and Editing with Visual Foundation Models| | 143|chatchat-space/Langchain-Chatchat !2025-03-283442020|Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM) QA app with langchain| | 144|unclecode/crawl4ai !2025-03-283434163|🔥🕷️ Crawl4AI: Open-source LLM Friendly Web Crawler & Scrapper| | 145|Bin-Huang/chatbox !2025-03-283374733 |A desktop app for GPT-4 / GPT-3.5 (OpenAI API) that supports Windows, Mac & Linux| | 146|milvus-io/milvus !2025-03-283366525 |A cloud-native vector database, storage for next generation AI applications| | 147|mendableai/firecrawl !2025-03-2833297128|🔥 Turn entire websites into LLM-ready markdown| | 148|pola-rs/polars !2025-03-283269320|Fast multi-threaded, hybrid-out-of-core query engine focussing on DataFrame front-ends| | 149|Pythagora-io/gpt-pilot !2025-03-28325321|PoC for a scalable dev tool that writes entire apps from scratch while the developer oversees the implementation| | 150|hashicorp/vault !2025-03-28320797|A tool for secrets management, encryption as a service, and privileged access management| | 151|shardeum/shardeum !2025-03-28319580|Shardeum is an EVM based autoscaling blockchain| | 152|Chanzhaoyu/chatgpt-web !2025-03-28319242 |A demonstration website built with Express and Vue3 called ChatGPT| | 153|lllyasviel/ControlNet !2025-03-283186413 |Let us control diffusion models!| | 154|google/jax !2025-03-28317727|Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more| | 155|facebookresearch/detectron2 !2025-03-28315987|Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.| | 156|myshell-ai/OpenVoice !2025-03-28315233|Instant voice cloning by MyShell| | 157|TheAlgorithms/C-Plus-Plus !2025-03-283151411|Collection of various algorithms in mathematics, machine learning, computer science and physics implemented in C++ for educational purposes.| | 158|hiroi-sora/Umi-OCR !2025-03-283138129|OCR图片转文字识别软件，完全离线。截屏/批量导入图片，支持多国语言、合并段落、竖排文字。可排除水印区域，提取干净的文本。基于 PaddleOCR 。| | 159|mudler/LocalAI !2025-03-283127815|🤖 The free, Open Source OpenAI alternative. Self-hosted, community-driven and local-first. Drop-in replacement for OpenAI running on consumer-grade hardware. No GPU required. Runs gguf, transformers, diffusers and many more models architectures. It allows to generate Text, Audio, Video, Images. Also with voice cloning capabilities.| | 160|facebookresearch/fairseq !2025-03-28312124 |Facebook AI Research Sequence-to-Sequence Toolkit written in Python.| | 161|alibaba/nacos !2025-03-28310559|an easy-to-use dynamic service discovery, configuration and service management platform for building cloud native applications.| | 162|yunjey/pytorch-tutorial !2025-03-28310326|PyTorch Tutorial for Deep Learning Researchers| | 163|v2fly/v2ray-core !2025-03-28307448|A platform for building proxies to bypass network restrictions.| | 164|mckaywrigley/chatbot-ui !2025-03-283067714|The open-source AI chat interface for everyone.| | 165|TabbyML/tabby !2025-03-28305949 |Self-hosted AI coding assistant| | 166|deepseek-ai/awesome-deepseek-integration !2025-03-283053193|| | 167|danielmiessler/fabric !2025-03-283028914|fabric is an open-source framework for augmenting humans using AI.| | 168|xinntao/Real-ESRGAN !2025-03-283026623 |Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.| | 169|paul-gauthier/aider !2025-03-283014642|aider is GPT powered coding in your terminal| | 170|tatsu-lab/stanfordalpaca !2025-03-28299022 |Code and documentation to train Stanford's Alpaca models, and generate the data.| | 171|DataTalksClub/data-engineering-zoomcamp !2025-03-282971817|Free Data Engineering course!| | 172|HeyPuter/puter !2025-03-282967014|🌐 The Internet OS! Free, Open-Source, and Self-Hostable.| | 173|mli/paper-reading !2025-03-282962314|Classic Deep Learning and In-Depth Reading of New Papers Paragraph by Paragraph| | 174|linexjlin/GPTs !2025-03-28295568|leaked prompts of GPTs| | 175|s0md3v/roop !2025-03-28295286 |one-click deepfake (face swap)| | 176|JushBJJ/Mr.-Ranedeer-AI-Tutor !2025-03-2829465-1 |A GPT-4 AI Tutor Prompt for customizable personalized learning experiences.| | 177|opendatalab/MinerU !2025-03-282927074|A one-stop, open-source, high-quality data extraction tool, supports PDF/webpage/e-book extraction.一站式开源高质量数据提取工具，支持PDF/网页/多格式电子书提取。| | 178|mouredev/Hello-Python !2025-03-282920720|Curso para aprender el lenguaje de programación Python desde cero y para principiantes. 75 clases, 37 horas en vídeo, código, proyectos y grupo de chat. Fundamentos, frontend, backend, testing, IA...| | 179|Lightning-AI/pytorch-lightning !2025-03-28292039|Pretrain, finetune and deploy AI models on multiple GPUs, TPUs with zero code changes.| | 180|crewAIInc/crewAI !2025-03-282919344|Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.| | 181|facebook/folly !2025-03-282916612|An open-source C++ library developed and used at Facebook.| | 182|google-ai-edge/mediapipe !2025-03-28291519|Cross-platform, customizable ML solutions for live and streaming media.| | 183| getcursor/cursor !2025-03-282892025 | An editor made for programming with AI| | 184|chatanywhere/GPTAPIfree !2025-03-282856424|Free ChatGPT API Key, Free ChatGPT API, supports GPT-4 API (free), ChatGPT offers a free domestic forwarding API that allows direct connections without the need for a proxy. It can be used in conjunction with software/plugins like ChatBox, significantly reducing interface usage costs. Enjoy unlimited and unrestricted chatting within China| | 185|meta-llama/llama3 !2025-03-28285552|The official Meta Llama 3 GitHub site| | 186|tinygrad/tinygrad !2025-03-282845811|You like pytorch? You like micrograd? You love tinygrad! ❤️| | 187|google-research/tuningplaybook !2025-03-282841514|A playbook for systematically maximizing the performance of deep learning models.| | 188|huggingface/diffusers !2025-03-282830222|🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX.| | 189|tokio-rs/tokio !2025-03-28282408|A runtime for writing reliable asynchronous applications with Rust. Provides I/O, networking, scheduling, timers, ...| | 190|RVC-Project/Retrieval-based-Voice-Conversion-WebUI !2025-03-282823817|Voice data !2025-03-282822612|Jan is an open source alternative to ChatGPT that runs 100% offline on your computer| | 192|openai/CLIP !2025-03-282814720|CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image| | 193|🔥khoj-ai/khoj !2025-03-2828112313|Your AI second brain. A copilot to get answers to your questions, whether they be from your own notes or from the internet. Use powerful, online (e.g gpt4) or private, local (e.g mistral) LLMs. Self-host locally or use our web app. Access from Obsidian, Emacs, Desktop app, Web or Whatsapp.| | 194| acheong08/ChatGPT !2025-03-2828054-2 | Reverse engineered ChatGPT API | | 195|iperov/DeepFaceLive !2025-03-28279345 |Real-time face swap for PC streaming or video calls| | 196|eugeneyan/applied-ml !2025-03-28278471|📚 Papers & tech blogs by companies sharing their work on data science & machine learning in production.| | 197|XTLS/Xray-core !2025-03-282778213|Xray, Penetrates Everything. Also the best v2ray-core, with XTLS support. Fully compatible configuration.| | 198|feder-cr/JobsApplierAIAgent !2025-03-282776410|AutoJobsApplierAI_Agent aims to easy job hunt process by automating the job application process. Utilizing artificial intelligence, it enables users to apply for multiple jobs in an automated and personalized way.| | 199|mindsdb/mindsdb !2025-03-282750631|The platform for customizing AI from enterprise data| | 200|DataExpert-io/data-engineer-handbook !2025-03-282721611|This is a repo with links to everything you'd ever want to learn about data engineering| | 201|exo-explore/exo !2025-03-282721633|Run your own AI cluster at home with everyday devices 📱💻 🖥️⌚| | 202|taichi-dev/taichi !2025-03-2826926-1|Productive, portable, and performant GPU programming in Python.| | 203|mem0ai/mem0 !2025-03-282689134|The memory layer for Personalized AI| | 204|svc-develop-team/so-vits-svc !2025-03-28268096 |SoftVC VITS Singing Voice Conversion| | 205|OpenBMB/ChatDev !2025-03-28265624|Create Customized Software using Natural Language Idea (through Multi-Agent Collaboration)| | 206|roboflow/supervision !2025-03-282632010|We write your reusable computer vision tools. 💜| | 207|drawdb-io/drawdb !2025-03-282626913|Free, simple, and intuitive online database design tool and SQL generator.| | 208|karpathy/llm.c !2025-03-28261633|LLM training in simple, raw C/CUDA| | 209|airbnb/lottie-ios !2025-03-28261431|An iOS library to natively render After Effects vector animations| | 210|openai/openai-python !2025-03-282607713|The OpenAI Python library provides convenient access to the OpenAI API from applications written in the Python language.| | 211|academic/awesome-datascience !2025-03-28259876|📝 An awesome Data Science repository to learn and apply for real world problems.| | 212|harry0703/MoneyPrinterTurbo !2025-03-282576618|Generate short videos with one click using a large model| | 213|gabime/spdlog !2025-03-282571511|Fast C++ logging library.| | 214|ocrmypdf/OCRmyPDF !2025-03-2825674217|OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched| | 215|Vision-CAIR/MiniGPT-4 !2025-03-28256170 |Enhancing Vision-language Understanding with Advanced Large Language Models| | 216|Stability-AI/generative-models !2025-03-28255936|Generative Models by Stability AI| | 217|DS4SD/docling !2025-03-282555662|Get your docs ready for gen AI| | 218|PostHog/posthog !2025-03-282533227|🦔 PostHog provides open-source product analytics, session recording, feature flagging and A/B testing that you can self-host.| | 219|nrwl/nx !2025-03-282509612|Smart Monorepos · Fast CI| | 220|continuedev/continue !2025-03-282500737|⏩ the open-source copilot chat for software development—bring the power of ChatGPT to VS Code| | 221|opentofu/opentofu !2025-03-28247968|OpenTofu lets you declaratively manage your cloud infrastructure.| | 222|invoke-ai/InvokeAI !2025-03-28247293|InvokeAI is a leading creative engine for Stable Diffusion models, empowering professionals, artists, and enthusiasts to generate and create visual media using the latest AI-driven technologies. The solution offers an industry leading WebUI, supports terminal use through a CLI, and serves as the foundation for multiple commercial products.| | 223|deepinsight/insightface !2025-03-282471615 |State-of-the-art 2D and 3D Face Analysis Project| | 224|apache/flink !2025-03-28246865|Apache Flink| | 225|ComposioHQ/composio !2025-03-28246436|Composio equips agents with well-crafted tools empowering them to tackle complex tasks| | 226|Genesis-Embodied-AI/Genesis !2025-03-282458314|A generative world for general-purpose robotics & embodied AI learning.| | 227|stretchr/testify !2025-03-28243184|A toolkit with common assertions and mocks that plays nicely with the standard library| | 228| yetone/openai-translator !2025-03-28242921 | Browser extension and cross-platform desktop application for translation based on ChatGPT API | | 229|frappe/erpnext !2025-03-282425211|Free and Open Source Enterprise Resource Planning (ERP)| | 230|songquanpeng/one-api !2025-03-282410034|OpenAI 接口管理 & 分发系统，支持 Azure、Anthropic Claude、Google PaLM 2 & Gemini、智谱 ChatGLM、百度文心一言、讯飞星火认知、阿里通义千问、360 智脑以及腾讯混元，可用于二次分发管理 key，仅单可执行文件，已打包好 Docker 镜像，一键部署，开箱即用. OpenAI key management & redistribution system, using a single API for all LLMs, and features an English UI.| | 231| microsoft/JARVIS !2025-03-28240604 | a system to connect LLMs with ML community | | 232|google/flatbuffers !2025-03-28239965|FlatBuffers: Memory Efficient Serialization Library| | 233|microsoft/graphrag !2025-03-282398928|A modular graph-based Retrieval-Augmented Generation (RAG) system| | 234|rancher/rancher !2025-03-28239675|Complete container management platform| | 235|bazelbuild/bazel !2025-03-282384618|a fast, scalable, multi-language and extensible build system| | 236|modularml/mojo !2025-03-28238236 |The Mojo Programming Language| | 237|danny-avila/LibreChat !2025-03-282378753|Enhanced ChatGPT Clone: Features OpenAI, GPT-4 Vision, Bing, Anthropic, OpenRouter, Google Gemini, AI model switching, message search, langchain, DALL-E-3, ChatGPT Plugins, OpenAI Functions, Secure Multi-User System, Presets, completely open-source for self-hosting. More features in development| |!green-up-arrow.svg 238|🔥🔥🔥Shubhamsaboo/awesome-llm-apps !2025-03-28237391211|Collection of awesome LLM apps with RAG using OpenAI, Anthropic, Gemini and opensource models.| |!red-down-arrow 239|microsoft/semantic-kernel !2025-03-282373611|Integrate cutting-edge LLM technology quickly and easily into your apps| |!red-down-arrow 240|TheAlgorithms/Rust !2025-03-28236995|All Algorithms implemented in Rust| | 241|stanford-oval/storm !2025-03-28236326|An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.| | 242|openai/gpt-2 !2025-03-28232483|Code for the paper "Language Models are Unsupervised Multitask Learners"| | 243|labring/FastGPT !2025-03-282319445|A platform that uses the OpenAI API to quickly build an AI knowledge base, supporting many-to-many relationships.| | 244|pathwaycom/llm-app !2025-03-2822928-10|Ready-to-run cloud templates for RAG, AI pipelines, and enterprise search with live data. 🐳Docker-friendly.⚡Always in sync with Sharepoint, Google Drive, S3, Kafka, PostgreSQL, real-time data APIs, and more.| | 245|warpdotdev/Warp !2025-03-282286825|Warp is a modern, Rust-based terminal with AI built in so you and your team can build great software, faster.| | 246|🔥agno-agi/agno !2025-03-2822833298|Agno is a lightweight library for building Multimodal Agents. It exposes LLMs as a unified API and gives them superpowers like memory, knowledge, tools and reasoning.| | 247|qdrant/qdrant !2025-03-282275214 |Qdrant - Vector Database for the next generation of AI applications. Also available in the cloud https://cloud.qdrant.io/| | 248|ashishpatel26/500-AI-Machine-learning-Deep-learning-Computer-vision-NLP-Projects-with-code !2025-03-282271815|500 AI Machine learning Deep learning Computer vision NLP Projects with code| | 249|stanfordnlp/dspy !2025-03-282268321|Stanford DSPy: The framework for programming—not prompting—foundation models| | 250|PaddlePaddle/Paddle !2025-03-28226246|PArallel Distributed Deep LEarning: Machine Learning Framework from Industrial Practice （『飞桨』核心框架，深度学习&机器学习高性能单机、分布式训练和跨平台部署）| | 251|zulip/zulip !2025-03-28225464|Zulip server and web application. Open-source team chat that helps teams stay productive and focused.| | 252|Hannibal046/Awesome-LLM !2025-03-282240721|Awesome-LLM: a curated list of Large Language Model| | 253|facefusion/facefusion !2025-03-282218812|Next generation face swapper and enhancer| | 254|Mozilla-Ocho/llamafile !2025-03-28220624|Distribute and run LLMs with a single file.| | 255|yuliskov/SmartTube !2025-03-282201614|SmartTube - an advanced player for set-top boxes and tvs running Android OS| | 256|haotian-liu/LLaVA !2025-03-282201316 |Large Language-and-Vision Assistant built towards multimodal GPT-4 level capabilities.| | 257|ashishps1/awesome-system-design-resources !2025-03-282189367|This repository contains System Design resources which are useful while preparing for interviews and learning Distributed Systems| | 258|Cinnamon/kotaemon !2025-03-28218248|An open-source RAG-based tool for chatting with your documents.| | 259|CodePhiliaX/Chat2DB !2025-03-282179757|🔥🔥🔥AI-driven database tool and SQL client, The hottest GUI client, supporting MySQL, Oracle, PostgreSQL, DB2, SQL Server, DB2, SQLite, H2, ClickHouse, and more.| | 260|blakeblackshear/frigate !2025-03-282177113|NVR with realtime local object detection for IP cameras| | 261|facebookresearch/audiocraft !2025-03-28217111|Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable music generation LM with textual and melodic conditioning.| | 262|karpathy/minGPT !2025-03-28216567|A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training| | 263|grpc/grpc-go !2025-03-282159510|The Go language implementation of gRPC. HTTP/2 based RPC| | 264|HumanSignal/label-studio !2025-03-282137618|Label Studio is a multi-type data labeling and annotation tool with standardized output format| | 265|yoheinakajima/babyagi !2025-03-28212764 |uses OpenAI and Pinecone APIs to create, prioritize, and execute tasks, This is a pared-down version of the original Task-Driven Autonomous Agent| | 266|deepseek-ai/DeepSeek-Coder !2025-03-282118210|DeepSeek Coder: Let the Code Write Itself| | 267|BuilderIO/gpt-crawler !2025-03-282118010|Crawl a site to generate knowledge files to create your own custom GPT from a URL| | 268| openai/chatgpt-retrieval-plugin !2025-03-2821152-1 | Plugins are chat extensions designed specifically for language models like ChatGPT, enabling them to access up-to-date information, run computations, or interact with third-party services in response to a user's request.| | 269|microsoft/OmniParser !2025-03-282113123|A simple screen parsing tool towards pure vision based GUI agent| | 270|black-forest-labs/flux !2025-03-282107219|Official inference repo for FLUX.1 models| | 271|ItzCrazyKns/Perplexica !2025-03-282099154|Perplexica is an AI-powered search engine. It is an Open source alternative to Perplexity AI| | 272|microsoft/unilm !2025-03-28209876|Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities| | 273|Sanster/lama-cleaner !2025-03-282077614|Image inpainting tool powered by SOTA AI Model. Remove any unwanted object, defect, people from your pictures or erase and replace(powered by stable diffusion) any thing on your pictures.| | 274|assafelovic/gpt-researcher !2025-03-282057222|GPT based autonomous agent that does online comprehensive research on any given topic| | 275|PromtEngineer/localGPT !2025-03-28204230 |Chat with your documents on your local device using GPT models. No data leaves your device and 100% private.| | 276|elastic/kibana !2025-03-28203482|Your window into the Elastic Stack| | 277|fishaudio/fish-speech !2025-03-282033222|Brand new TTS solution| | 278|mlc-ai/mlc-llm !2025-03-282028110 |Enable everyone to develop, optimize and deploy AI models natively on everyone's devices.| | 279|deepset-ai/haystack !2025-03-282005320|🔍 Haystack is an open source NLP framework to interact with your data using Transformer models and LLMs (GPT-4, ChatGPT and alike). Haystack offers production-ready tools to quickly build complex question answering, semantic search, text generation applications, and more.| | 280|tree-sitter/tree-sitter !2025-03-28200487|An incremental parsing system for programming tools| | 281|Anjok07/ultimatevocalremovergui !2025-03-281999811|GUI for a Vocal Remover that uses Deep Neural Networks.| | 282|guidance-ai/guidance !2025-03-28199622|A guidance language for controlling large language models.| | 283|ml-explore/mlx !2025-03-28199619|MLX: An array framework for Apple silicon| | 284|mlflow/mlflow !2025-03-281995314|Open source platform for the machine learning lifecycle| | 285|ml-tooling/best-of-ml-python !2025-03-28198631|🏆 A ranked list of awesome machine learning Python libraries. Updated weekly.| | 286|BerriAI/litellm !2025-03-281981862|Call all LLM APIs using the OpenAI format. Use Bedrock, Azure, OpenAI, Cohere, Anthropic, Ollama, Sagemaker, HuggingFace, Replicate (100+ LLMs)| | 287|LazyVim/LazyVim !2025-03-281981320|Neovim config for the lazy| | 288|wez/wezterm !2025-03-281976018|A GPU-accelerated cross-platform terminal emulator and multiplexer written by @wez and implemented in Rust| | 289|valkey-io/valkey !2025-03-281970416|A flexible distributed key-value datastore that supports both caching and beyond caching workloads.| | 290|LiLittleCat/awesome-free-chatgpt !2025-03-28196185|🆓免费的 ChatGPT 镜像网站列表，持续更新。List of free ChatGPT mirror sites, continuously updated.| | 291|Byaidu/PDFMathTranslate !2025-03-281947645|PDF scientific paper translation with preserved formats - 基于 AI 完整保留排版的 PDF 文档全文双语翻译，支持 Google/DeepL/Ollama/OpenAI 等服务，提供 CLI/GUI/Docker| | 292|openai/swarm !2025-03-281947111|Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.| | 293|HqWu-HITCS/Awesome-Chinese-LLM !2025-03-281921423|Organizing smaller, cost-effective, privately deployable open-source Chinese language models, including related datasets and tutorials| | 294|stitionai/devika !2025-03-28190903|Devika is an Agentic AI Software Engineer that can understand high-level human instructions, break them down into steps, research relevant information, and write code to achieve the given objective. Devika aims to be a competitive open-source alternative to Devin by Cognition AI.| | 295|OpenBMB/MiniCPM-o !2025-03-28190887|MiniCPM-o 2.6: A GPT-4o Level MLLM for Vision, Speech and Multimodal Live Streaming on Your Phone| | 296|samber/lo !2025-03-281904815|💥 A Lodash-style Go library based on Go 1.18+ Generics (map, filter, contains, find...)| | 297|chroma-core/chroma !2025-03-281895221 |the AI-native open-source embedding database| | 298|DarkFlippers/unleashed-firmware !2025-03-28189278|Flipper Zero Unleashed Firmware| | 299|brave/brave-browser !2025-03-281892710|Brave browser for Android, iOS, Linux, macOS, Windows.| | 300| tloen/alpaca-lora !2025-03-28188641 | Instruct-tune LLaMA on consumer hardware| | 301|VinciGit00/Scrapegraph-ai !2025-03-281884618|Python scraper based on AI| | 302|gitroomhq/postiz-app !2025-03-281879110|📨 Schedule social posts, measure them, exchange with other members and get a lot of help from AI 🚀| | 303|PrefectHQ/prefect !2025-03-281878715|Prefect is a workflow orchestration tool empowering developers to build, observe, and react to data pipelines| | 304|ymcui/Chinese-LLaMA-Alpaca !2025-03-28187723 |Chinese LLaMA & Alpaca LLMs| | 305|kenjihiranabe/The-Art-of-Linear-Algebra !2025-03-28187335|Graphic notes on Gilbert Strang's "Linear Algebra for Everyone"| | 306|joonspk-research/generativeagents !2025-03-28187288|Generative Agents: Interactive Simulacra of Human Behavior| | 307|renovatebot/renovate !2025-03-28186820|Universal dependency update tool that fits into your workflows.| | 308|gventuri/pandas-ai !2025-03-28186109 |Pandas AI is a Python library that integrates generative artificial intelligence capabilities into Pandas, making dataframes conversational| | 309|thingsboard/thingsboard !2025-03-28185184|Open-source IoT Platform - Device management, data collection, processing and visualization.| | 310|ente-io/ente !2025-03-28184722|Fully open source, End to End Encrypted alternative to Google Photos and Apple Photos| | 311|serengil/deepface !2025-03-281840113|A Lightweight Face Recognition and Facial Attribute Analysis (Age, Gender, Emotion and Race) Library for Python| | 312|Raphire/Win11Debloat !2025-03-281840132|A simple, easy to use PowerShell script to remove pre-installed apps from windows, disable telemetry, remove Bing from windows search as well as perform various other changes to declutter and improve your windows experience. This script works for both windows 10 and windows 11.| | 313|Avaiga/taipy !2025-03-28179235|Turns Data and AI algorithms into production-ready web applications in no time.| | 314|microsoft/qlib !2025-03-281784231|Qlib is an AI-oriented quantitative investment platform that aims to realize the potential, empower research, and create value using AI technologies in quantitative investment, from exploring ideas to implementing productions. Qlib supports diverse machine learning modeling paradigms. including supervised learning, market dynamics modeling, and RL.| | 315|CopilotKit/CopilotKit !2025-03-281778571|Build in-app AI chatbots 🤖, and AI-powered Textareas ✨, into react web apps.| | 316|QwenLM/Qwen-7B !2025-03-281766017|The official repo of Qwen-7B (通义千问-7B) chat & pretrained large language model proposed by Alibaba Cloud.| | 317|w-okada/voice-changer !2025-03-28176078 |リアルタイムボイスチェンジャー Realtime Voice Changer| | 318|rlabbe/Kalman-and-Bayesian-Filters-in-Python !2025-03-281756011|Kalman Filter book using Jupyter Notebook. Focuses on building intuition and experience, not formal proofs. Includes Kalman filters,extended Kalman filters, unscented Kalman filters, particle filters, and more. All exercises include solutions.| | 319|Mikubill/sd-webui-controlnet !2025-03-28174794 |WebUI extension for ControlNet| | 320|jingyaogong/minimind !2025-03-2817380116|「大模型」3小时完全从0训练26M的小参数GPT，个人显卡即可推理训练！| | 321|apify/crawlee !2025-03-28172696|Crawlee—A web scraping and browser automation library for Node.js to build reliable crawlers. In JavaScript and TypeScript. Extract data for AI, LLMs, RAG, or GPTs. Download HTML, PDF, JPG, PNG, and other files from websites. Works with Puppeteer, Playwright, Cheerio, JSDOM, and raw HTTP. Both headful and headless mode. With proxy rotation.| | 322|apple/ml-stable-diffusion !2025-03-28172395|Stable Diffusion with Core ML on Apple Silicon| | 323| transitive-bullshit/chatgpt-api !2025-03-28172095 | Node.js client for the official ChatGPT API. | | 324|teableio/teable !2025-03-281719222|✨ The Next Gen Airtable Alternative: No-Code Postgres| | 325| xx025/carrot !2025-03-28170900 | Free ChatGPT Site List | | 326|microsoft/LightGBM !2025-03-28170723|A fast, distributed, high-performance gradient boosting (GBT, GBDT, GBRT, GBM or MART) framework based on decision tree algorithms, used for ranking, classification and many other machine learning tasks.| | 327|VikParuchuri/surya !2025-03-28169827|Accurate line-level text detection and recognition (OCR) in any language| | 328|deepseek-ai/Janus !2025-03-281692825|Janus-Series: Unified Multimodal Understanding and Generation Models| | 329|ardalis/CleanArchitecture !2025-03-28168823|Clean Architecture Solution Template: A starting point for Clean Architecture with ASP.NET Core| | 330|neondatabase/neon !2025-03-28166466|Neon: Serverless Postgres. We separated storage and compute to offer autoscaling, code-like database branching, and scale to zero.| | 331|kestra-io/kestra !2025-03-281661313|⚡ Workflow Automation Platform. Orchestrate & Schedule code in any language, run anywhere, 500+ plugins. Alternative to Zapier, Rundeck, Camunda, Airflow...| | 332|Dao-AILab/flash-attention !2025-03-281659720|Fast and memory-efficient exact attention| | 333|RPCS3/rpcs3 !2025-03-281655712|PS3 emulator/debugger| | 334|meta-llama/llama-recipes !2025-03-28165486|Scripts for fine-tuning Llama2 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization & question answering. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment.Demo apps to showcase Llama2 for WhatsApp & Messenger| | 335|emilwallner/Screenshot-to-code !2025-03-28165180|A neural network that transforms a design mock-up into a static website.| | 336|datawhalechina/llm-cookbook !2025-03-281650922|面向开发者的 LLM 入门教程，吴恩达大模型系列课程中文版| | 337|e2b-dev/awesome-ai-agents !2025-03-281643923|A list of AI autonomous agents| | 338|QwenLM/Qwen2.5 !2025-03-281641114|Qwen2.5 is the large language model series developed by Qwen team, Alibaba Cloud.| | 339|dair-ai/ML-YouTube-Courses !2025-03-28164114|📺 Discover the latest machine learning / AI courses on YouTube.| | 340|pybind/pybind11 !2025-03-28163620|Seamless operability between C++11 and Python| | 341|graphdeco-inria/gaussian-splatting !2025-03-281627116|Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"| | 342|meta-llama/codellama !2025-03-28162531|Inference code for CodeLlama models| | 343|TransformerOptimus/SuperAGI !2025-03-28161292 | SuperAGI - A dev-first open source autonomous AI agent framework. Enabling developers to build, manage & run useful autonomous agents quickly and reliably.| | 344|microsoft/onnxruntime !2025-03-28161169|ONNX Runtime: cross-platform, high-performance ML inferencing and training accelerator| | 345|IDEA-Research/Grounded-Segment-Anything !2025-03-281601411 |Marrying Grounding DINO with Segment Anything & Stable Diffusion & BLIP - Automatically Detect, Segment and Generate Anything with Image and Text Inputs| | 346|ddbourgin/numpy-ml !2025-03-28160054|Machine learning, in numpy| | 347|eosphoros-ai/DB-GPT !2025-03-281585225|Revolutionizing Database Interactions with Private LLM Technology| | 348|Stability-AI/StableLM !2025-03-28158310 |Stability AI Language Models| | 349|openai/evals !2025-03-28157935 |Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.| | 350|THUDM/ChatGLM2-6B !2025-03-28157500|ChatGLM2-6B: An Open Bilingual Chat LLM | | 351|sunner/ChatALL !2025-03-28156761 |Concurrently chat with ChatGPT, Bing Chat, Bard, Alpaca, Vincuna, Claude, ChatGLM, MOSS, iFlytek Spark, ERNIE and more, discover the best answers| | 352|abseil/abseil-cpp !2025-03-28156656|Abseil Common Libraries (C++)| | 353|NVIDIA/open-gpu-kernel-modules !2025-03-28156531|NVIDIA Linux open GPU kernel module source| | 354|letta-ai/letta !2025-03-281563718|Letta (formerly MemGPT) is a framework for creating LLM services with memory.| | 355|typescript-eslint/typescript-eslint !2025-03-28156211|✨ Monorepo for all the tooling which enables ESLint to support TypeScript| | 356|umijs/umi !2025-03-28156211|A framework in react community ✨| | 357|AI4Finance-Foundation/FinGPT !2025-03-281561215|Data-Centric FinGPT. Open-source for open finance! Revolutionize 🔥 We'll soon release the trained model.| | 358|amplication/amplication !2025-03-28156022|🔥🔥🔥 The Only Production-Ready AI-Powered Backend Code Generation| | 359|KindXiaoming/pykan !2025-03-28155477|Kolmogorov Arnold Networks| | 360|arc53/DocsGPT !2025-03-28154900|GPT-powered chat for documentation, chat with your documents| | 361|influxdata/telegraf !2025-03-28154502|Agent for collecting, processing, aggregating, and writing metrics, logs, and other arbitrary data.| | 362|microsoft/Bringing-Old-Photos-Back-to-Life !2025-03-28154084|Bringing Old Photo Back to Life (CVPR 2020 oral)| | 363|GaiZhenbiao/ChuanhuChatGPT !2025-03-2815394-2|GUI for ChatGPT API and many LLMs. Supports agents, file-based QA, GPT finetuning and query with web search. All with a neat UI.| | 364|Zeyi-Lin/HivisionIDPhotos !2025-03-281529710|⚡️HivisionIDPhotos: a lightweight and efficient AI ID photos tools. 一个轻量级的AI证件照制作算法。| | 365| mayooear/gpt4-pdf-chatbot-langchain !2025-03-281529518 | GPT4 & LangChain Chatbot for large PDF docs | | 366|1Panel-dev/MaxKB !2025-03-2815277148|? Based on LLM large language model knowledge base Q&A system. Ready to use out of the box, supports quick integration into third-party business systems. Officially produced by 1Panel| | 367|ai16z/eliza !2025-03-281526811|Conversational Agent for Twitter and Discord| | 368|apache/arrow !2025-03-28151684|Apache Arrow is a multi-language toolbox for accelerated data interchange and in-memory processing| | 369|princeton-nlp/SWE-agent !2025-03-281516119|SWE-agent: Agent Computer Interfaces Enable Software Engineering Language Models| | 370|mlc-ai/web-llm !2025-03-281509311 |Bringing large-language models and chat to web browsers. Everything runs inside the browser with no server support.| | 371|guillaumekln/faster-whisper !2025-03-281507117 |Faster Whisper transcription with CTranslate2| | 372|overleaf/overleaf !2025-03-28150316|A web-based collaborative LaTeX editor| | 373|triton-lang/triton !2025-03-28150169|Development repository for the Triton language and compiler| | 374|soxoj/maigret !2025-03-281500410|🕵️‍♂️ Collect a dossier on a person by username from thousands of sites| | 375|alibaba/lowcode-engine !2025-03-28149841|An enterprise-class low-code technology stack with scale-out design / 一套面向扩展设计的企业级低代码技术体系| | 376|espressif/esp-idf !2025-03-28148545|Espressif IoT Development Framework. Official development framework for Espressif SoCs.| | 377|pgvector/pgvector !2025-03-281484913|Open-source vector similarity search for Postgres| | 378|datawhalechina/leedl-tutorial !2025-03-28148246|《李宏毅深度学习教程》（李宏毅老师推荐👍），PDF下载地址：https://github.com/datawhalechina/leedl-tutorial/releases| | 379|xcanwin/KeepChatGPT !2025-03-28147972 |Using ChatGPT is more efficient and smoother, perfectly solving ChatGPT network errors. No longer do you need to frequently refresh the webpage, saving over 10 unnecessary steps| | 380|m-bain/whisperX !2025-03-281471313|WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)| | 381|HumanAIGC/AnimateAnyone !2025-03-2814706-1|Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation| |!green-up-arrow.svg 382|naklecha/llama3-from-scratch !2025-03-281469024|llama3 implementation one matrix multiplication at a time| |!red-down-arrow 383| fauxpilot/fauxpilot !2025-03-28146871 | An open-source GitHub Copilot server | | 384|LlamaFamily/Llama-Chinese !2025-03-28145111|Llama Chinese Community, the best Chinese Llama large model, fully open source and commercially available| | 385|BradyFU/Awesome-Multimodal-Large-Language-Models !2025-03-281450121|Latest Papers and Datasets on Multimodal Large Language Models| | 386|vanna-ai/vanna !2025-03-281449819|🤖 Chat with your SQL database 📊. Accurate Text-to-SQL Generation via LLMs using RAG 🔄.| | 387|bleedline/aimoneyhunter !2025-03-28144845|AI Side Hustle Money Mega Collection: Teaching You How to Utilize AI for Various Side Projects to Earn Extra Income.| | 388|stefan-jansen/machine-learning-for-trading !2025-03-28144629|Code for Machine Learning for Algorithmic Trading, 2nd edition.| | 389|state-spaces/mamba !2025-03-28144139|Mamba: Linear-Time Sequence Modeling with Selective State Spaces| | 390|vercel/ai-chatbot !2025-03-281434614|A full-featured, hackable Next.js AI chatbot built by Vercel| | 391|steven-tey/novel !2025-03-281428410|Notion-style WYSIWYG editor with AI-powered autocompletions| | 392|unifyai/ivy !2025-03-281409348|Unified AI| | 393|chidiwilliams/buzz !2025-03-281402411 |Buzz transcribes and translates audio offline on your personal computer. Powered by OpenAI's Whisper.| | 394|lukas-blecher/LaTeX-OCR !2025-03-28139769|pix2tex: Using a ViT to convert images of equations into LaTeX code.| | 395|openai/tiktoken !2025-03-28139599|tiktoken is a fast BPE tokeniser for use with OpenAI's models.| | 396|nocobase/nocobase !2025-03-281391522|NocoBase is a scalability-first, open-source no-code/low-code platform for building business applications and enterprise solutions.| | 397|neonbjb/tortoise-tts !2025-03-28139010 |A multi-voice TTS system trained with an emphasis on quality| | 398|yamadashy/repomix !2025-03-281382036|📦 Repomix (formerly Repopack) is a powerful tool that packs your entire repository into a single, AI-friendly file. Perfect for when you need to feed your codebase to Large Language Models (LLMs) or other AI tools like Claude, ChatGPT, and Gemini.| | 399|adobe/react-spectrum !2025-03-28136766|A collection of libraries and tools that help you build adaptive, accessible, and robust user experiences.| | 400|THUDM/ChatGLM3 !2025-03-28136684|ChatGLM3 series: Open Bilingual Chat LLMs | | 401|NVIDIA/NeMo !2025-03-28134837|A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)| | 402|BlinkDL/RWKV-LM !2025-03-28134346 |RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it combines the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.| | 403| fuergaosi233/wechat-chatgpt !2025-03-28133330 | Use ChatGPT On Wechat via wechaty | | 404|udecode/plate !2025-03-28133325|A rich-text editor powered by AI| | 405|xenova/transformers.js !2025-03-281331219|State-of-the-art Machine Learning for the web. Run 🤗 Transformers directly in your browser, with no need for a server!| | 406|stas00/ml-engineering !2025-03-281325615|Machine Learning Engineering Guides and Tools| | 407| wong2/chatgpt-google-extension !2025-03-2813241-1 | A browser extension that enhances search engines with ChatGPT, this repos will not be updated from 2023-02-20| | 408|mrdbourke/pytorch-deep-learning !2025-03-281317520|Materials for the Learn PyTorch for Deep Learning: Zero to Mastery course.| | 409|Koenkk/zigbee2mqtt !2025-03-28131544|Zigbee 🐝 to MQTT bridge 🌉, get rid of your proprietary Zigbee bridges 🔨| | 410|vercel-labs/ai !2025-03-281298528|Build AI-powered applications with React, Svelte, and Vue| | 411|netease-youdao/QAnything !2025-03-28129318|Question and Answer based on Anything.| | 412|huggingface/trl !2025-03-281289622|Train transformer language models with reinforcement learning.| | 413|microsoft/BitNet !2025-03-28128503|Official inference framework for 1-bit LLMs| | 414|mediar-ai/screenpipe !2025-03-281283915|24/7 local AI screen & mic recording. Build AI apps that have the full context. Works with Ollama. Alternative to Rewind.ai. Open. Secure. You own your data. Rust.| | 415|Skyvern-AI/skyvern !2025-03-281277612|Automate browser-based workflows with LLMs and Computer Vision| | 416|pytube/pytube !2025-03-28126591|A lightweight, dependency-free Python library (and command-line utility) for downloading YouTube Videos.| | 417|official-stockfish/Stockfish !2025-03-28126574|UCI chess engine| | 418|sgl-project/sglang !2025-03-281260143|SGLang is a structured generation language designed for large language models (LLMs). It makes your interaction with LLMs faster and more controllable.| | 419|plasma-umass/scalene !2025-03-28125535|Scalene: a high-performance, high-precision CPU, GPU, and memory profiler for Python with AI-powered optimization proposals| | 420|danswer-ai/danswer !2025-03-28125503|Ask Questions in natural language and get Answers backed by private sources. Connects to tools like Slack, GitHub, Confluence, etc.| | 421|OpenTalker/SadTalker !2025-03-28125226|[CVPR 2023] SadTalker：Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation| | 422|facebookresearch/AnimatedDrawings !2025-03-28123693 |Code to accompany "A Method for Animating Children's Drawings of the Human Figure"| | 423|activepieces/activepieces !2025-03-28123609|Your friendliest open source all-in-one automation tool ✨ Workflow automation tool 100+ integration / Enterprise automation tool / Zapier Alternative| | 424|ggerganov/ggml !2025-03-28121992 |Tensor library for machine learning| | 425|bytebase/bytebase !2025-03-28121694|World's most advanced database DevOps and CI/CD for Developer, DBA and Platform Engineering teams. The GitLab/GitHub for database DevOps.| | 426| willwulfken/MidJourney-Styles-and-Keywords-Reference !2025-03-28120971 | A reference containing Styles and Keywords that you can use with MidJourney AI| | 427|Huanshere/VideoLingo !2025-03-281207013|Netflix-level subtitle cutting, translation, alignment, and even dubbing - one-click fully automated AI video subtitle team | | 428|OpenLMLab/MOSS !2025-03-28120330 |An open-source tool-augmented conversational language model from Fudan University| | 429|llmware-ai/llmware !2025-03-281200727|Providing enterprise-grade LLM-based development framework, tools, and fine-tuned models.| | 430|PKU-YuanGroup/Open-Sora-Plan !2025-03-28119362|This project aim to reproduce Sora (Open AI T2V model), but we only have limited resource. We deeply wish the all open source community can contribute to this project.| | 431|ShishirPatil/gorilla !2025-03-28119332 |Gorilla: An API store for LLMs| | 432|NVIDIA/Megatron-LM !2025-03-281192716|Ongoing research training transformer models at scale| | 433|illacloud/illa-builder !2025-03-28119192|Create AI-Driven Apps like Assembling Blocks| | 434|marimo-team/marimo !2025-03-281191521|A reactive notebook for Python — run reproducible experiments, execute as a script, deploy as an app, and version with git.| | 435|smol-ai/developer !2025-03-28119111 | With 100k context windows on the way, it's now feasible for every dev to have their own smol developer| | 436|Lightning-AI/litgpt !2025-03-28118878|Pretrain, finetune, deploy 20+ LLMs on your own data. Uses state-of-the-art techniques: flash attention, FSDP, 4-bit, LoRA, and more.| | 437|openai/shap-e !2025-03-28118474 |Generate 3D objects conditioned on text or images| | 438|eugeneyan/open-llms !2025-03-28118451 |A list of open LLMs available for commercial use.| | 439|andrewyng/aisuite !2025-03-28118124|Simple, unified interface to multiple Generative AI providers| | 440|hajimehoshi/ebiten !2025-03-28117816|Ebitengine - A dead simple 2D game engine for Go| | 441|kgrzybek/modular-monolith-with-ddd !2025-03-28117493|Full Modular Monolith application with Domain-Driven Design approach.| | 442|h2oai/h2ogpt !2025-03-2811736-1 |Come join the movement to make the world's best open source GPT led by H2O.ai - 100% private chat and document search, no data leaks, Apache 2.0| | 443|owainlewis/awesome-artificial-intelligence !2025-03-28117332|A curated list of Artificial Intelligence (AI) courses, books, video lectures and papers.| | 444|DataTalksClub/mlops-zoomcamp !2025-03-28116643|Free MLOps course from DataTalks.Club| | 445|Rudrabha/Wav2Lip !2025-03-281163410|This repository contains the codes of "A Lip Sync Expert Is All You Need for Speech to Lip Generation In the Wild", published at ACM Multimedia 2020.| | 446|aishwaryanr/awesome-generative-ai-guide !2025-03-281152810|A one stop repository for generative AI research updates, interview resources, notebooks and much more!| | 447|karpathy/micrograd !2025-03-28115146|A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API| | 448|InstantID/InstantID !2025-03-28115111|InstantID : Zero-shot Identity-Preserving Generation in Seconds 🔥| | 449|facebookresearch/seamlesscommunication !2025-03-28114434|Foundational Models for State-of-the-Art Speech and Text Translation| | 450|anthropics/anthropic-cookbook !2025-03-281140112|A collection of notebooks/recipes showcasing some fun and effective ways of using Claude.| | 451|mastra-ai/mastra !2025-03-281139240|the TypeScript AI agent framework| | 452|NVIDIA/TensorRT !2025-03-28113864|NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.| | 453|plandex-ai/plandex !2025-03-28113645|An AI coding engine for complex tasks| | 454|RUCAIBox/LLMSurvey !2025-03-28112735 |A collection of papers and resources related to Large Language Models.| | 455|kubeshark/kubeshark !2025-03-28112711|The API traffic analyzer for Kubernetes providing real-time K8s protocol-level visibility, capturing and monitoring all traffic and payloads going in, out and across containers, pods, nodes and clusters. Inspired by Wireshark, purposely built for Kubernetes| | 456|electric-sql/pglite !2025-03-28112617|Lightweight Postgres packaged as WASM into a TypeScript library for the browser, Node.js, Bun and Deno from https://electric-sql.com| | 457|lightaime/camel !2025-03-281124441 |🐫 CAMEL: Communicative Agents for “Mind” Exploration of Large Scale Language Model Society| | 458|huggingface/lerobot !2025-03-281120184|🤗 LeRobot: State-of-the-art Machine Learning for Real-World Robotics in Pytorch| | 459|normal-computing/outlines !2025-03-28111657|Generative Model Programming| | 460|libretro/RetroArch !2025-03-28110701|Cross-platform, sophisticated frontend for the libretro API. Licensed GPLv3.| | 461|THUDM/CogVideo !2025-03-28110599|Text-to-video generation: CogVideoX (2024) and CogVideo (ICLR 2023)| | 462|bentoml/OpenLLM !2025-03-28110495|An open platform for operating large language models (LLMs) in production. Fine-tune, serve, deploy, and monitor any LLMs with ease.| | 463|vosen/ZLUDA !2025-03-28110429|CUDA on AMD GPUs| | 464|dair-ai/ML-Papers-of-the-Week !2025-03-28110304 |🔥Highlighting the top ML papers every week.| | 465|WordPress/gutenberg !2025-03-28110212|The Block Editor project for WordPress and beyond. Plugin is available from the official repository.| | 466|microsoft/data-formulator !2025-03-281099827|🪄 Create rich visualizations with AI| | 467|LibreTranslate/LibreTranslate !2025-03-28109887|Free and Open Source Machine Translation API. Self-hosted, offline capable and easy to setup.| | 468|block/goose !2025-03-281097737|an open-source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM| | 469|getumbrel/llama-gpt !2025-03-28109553|A self-hosted, offline, ChatGPT-like chatbot. Powered by Llama 2. 100% private, with no data leaving your device.| | 470|HigherOrderCO/HVM !2025-03-28109182|A massively parallel, optimal functional runtime in Rust| | 471|databrickslabs/dolly !2025-03-2810812-3 | A large language model trained on the Databricks Machine Learning Platform| | 472|srush/GPU-Puzzles !2025-03-28108014|Solve puzzles. Learn CUDA.| | 473|Z3Prover/z3 !2025-03-28107952|The Z3 Theorem Prover| | 474|UFund-Me/Qbot !2025-03-281079313 |Qbot is an AI-oriented quantitative investment platform, which aims to realize the potential, empower AI technologies in quantitative investment| | 475|langchain-ai/langgraph !2025-03-281077336|| | 476|lz4/lz4 !2025-03-28107647|Extremely Fast Compression algorithm| | 477|magic-research/magic-animate !2025-03-28107160|MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model| | 478|PaperMC/Paper !2025-03-281071410|The most widely used, high performance Minecraft server that aims to fix gameplay and mechanics inconsistencies| | 479|getomni-ai/zerox !2025-03-281071015|Zero shot pdf OCR with gpt-4o-mini| |!green-up-arrow.svg 480|🔥NirDiamant/GenAIAgents !2025-03-2810693318|This repository provides tutorials and implementations for various Generative AI Agent techniques, from basic to advanced. It serves as a comprehensive guide for building intelligent, interactive AI systems.| |!red-down-arrow 481|Unstructured-IO/unstructured !2025-03-28106889|Open source libraries and APIs to build custom preprocessing pipelines for labeling, training, or production machine learning pipelines.| | 482|apache/thrift !2025-03-28106610|Apache Thrift| | 483| TheR1D/shellgpt !2025-03-28106097 | A command-line productivity tool powered by ChatGPT, will help you accomplish your tasks faster and more efficiently | | 484|TheRamU/Fay !2025-03-281060312 |Fay is a complete open source project that includes Fay controller and numeral models, which can be used in different applications such as virtual hosts, live promotion, numeral human interaction and so on| | 485|zyronon/douyin !2025-03-28105566|Vue3 + Pinia + Vite5 仿抖音，Vue 在移动端的最佳实践 . Imitate TikTok ，Vue Best practices on Mobile| | 486|THU-MIG/yolov10 !2025-03-28105485|YOLOv10: Real-Time End-to-End Object Detection| | 487|idootop/mi-gpt !2025-03-281052522|? Transform XiaoAi speaker into a personal voice assistant with ChatGPT and DouBao integration.| | 488|SakanaAI/AI-Scientist !2025-03-281051310|The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑‍🔬| | 489|szimek/sharedrop !2025-03-28105101|Easy P2P file transfer powered by WebRTC - inspired by Apple AirDrop| | 490|salesforce/LAVIS !2025-03-28103942 |LAVIS - A One-stop Library for Language-Vision Intelligence| | 491|aws/amazon-sagemaker-examples !2025-03-28103654|Example 📓 Jupyter notebooks that demonstrate how to build, train, and deploy machine learning models using 🧠 Amazon SageMaker.| | 492|artidoro/qlora !2025-03-28103402 |QLoRA: Efficient Finetuning of Quantized LLMs| | 493|lllyasviel/stable-diffusion-webui-forge !2025-03-281029314| a platform on top of Stable Diffusion WebUI (based on Gradio) to make development easier, optimize resource management, and speed up inference| | 494|NielsRogge/Transformers-Tutorials !2025-03-28102487|This repository contains demos I made with the Transformers library by HuggingFace.| | 495|kedro-org/kedro !2025-03-28102371|Kedro is a toolbox for production-ready data science. It uses software engineering best practices to help you create data engineering and data science pipelines that are reproducible, maintainable, and modular.| | 496| chathub-dev/chathub !2025-03-28102301 | All-in-one chatbot client | | 497|microsoft/promptflow !2025-03-28101612|Build high-quality LLM apps - from prototyping, testing to production deployment and monitoring.| | 498|mistralai/mistral-src !2025-03-28101372|Reference implementation of Mistral AI 7B v0.1 model.| | 499|burn-rs/burn !2025-03-28101183|Burn - A Flexible and Comprehensive Deep Learning Framework in Rust| | 500|AIGC-Audio/AudioGPT !2025-03-28101150 |AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head| | 501|facebookresearch/dinov2 !2025-03-281011210 |PyTorch code and models for the DINOv2 self-supervised learning method.| | 502|RockChinQ/LangBot !2025-03-281008455|😎丰富生态、🧩支持扩展、🦄多模态 - 大模型原生即时通信机器人平台 🤖 | | 503|78/xiaozhi-esp32 !2025-03-281008180|Build your own AI friend| | 504|cumulo-autumn/StreamDiffusion !2025-03-28100761|StreamDiffusion: A Pipeline-Level Solution for Real-Time Interactive Generation| | 505|DataTalksClub/machine-learning-zoomcamp !2025-03-28100664|The code from the Machine Learning Bookcamp book and a free course based on the book| | 506|nerfstudio-project/nerfstudio !2025-03-28100343|A collaboration friendly studio for NeRFs| | 507|cupy/cupy !2025-03-28100344|NumPy & SciPy for GPU| | 508|NVIDIA/TensorRT-LLM !2025-03-281000823|TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.| | 509|wasp-lang/open-saas !2025-03-2899665|A free, open-source SaaS app starter for React & Node.js with superpowers. Production-ready. Community-driven.| | 510|huggingface/text-generation-inference !2025-03-2899383|Large Language Model Text Generation Inference| | 511|jxnl/instructor !2025-03-2899224|structured outputs for llms| | 512|GoogleCloudPlatform/generative-ai !2025-03-2899086|Sample code and notebooks for Generative AI on Google Cloud| | 513|manticoresoftware/manticoresearch !2025-03-2898799|Easy to use open source fast database for search | | 514|langfuse/langfuse !2025-03-28985134|🪢 Open source LLM engineering platform. Observability, metrics, evals, prompt management, testing, prompt playground, datasets, LLM evaluations -- 🍊YC W23 🤖 integrate via Typescript, Python / Decorators, OpenAI, Langchain, LlamaIndex, Litellm, Instructor, Mistral, Perplexity, Claude, Gemini, Vertex| | 515|keephq/keep !2025-03-2897949|The open-source alert management and AIOps platform| | 516|sashabaranov/go-openai !2025-03-2897843|OpenAI ChatGPT, GPT-3, GPT-4, DALL·E, Whisper API wrapper for Go| | 517|autowarefoundation/autoware !2025-03-2897766|Autoware - the world's leading open-source software project for autonomous driving| | 518|anthropics/courses !2025-03-2897269|Anthropic's educational courses| | 519|popcorn-official/popcorn-desktop !2025-03-2896853|Popcorn Time is a multi-platform, free software BitTorrent client that includes an integrated media player ( Windows / Mac / Linux ) A Butter-Project Fork| | 520|getmaxun/maxun !2025-03-28968515|🔥 Open-source no-code web data extraction platform. Turn websites to APIs and spreadsheets with no-code robots in minutes! [In Beta]| | 521|wandb/wandb !2025-03-2896763|🔥 A tool for visualizing and tracking your machine learning experiments. This repo contains the CLI and Python API.| | 522|karpathy/minbpe !2025-03-2895353|Minimal, clean, code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.| | 523|bigscience-workshop/petals !2025-03-2895142|🌸 Run large language models at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading| | 524|OthersideAI/self-operating-computer !2025-03-2894931|A framework to enable multimodal models to operate a computer.| | 525|mshumer/gpt-prompt-engineer !2025-03-2894911|| | 526| BloopAI/bloop !2025-03-2894710 | A fast code search engine written in Rust| | 527|BlinkDL/ChatRWKV !2025-03-289467-1 |ChatRWKV is like ChatGPT but powered by RWKV (100% RNN) language model, and open source.| | 528|timlrx/tailwind-nextjs-starter-blog !2025-03-2894677|This is a Next.js, Tailwind CSS blogging starter template. Comes out of the box configured with the latest technologies to make technical writing a breeze. Easily configurable and customizable. Perfect as a replacement to existing Jekyll and Hugo individual blogs.| | 529|google/benchmark !2025-03-2893634|A microbenchmark support library| | 530|facebookresearch/nougat !2025-03-2893603|Implementation of Nougat Neural Optical Understanding for Academic Documents| | 531|modelscope/facechain !2025-03-2893536|FaceChain is a deep-learning toolchain for generating your Digital-Twin.| | 532|DrewThomasson/ebook2audiobook !2025-03-2893388|Convert ebooks to audiobooks with chapters and metadata using dynamic AI models and voice cloning. Supports 1,107+ languages!| | 533|RayTracing/raytracing.github.io !2025-03-2893035|Main Web Site (Online Books)| | 534|QwenLM/Qwen2.5-VL !2025-03-28930249|Qwen2.5-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.| | 535|WongKinYiu/yolov9 !2025-03-2892201|Implementation of paper - YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information| | 536|alibaba-damo-academy/FunASR !2025-03-28920222|A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models.| | 537|Visualize-ML/Book4Power-of-Matrix !2025-03-2891931|Book4 'Power of Matrix' | | 538|dice2o/BingGPT !2025-03-289185-1 |Desktop application of new Bing's AI-powered chat (Windows, macOS and Linux)| | 539|browserbase/stagehand !2025-03-28917621|An AI web browsing framework focused on simplicity and extensibility.| | 540|FlagOpen/FlagEmbedding !2025-03-28914111|Dense Retrieval and Retrieval-augmented LLMs| | 541|Const-me/Whisper !2025-03-2890979|High-performance GPGPU inference of OpenAI's Whisper automatic speech recognition (ASR) model| | 542|lucidrains/denoising-diffusion-pytorch !2025-03-2890942|Implementation of Denoising Diffusion Probabilistic Model in Pytorch| | 543|Chainlit/chainlit !2025-03-28904422|Build Conversational AI in minutes ⚡️| | 544|togethercomputer/OpenChatKit !2025-03-2890160 |OpenChatKit provides a powerful, open-source base to create both specialized and general purpose chatbots for various applications| | 545|Stability-AI/StableStudio !2025-03-2889631 |Community interface for generative AI| | 546|voicepaw/so-vits-svc-fork !2025-03-2889482 |so-vits-svc fork with realtime support, improved interface and more features.| | 547|pymc-devs/pymc !2025-03-2889413|Bayesian Modeling and Probabilistic Programming in Python| | 548|espnet/espnet !2025-03-2889302|End-to-End Speech Processing Toolkit| | 549|kedacore/keda !2025-03-2888991|KEDA is a Kubernetes-based Event Driven Autoscaling component. It provides event driven scale for any container running in Kubernetes| | 550|open-mmlab/Amphion !2025-03-28886911|Amphion (/æmˈfaɪən/) is a toolkit for Audio, Music, and Speech Generation. Its purpose is to support reproducible research and help junior researchers and engineers get started in the field of audio, music, and speech generation research and development.| | 551|gorse-io/gorse !2025-03-2888451|Gorse open source recommender system engine| | 552|adams549659584/go-proxy-bingai !2025-03-288768-1 |A Microsoft New Bing demo site built with Vue3 and Go, providing a consistent UI experience, supporting ChatGPT prompts, and accessible within China| | 553|open-mmlab/mmsegmentation !2025-03-2887513|OpenMMLab Semantic Segmentation Toolbox and Benchmark.| | 554|bytedance/monolith !2025-03-2887223|ByteDance's Recommendation System| | 555|LouisShark/chatgptsystemprompt !2025-03-2887216|store all agent's system prompt| | 556|brexhq/prompt-engineering !2025-03-2887080 |Tips and tricks for working with Large Language Models like OpenAI's GPT-4.| | 557|erincatto/box2d !2025-03-2886841|Box2D is a 2D physics engine for games| | 558|🔥microsoft/ai-agents-for-beginners !2025-03-288669323|10 Lessons to Get Started Building AI Agents| | 559|nashsu/FreeAskInternet !2025-03-2886102|FreeAskInternet is a completely free, private and locally running search aggregator & answer generate using LLM, without GPU needed. The user can ask a question and the system will make a multi engine search and combine the search result to the ChatGPT3.5 LLM and generate the answer based on search results.| | 560|goldmansachs/gs-quant !2025-03-2885981|Python toolkit for quantitative finance| | 561|srbhr/Resume-Matcher !2025-03-2885800|Open Source Free ATS Tool to compare Resumes with Job Descriptions and create a score to rank them.| | 562|facebookresearch/ImageBind !2025-03-2885681 |ImageBind One Embedding Space to Bind Them All| | 563|ashawkey/stable-dreamfusion !2025-03-2885481 |A pytorch implementation of text-to-3D dreamfusion, powered by stable diffusion.| | 564|meetecho/janus-gateway !2025-03-2885232|Janus WebRTC Server| | 565|google/magika !2025-03-2885003|Detect file content types with deep learning| | 566|huggingface/chat-ui !2025-03-2884871 |Open source codebase powering the HuggingChat app| | 567|EleutherAI/lm-evaluation-harness !2025-03-28843012|A framework for few-shot evaluation of autoregressive language models.| | 568|jina-ai/reader !2025-03-2884089|Convert any URL to an LLM-friendly input with a simple prefix https://r.jina.ai/| | 569|microsoft/TypeChat !2025-03-288406-1|TypeChat is a library that makes it easy to build natural language interfaces using types.| | 570|thuml/Time-Series-Library !2025-03-28839715|A Library for Advanced Deep Time Series Models.| | 571|OptimalScale/LMFlow !2025-03-2883882|An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Model for All.| | 572|baptisteArno/typebot.io !2025-03-2883845|💬 Typebot is a powerful chatbot builder that you can self-host.| | 573|jzhang38/TinyLlama !2025-03-2883504|The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.| | 574|fishaudio/Bert-VITS2 !2025-03-2883472|vits2 backbone with multilingual-bert| | 575|OpenBMB/XAgent !2025-03-2882683|An Autonomous LLM Agent for Complex Task Solving| | 576|Acly/krita-ai-diffusion !2025-03-2882387|Streamlined interface for generating images with AI in Krita. Inpaint and outpaint with optional text prompt, no tweaking required.| | 577|jasonppy/VoiceCraft !2025-03-2882151|Zero-Shot Speech Editing and Text-to-Speech in the Wild| | 578|SJTU-IPADS/PowerInfer !2025-03-2881693|High-speed Large Language Model Serving on PCs with Consumer-grade GPUs| | 579|modelscope/DiffSynth-Studio !2025-03-28814713|Enjoy the magic of Diffusion models!| | 580|o3de/o3de !2025-03-2881443|Open 3D Engine (O3DE) is an Apache 2.0-licensed multi-platform 3D engine that enables developers and content creators to build AAA games, cinema-quality 3D worlds, and high-fidelity simulations without any fees or commercial obligations.| | 581|zmh-program/chatnio !2025-03-2881325|🚀 Next Generation AI One-Stop Internationalization Solution. 🚀 下一代 AI 一站式 B/C 端解决方案，支持 OpenAI，Midjourney，Claude，讯飞星火，Stable Diffusion，DALL·E，ChatGLM，通义千问，腾讯混元，360 智脑，百川 AI，火山方舟，新必应，Gemini，Moonshot 等模型，支持对话分享，自定义预设，云端同步，模型市场，支持弹性计费和订阅计划模式，支持图片解析，支持联网搜索，支持模型缓存，丰富美观的后台管理与仪表盘数据统计。| | 582|leptonai/searchwithlepton !2025-03-2880632|Building a quick conversation-based search demo with Lepton AI.| | 583|sebastianstarke/AI4Animation !2025-03-2880620|Bringing Characters to Life with Computer Brains in Unity| | 584|wangrongding/wechat-bot !2025-03-2880528|🤖一个基于 WeChaty 结合 DeepSeek / ChatGPT / Kimi / 讯飞等Ai服务实现的微信机器人，可以用来帮助你自动回复微信消息，或者管理微信群/好友，检测僵尸粉等...| | 585|openvinotoolkit/openvino !2025-03-2880528|OpenVINO™ is an open-source toolkit for optimizing and deploying AI inference| | 586|steven2358/awesome-generative-ai !2025-03-28802610|A curated list of modern Generative Artificial Intelligence projects and services| | 587|adam-maj/tiny-gpu !2025-03-2880234|A minimal GPU design in Verilog to learn how GPUs work from the ground up| | 588| anse-app/chatgpt-demo !2025-03-2880180 | A demo repo based on OpenAI API (gpt-3.5-turbo) | | 589| acheong08/EdgeGPT !2025-03-288015-1 |Reverse engineered API of Microsoft's Bing Chat | | 590|ai-collection/ai-collection !2025-03-2879994 |The Generative AI Landscape - A Collection of Awesome Generative AI Applications| | 591|GreyDGL/PentestGPT !2025-03-2879953 |A GPT-empowered penetration testing tool| | 592|delta-io/delta !2025-03-2879112|An open-source storage framework that enables building a Lakehouse architecture with compute engines including Spark, PrestoDB, Flink, Trino, and Hive and APIs| | 593|dataelement/bisheng !2025-03-2879085|Bisheng is an open LLM devops platform for next generation AI applications.| | 594|e2b-dev/e2b !2025-03-2878447 |Vercel for AI agents. We help developers to build, deploy, and monitor AI agents. Focusing on specialized AI agents that build software for you - your personal software developers.| | 595|01-ai/Yi !2025-03-2878311|A series of large language models trained from scratch by developers @01-ai| | 596|Plachtaa/VALL-E-X !2025-03-287830-1|An open source implementation of Microsoft's VALL-E X zero-shot TTS model. The demo is available at https://plachtaa.github.io| | 597|abhishekkrthakur/approachingalmost !2025-03-2878204|Approaching (Almost) Any Machine Learning Problem| | 598|pydantic/pydantic-ai !2025-03-28781041|Agent Framework / shim to use Pydantic with LLMs| | 599|rany2/edge-tts !2025-03-2877901|Use Microsoft Edge's online text-to-speech service from Python WITHOUT needing Microsoft Edge or Windows or an API key| | 600|CASIA-IVA-Lab/FastSAM !2025-03-2877881|Fast Segment Anything| | 601|netease-youdao/EmotiVoice !2025-03-2877817|EmotiVoice 😊: a Multi-Voice and Prompt-Controlled TTS Engine| | 602|lllyasviel/IC-Light !2025-03-2877804|More relighting!| | 603|kroma-network/tachyon !2025-03-287774-1|Modular ZK(Zero Knowledge) backend accelerated by GPU| | 604|deep-floyd/IF !2025-03-2877731 |A novel state-of-the-art open-source text-to-image model with a high degree of photorealism and language understanding| | 605|oumi-ai/oumi !2025-03-2877705|Everything you need to build state-of-the-art foundation models, end-to-end.| | 606|reorproject/reor !2025-03-2877681|AI note-taking app that runs models locally.| | 607|lightpanda-io/browser !2025-03-28775813|Lightpanda: the headless browser designed for AI and automation| | 608|xiangsx/gpt4free-ts !2025-03-287755-1|Providing a free OpenAI GPT-4 API ! This is a replication project for the typescript version of xtekky/gpt4free| | 609|IDEA-Research/GroundingDINO !2025-03-28773311|Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"| | 610|bunkerity/bunkerweb !2025-03-2877326|🛡️ Make your web services secure by default !| | 611|vikhyat/moondream !2025-03-2877057|tiny vision language model| | 612|firmai/financial-machine-learning !2025-03-287703-1|A curated list of practical financial machine learning tools and applications.| | 613|n8n-io/self-hosted-ai-starter-kit !2025-03-28765121|The Self-hosted AI Starter Kit is an open-source template that quickly sets up a local AI environment. Curated by n8n, it provides essential tools for creating secure, self-hosted AI workflows.| | 614|intel-analytics/ipex-llm !2025-03-2876507|Accelerate local LLM inference and finetuning (LLaMA, Mistral, ChatGLM, Qwen, Baichuan, Mixtral, Gemma, etc.) on Intel CPU and GPU (e.g., local PC with iGPU, discrete GPU such as Arc, Flex and Max). A PyTorch LLM library that seamlessly integrates with llama.cpp, HuggingFace, LangChain, LlamaIndex, DeepSpeed, vLLM, FastChat, ModelScope, etc.| | 615|jrouwe/JoltPhysics !2025-03-28764510|A multi core friendly rigid body physics and collision detection library. Written in C++. Suitable for games and VR applications. Used by Horizon Forbidden West.| | 616|THUDM/CodeGeeX2 !2025-03-2876270|CodeGeeX2: A More Powerful Multilingual Code Generation Model| | 617|meta-llama/llama-stack !2025-03-2875866|Composable building blocks to build Llama Apps| | 618|sweepai/sweep !2025-03-287530-1|Sweep is an AI junior developer| | 619|lllyasviel/Omost !2025-03-2875301|Your image is almost there!| | 620|ahmedbahaaeldin/From-0-to-Research-Scientist-resources-guide !2025-03-2875050|Detailed and tailored guide for undergraduate students or anybody want to dig deep into the field of AI with solid foundation.| | 621|dair-ai/ML-Papers-Explained !2025-03-2875050|Explanation to key concepts in ML| | 622|zaidmukaddam/scira !2025-03-28750110|Scira (Formerly MiniPerplx) is a minimalistic AI-powered search engine that helps you find information on the internet. Powered by Vercel AI SDK! Search with models like Grok 2.0.| | 623|Portkey-AI/gateway !2025-03-28749416|A Blazing Fast AI Gateway. Route to 100+ LLMs with 1 fast & friendly API.| | 624|web-infra-dev/midscene !2025-03-28748729|An AI-powered automation SDK can control the page, perform assertions, and extract data in JSON format using natural language.| | 625|zilliztech/GPTCache !2025-03-2874801 |GPTCache is a library for creating semantic cache to store responses from LLM queries.| | 626|niedev/RTranslator !2025-03-2874742|RTranslator is the world's first open source real-time translation app.| |!green-up-arrow.svg 627|roboflow/notebooks !2025-03-2874666|Examples and tutorials on using SOTA computer vision models and techniques. Learn everything from old-school ResNet, through YOLO and object-detection transformers like DETR, to the latest models like Grounding DINO and SAM.| |!red-down-arrow 628|openlm-research/openllama !2025-03-2874652|OpenLLaMA, a permissively licensed open source reproduction of Meta AI’s LLaMA 7B trained on the RedPajama dataset| | 629|LiheYoung/Depth-Anything !2025-03-2874155|Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data| | 630|enso-org/enso !2025-03-2874040|Hybrid visual and textual functional programming.| | 631|bigcode-project/starcoder !2025-03-287401-1 |Home of StarCoder: fine-tuning & inference!| | 632|git-ecosystem/git-credential-manager !2025-03-2873975|Secure, cross-platform Git credential storage with authentication to GitHub, Azure Repos, and other popular Git hosting services.| | 633|OpenGVLab/InternVL !2025-03-2873634|[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4V. 接近GPT-4V表现的可商用开源模型| | 634|WooooDyy/LLM-Agent-Paper-List !2025-03-2873551|The paper list of the 86-page paper "The Rise and Potential of Large Language Model Based Agents: A Survey" by Zhiheng Xi et al.| | 635|lencx/Noi !2025-03-2873157|🦄 AI + Tools + Plugins + Community| | 636|udlbook/udlbook !2025-03-2873075|Understanding Deep Learning - Simon J.D. Prince| | 637|OpenBMB/MiniCPM !2025-03-2872841|MiniCPM-2B: An end-side LLM outperforms Llama2-13B.| | 638|jaywalnut310/vits !2025-03-2872815 |VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech| | 639|xorbitsai/inference !2025-03-28727528|Replace OpenAI GPT with another LLM in your app by changing a single line of code. Xinference gives you the freedom to use any LLM you need. With Xinference, you're empowered to run inference with any open-source language models, speech recognition models, and multimodal models, whether in the cloud, on-premises, or even on your laptop.| | 640|PWhiddy/PokemonRedExperiments !2025-03-2872492|Playing Pokemon Red with Reinforcement Learning| | 641|Canner/WrenAI !2025-03-28723213|🤖 Open-source AI Agent that empowers data-driven teams to chat with their data to generate Text-to-SQL, charts, spreadsheets, reports, and BI. 📈📊📋🧑‍💻| | 642|miurla/morphic !2025-03-2872258|An AI-powered answer engine with a generative UI| | 643|ml-explore/mlx-examples !2025-03-2872168|Examples in the MLX framework| | 644|PKU-YuanGroup/ChatLaw !2025-03-2872010|Chinese Legal Large Model| | 645|NVIDIA/cutlass !2025-03-2871883|CUDA Templates for Linear Algebra Subroutines| | 646|FoundationVision/VAR !2025-03-28717444|[GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction"| | 647|ymcui/Chinese-LLaMA-Alpaca-2 !2025-03-2871561|Chinese LLaMA-2 & Alpaca-2 LLMs| | 648|nadermx/backgroundremover !2025-03-2871514 |Background Remover lets you Remove Background from images and video using AI with a simple command line interface that is free and open source.| | 649|onuratakan/gpt-computer-assistant !2025-03-28714514|gpt-4o for windows, macos and ubuntu| | 650|graviraja/MLOps-Basics !2025-03-2871326|| | 651|Future-House/paper-qa !2025-03-287118-1|High accuracy RAG for answering questions from scientific documents with citations| | 652|open-mmlab/mmagic !2025-03-2871102 |OpenMMLab Multimodal Advanced, Generative, and Intelligent Creation Toolbox| | 653|bhaskatripathi/pdfGPT !2025-03-2870941 |PDF GPT allows you to chat with the contents of your PDF file by using GPT capabilities. The only open source solution to turn your pdf files in a chatbot!| | 654|ollama/ollama-python !2025-03-28709117|Ollama Python library| | 655|facebookresearch/DiT !2025-03-2870376|Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"| | 656|geekyutao/Inpaint-Anything !2025-03-2870262 |Inpaint anything using Segment Anything and inpainting models.| | 657|AbdullahAlfaraj/Auto-Photoshop-StableDiffusion-Plugin !2025-03-2870160 |A user-friendly plug-in that makes it easy to generate stable diffusion images inside Photoshop using Automatic1111-sd-webui as a backend.| | 658|apple/corenet !2025-03-2869990|CoreNet: A library for training deep neural networks| | 659|openstatusHQ/openstatus !2025-03-2869926|🏓 The open-source synthetic monitoring platform 🏓| | 660|weaviate/Verba !2025-03-2869772|Retrieval Augmented Generation (RAG) chatbot powered by Weaviate| | 661|meshery/meshery !2025-03-2869630|Meshery, the cloud native manager| | 662|OpenTalker/video-retalking !2025-03-2869530|[SIGGRAPH Asia 2022] VideoReTalking: Audio-based Lip Synchronization for Talking Head Video Editing In the Wild| | 663|digitalinnovationone/dio-lab-open-source !2025-03-28689013|Repositório do lab "Contribuindo em um Projeto Open Source no GitHub" da Digital Innovation One.| | 664|jianchang512/ChatTTS-ui !2025-03-2868842|一个简单的本地网页界面，直接使用ChatTTS将文字合成为语音，同时支持对外提供API接口。| | 665|patchy631/ai-engineering-hub !2025-03-28686434|In-depth tutorials on LLMs, RAGs and real-world AI agent applications.| | 666|gunnarmorling/1brc !2025-03-2868512|1️⃣🐝🏎️ The One Billion Row Challenge -- A fun exploration of how quickly 1B rows from a text file can be aggregated with Java| | 667|Azure-Samples/azure-search-openai-demo !2025-03-2868482 |A sample app for the Retrieval-Augmented Generation pattern running in Azure, using Azure Cognitive Search for retrieval and Azure OpenAI large language models to power ChatGPT-style and Q&A experiences.| | 668|mit-han-lab/streaming-llm !2025-03-2868382|Efficient Streaming Language Models with Attention Sinks| | 669|InternLM/InternLM !2025-03-2868352|InternLM has open-sourced a 7 billion parameter base model, a chat model tailored for practical scenarios and the training system.| | 670|dependency-check/DependencyCheck !2025-03-2868191|OWASP dependency-check is a software composition analysis utility that detects publicly disclosed vulnerabilities in application dependencies.| | 671|Soulter/AstrBot !2025-03-28678643|✨易上手的多平台 LLM 聊天机器人及开发框架✨。支持 QQ、QQ频道、Telegram、微信平台(Gewechat, 企业微信)、内置 Web Chat，OpenAI GPT、DeepSeek、Ollama、Llama、GLM、Gemini、OneAPI、LLMTuner，支持 LLM Agent 插件开发，可视化面板。一键部署。支持 Dify 工作流、代码执行器、Whisper 语音转文字。| | 672|react-native-webview/react-native-webview !2025-03-2867792|React Native Cross-Platform WebView| | 673|modelscope/agentscope !2025-03-28676916|Start building LLM-empowered multi-agent applications in an easier way.| | 674|mylxsw/aidea !2025-03-2867381|AIdea is a versatile app that supports GPT and domestic large language models，also supports "Stable Diffusion" text-to-image generation, image-to-image generation, SDXL 1.0, super-resolution, and image colorization| | 675|langchain-ai/ollama-deep-researcher !2025-03-28668635|Fully local web research and report writing assistant| | 676|threestudio-project/threestudio !2025-03-2866653|A unified framework for 3D content generation.| | 677|gaomingqi/Track-Anything !2025-03-2866631 |A flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI.| | 678|spdustin/ChatGPT-AutoExpert !2025-03-2866570|🚀🧠💬 Supercharged Custom Instructions for ChatGPT (non-coding) and ChatGPT Advanced Data Analysis (coding).| | 679|HariSekhon/DevOps-Bash-tools !2025-03-2866463|1000+ DevOps Bash Scripts - AWS, GCP, Kubernetes, Docker, CI/CD, APIs, SQL, PostgreSQL, MySQL, Hive, Impala, Kafka, Hadoop, Jenkins, GitHub, GitLab, BitBucket, Azure DevOps, TeamCity, Spotify, MP3, LDAP, Code/Build Linting, pkg mgmt for Linux, Mac, Python, Perl, Ruby, NodeJS, Golang, Advanced dotfiles: .bashrc, .vimrc, .gitconfig, .screenrc, tmux..| | 680|modelscope/swift !2025-03-28661530|ms-swift: Use PEFT or Full-parameter to finetune 200+ LLMs or 15+ MLLMs| | 681|langchain-ai/opengpts !2025-03-2866080|This is an open source effort to create a similar experience to OpenAI's GPTs and Assistants API| | 682| yihong0618/xiaogpt !2025-03-2865131 | Play ChatGPT with xiaomi ai speaker | | 683| civitai/civitai !2025-03-2865111 | Build a platform where people can share their stable diffusion models | | 684|KoljaB/RealtimeSTT !2025-03-28649513|A robust, efficient, low-latency speech-to-text library with advanced voice activity detection, wake word activation and instant transcription.| | 685|qunash/chatgpt-advanced !2025-03-2864910 | A browser extension that augments your ChatGPT prompts with web results.| | 686|Licoy/ChatGPT-Midjourney !2025-03-2864850|🎨 Own your own ChatGPT+Midjourney web service with one click| | 687|friuns2/BlackFriday-GPTs-Prompts !2025-03-2864744|List of free GPTs that doesn't require plus subscription| | 688|PixarAnimationStudios/OpenUSD !2025-03-2864700|Universal Scene Description| | 689|linyiLYi/street-fighter-ai !2025-03-2864630 |This is an AI agent for Street Fighter II Champion Edition.| | 690|run-llama/rags !2025-03-2864380|Build ChatGPT over your data, all with natural language| | 691|frdel/agent-zero !2025-03-2864154|Agent Zero AI framework| | 692|microsoft/DeepSpeedExamples !2025-03-2863911 |Example models using DeepSpeed| | 693|k8sgpt-ai/k8sgpt !2025-03-2863882|Giving Kubernetes Superpowers to everyone| | 694|open-metadata/OpenMetadata !2025-03-2863514|OpenMetadata is a unified platform for discovery, observability, and governance powered by a central metadata repository, in-depth lineage, and seamless team collaboration.| | 695|google/gemma.cpp !2025-03-2863163|lightweight, standalone C++ inference engine for Google's Gemma models.| | 696|RayVentura/ShortGPT !2025-03-286314-1|🚀🎬 ShortGPT - An experimental AI framework for automated short/video content creation. Enables creators to rapidly produce, manage, and deliver content using AI and automation.| | 697|openai/consistencymodels !2025-03-2862940 |Official repo for consistency models.| | 698|yangjianxin1/Firefly !2025-03-2862924|Firefly: Chinese conversational large language model (full-scale fine-tuning + QLoRA), supporting fine-tuning of Llma2, Llama, Baichuan, InternLM, Ziya, Bloom, and other large models| | 699|enricoros/big-AGI !2025-03-2862665|Generative AI suite powered by state-of-the-art models and providing advanced AI/AGI functions. It features AI personas, AGI functions, multi-model chats, text-to-image, voice, response streaming, code highlighting and execution, PDF import, presets for developers, much more. Deploy on-prem or in the cloud.| | 700|aptos-labs/aptos-core !2025-03-2862633|Aptos is a layer 1 blockchain built to support the widespread use of blockchain through better technology and user experience.| | 701|wenda-LLM/wenda !2025-03-286262-1 |Wenda: An LLM invocation platform. Its objective is to achieve efficient content generation tailored to specific environments while considering the limited computing resources of individuals and small businesses, as well as knowledge security and privacy concerns| | 702|Project-MONAI/MONAI !2025-03-2862603|AI Toolkit for Healthcare Imaging| | 703|HVision-NKU/StoryDiffusion !2025-03-2862470|Create Magic Story!| | 704|deepseek-ai/DeepSeek-LLM !2025-03-2862463|DeepSeek LLM: Let there be answers| | 705|Tohrusky/Final2x !2025-03-2862393|2^x Image Super-Resolution| | 706|OpenSPG/KAG !2025-03-28619611|KAG is a logical form-guided reasoning and retrieval framework based on OpenSPG engine and LLMs. It is used to build logical reasoning and factual Q&A solutions for professional domain knowledge bases. It can effectively overcome the shortcomings of the traditional RAG vector similarity calculation model.| | 707|Moonvy/OpenPromptStudio !2025-03-2861861 |AIGC Hint Word Visualization Editor| | 708|levihsu/OOTDiffusion !2025-03-2861761|Official implementation of OOTDiffusion| | 709|tmc/langchaingo !2025-03-2861729|LangChain for Go, the easiest way to write LLM-based programs in Go| | 710|vladmandic/automatic !2025-03-2861374|SD.Next: Advanced Implementation of Stable Diffusion and other Diffusion-based generative image models| | 711|clovaai/donut !2025-03-2861231 |Official Implementation of OCR-free Document Understanding Transformer (Donut) and Synthetic Document Generator (SynthDoG), ECCV 2022| | 712|Shaunwei/RealChar !2025-03-286121-1|🎙️🤖Create, Customize and Talk to your AI Character/Companion in Realtime(All in One Codebase!). Have a natural seamless conversation with AI everywhere(mobile, web and terminal) using LLM OpenAI GPT3.5/4, Anthropic Claude2, Chroma Vector DB, Whisper Speech2Text, ElevenLabs Text2Speech🎙️🤖| | 713|microsoft/TinyTroupe !2025-03-2861142|LLM-powered multiagent persona simulation for imagination enhancement and business insights.| | 714| rustformers/llm !2025-03-2861010 | Run inference for Large Language Models on CPU, with Rust| | 715|firebase/firebase-ios-sdk !2025-03-2860950|Firebase SDK for Apple App Development| | 716|vespa-engine/vespa !2025-03-2860824|The open big data serving engine. https://vespa.ai| | 717|n4ze3m/page-assist !2025-03-28607610|Use your locally running AI models to assist you in your web browsing| | 718|Dooy/chatgpt-web-midjourney-proxy !2025-03-2860646|chatgpt web, midjourney, gpts,tts, whisper 一套ui全搞定| | 719|ethereum-optimism/optimism !2025-03-2860213|Optimism is Ethereum, scaled.| | 720|sczhou/ProPainter !2025-03-2859971|[ICCV 2023] ProPainter: Improving Propagation and Transformer for Video Inpainting| | 721|MineDojo/Voyager !2025-03-2859951 |An Open-Ended Embodied Agent with Large Language Models| | 722|lavague-ai/LaVague !2025-03-2859800|Automate automation with Large Action Model framework| | 723|SevaSk/ecoute !2025-03-2859770 |Ecoute is a live transcription tool that provides real-time transcripts for both the user's microphone input (You) and the user's speakers output (Speaker) in a textbox. It also generates a suggested response using OpenAI's GPT-3.5 for the user to say based on the live transcription of the conversation.| | 724|google/mesop !2025-03-2859661|| | 725|pengxiao-song/LaWGPT !2025-03-2859542 |Repo for LaWGPT, Chinese-Llama tuned with Chinese Legal knowledge| | 726|fr0gger/Awesome-GPT-Agents !2025-03-2859434|A curated list of GPT agents for cybersecurity| | 727|google-deepmind/graphcast !2025-03-2859412|| | 728|comet-ml/opik !2025-03-28594126|Open-source end-to-end LLM Development Platform| | 729|SciPhi-AI/R2R !2025-03-28594033|A framework for rapid development and deployment of production-ready RAG systems| | 730|SkalskiP/courses !2025-03-2859272 |This repository is a curated collection of links to various courses and resources about Artificial Intelligence (AI)| | 731|QuivrHQ/MegaParse !2025-03-2859122|File Parser optimised for LLM Ingestion with no loss 🧠 Parse PDFs, Docx, PPTx in a format that is ideal for LLMs.| | 732|pytorch-labs/gpt-fast !2025-03-2858971|Simple and efficient pytorch-native transformer text generation in !2025-03-2858886|Curated list of chatgpt prompts from the top-rated GPTs in the GPTs Store. Prompt Engineering, prompt attack & prompt protect. Advanced Prompt Engineering papers.| | 734|nilsherzig/LLocalSearch !2025-03-2858852|LLocalSearch is a completely locally running search aggregator using LLM Agents. The user can ask a question and the system will use a chain of LLMs to find the answer. The user can see the progress of the agents and the final answer. No OpenAI or Google API keys are needed.| | 735|kuafuai/DevOpsGPT !2025-03-285874-2|Multi agent system for AI-driven software development. Convert natural language requirements into working software. Supports any development language and extends the existing base code.| | 736|myshell-ai/MeloTTS !2025-03-2858486|High-quality multi-lingual text-to-speech library by MyShell.ai. Support English, Spanish, French, Chinese, Japanese and Korean.| | 737|OpenGVLab/LLaMA-Adapter !2025-03-2858421 |Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters| | 738|volcengine/verl !2025-03-28582563|veRL: Volcano Engine Reinforcement Learning for LLM| | 739|a16z-infra/companion-app !2025-03-2858171|AI companions with memory: a lightweight stack to create and host your own AI companions| | 740|HumanAIGC/OutfitAnyone !2025-03-285816-1|Outfit Anyone: Ultra-high quality virtual try-on for Any Clothing and Any Person| | 741|josStorer/RWKV-Runner !2025-03-2857472|A RWKV management and startup tool, full automation, only 8MB. And provides an interface compatible with the OpenAI API. RWKV is a large language model that is fully open source and available for commercial use.| | 742|648540858/wvp-GB28181-pro !2025-03-2857414|WEB VIDEO PLATFORM是一个基于GB28181-2016标准实现的网络视频平台，支持NAT穿透，支持海康、大华、宇视等品牌的IPC、NVR、DVR接入。支持国标级联，支持rtsp/rtmp等视频流转发到国标平台，支持rtsp/rtmp等推流转发到国标平台。| | 743|ToonCrafter/ToonCrafter !2025-03-2857345|a research paper for generative cartoon interpolation| | 744|PawanOsman/ChatGPT !2025-03-2857191|OpenAI API Free Reverse Proxy| | 745|apache/hudi !2025-03-2857091|Upserts, Deletes And Incremental Processing on Big Data.| | 746| nsarrazin/serge !2025-03-2857081 | A web interface for chatting with Alpaca through llama.cpp. Fully dockerized, with an easy to use API| | 747|homanp/superagent !2025-03-2857021|🥷 Superagent - Build, deploy, and manage LLM-powered agents| | 748|ramonvc/freegpt-webui !2025-03-2856910|GPT 3.5/4 with a Chat Web UI. No API key is required.| | 749|baichuan-inc/baichuan-7B !2025-03-2856901|A large-scale 7B pretraining language model developed by BaiChuan-Inc.| | 750|Azure/azure-sdk-for-net !2025-03-2856792|This repository is for active development of the Azure SDK for .NET. For consumers of the SDK we recommend visiting our public developer docs at https://learn.microsoft.com/dotnet/azure/ or our versioned developer docs at https://azure.github.io/azure-sdk-for-net.| | 751|mnotgod96/AppAgent !2025-03-2856643|AppAgent: Multimodal Agents as Smartphone Users, an LLM-based multimodal agent framework designed to operate smartphone apps.| | 752|microsoft/TaskWeaver !2025-03-2856243|A code-first agent framework for seamlessly planning and executing data analytics tasks.| | 753| yetone/bob-plugin-openai-translator !2025-03-285600-1 | A Bob Plugin base ChatGPT API | | 754|PrefectHQ/marvin !2025-03-2855840 |A batteries-included library for building AI-powered software| | 755|microsoft/promptbase !2025-03-2855832|All things prompt engineering| | 756|fullstackhero/dotnet-starter-kit !2025-03-2855560|Production Grade Cloud-Ready .NET 8 Starter Kit (Web API + Blazor Client) with Multitenancy Support, and Clean/Modular Architecture that saves roughly 200+ Development Hours! All Batteries Included.| | 757|deepseek-ai/DeepSeek-Coder-V2 !2025-03-2855435|DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence| | 758|aiwaves-cn/agents !2025-03-2855391|An Open-source Framework for Autonomous Language Agents| | 759|microsoft/Mastering-GitHub-Copilot-for-Paired-Programming !2025-03-2855158|A 6 Lesson course teaching everything you need to know about harnessing GitHub Copilot and an AI Paired Programing resource.| | 760|allenai/OLMo !2025-03-2854506|Modeling, training, eval, and inference code for OLMo| | 761|apify/crawlee-python !2025-03-2854493|Crawlee—A web scraping and browser automation library for Python to build reliable crawlers. Extract data for AI, LLMs, RAG, or GPTs. Download HTML, PDF, JPG, PNG, and other files from websites. Works with BeautifulSoup, Playwright, and raw HTTP. Both headful and headless mode. With proxy rotation.| | 762|k2-fsa/sherpa-onnx !2025-03-28541520|Speech-to-text, text-to-speech, and speaker recongition using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, Raspberry Pi, RISC-V, x86_64 servers, websocket server/client, C/C++, Python, Kotlin, C#, Go, NodeJS, Java, Swift| | 763|TEN-framework/TEN-Agent !2025-03-28541411|TEN Agent is a realtime conversational AI agent powered by TEN. It seamlessly integrates the OpenAI Realtime API, RTC capabilities, and advanced features like weather updates, web search, computer vision, and Retrieval-Augmented Generation (RAG).| | 764|google/gemmapytorch !2025-03-2854010|The official PyTorch implementation of Google's Gemma models| | 765|snakers4/silero-vad !2025-03-2853858|Silero VAD: pre-trained enterprise-grade Voice Activity Detector| | 766|livekit/agents !2025-03-2853836|Build real-time multimodal AI applications 🤖🎙️📹| | 767|pipecat-ai/pipecat !2025-03-28537811|Open Source framework for voice and multimodal conversational AI| | 768|EricLBuehler/mistral.rs !2025-03-28536324|Blazingly fast LLM inference.| | 769|asg017/sqlite-vec !2025-03-28535810|Work-in-progress vector search SQLite extension that runs anywhere.| | 770|albertan017/LLM4Decompile !2025-03-2853563|Reverse Engineering: Decompiling Binary Code with Large Language Models| | 771|Permify/permify !2025-03-2853235|An open-source authorization as a service inspired by Google Zanzibar, designed to build and manage fine-grained and scalable authorization systems for any application.| | 772|imoneoi/openchat !2025-03-2853171|OpenChat: Advancing Open-source Language Models with Imperfect Data| | 773|mosaicml/composer !2025-03-2853140|Train neural networks up to 7x faster| | 774|dsdanielpark/Bard-API !2025-03-285277-1 |The python package that returns a response of Google Bard through API.| | 775|lxfater/inpaint-web !2025-03-2852552|A free and open-source inpainting & image-upscaling tool powered by webgpu and wasm on the browser。| | 776|leanprover/lean4 !2025-03-2852441|Lean 4 programming language and theorem prover| | 777|AILab-CVC/YOLO-World !2025-03-2852415|Real-Time Open-Vocabulary Object Detection| | 778|openchatai/OpenChat !2025-03-2852260 |Run and create custom ChatGPT-like bots with OpenChat, embed and share these bots anywhere, the open-source chatbot console.| | 779|mufeedvh/code2prompt !2025-03-28519414|A CLI tool to convert your codebase into a single LLM prompt with source tree, prompt templating, and token counting.| | 780|biobootloader/wolverine !2025-03-2851700 |Automatically repair python scripts through GPT-4 to give them regenerative abilities.| | 781|huggingface/parler-tts !2025-03-2851671|Inference and training library for high-quality TTS models.| | 782|Akegarasu/lora-scripts !2025-03-2851308 |LoRA training scripts use kohya-ss's trainer, for diffusion model.| | 783|openchatai/OpenCopilot !2025-03-285128-3|🤖 🔥 Let your users chat with your product features and execute things by text - open source Shopify sidekick| | 784|e2b-dev/fragments !2025-03-2851228|Open-source Next.js template for building apps that are fully generated by AI. By E2B.| | 785|microsoft/SynapseML !2025-03-2851132|Simple and Distributed Machine Learning| | 786|aigc-apps/sd-webui-EasyPhoto !2025-03-285108-1|📷 EasyPhoto | | 787|ChaoningZhang/MobileSAM !2025-03-2850944|This is the official code for Faster Segment Anything (MobileSAM) project that makes SAM lightweight| | 788|huggingface/alignment-handbook !2025-03-2850932|Robust recipes for to align language models with human and AI preferences| | 789|alpkeskin/mosint !2025-03-2850920|An automated e-mail OSINT tool| | 790|TaskingAI/TaskingAI !2025-03-2850891|The open source platform for AI-native application development.| | 791|lipku/metahuman-stream !2025-03-28507615|Real time interactive streaming digital human| | 792|OpenInterpreter/01 !2025-03-2850530|The open-source language model computer| | 793|open-compass/opencompass !2025-03-28505111|OpenCompass is an LLM evaluation platform, supporting a wide range of models (InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.| | 794|xxlong0/Wonder3D !2025-03-2850491|A cross-domain diffusion model for 3D reconstruction from a single image| | 795|pytorch/torchtune !2025-03-2850342|A Native-PyTorch Library for LLM Fine-tuning| | 796|SuperDuperDB/superduperdb !2025-03-2850192|🔮 SuperDuperDB: Bring AI to your database: Integrate, train and manage any AI models and APIs directly with your database and your data.| | 797|WhiskeySockets/Baileys !2025-03-2850057|Lightweight full-featured typescript/javascript WhatsApp Web API| | 798| mpociot/chatgpt-vscode !2025-03-2849890 | A VSCode extension that allows you to use ChatGPT | | 799|OpenGVLab/DragGAN !2025-03-2849880|Unofficial Implementation of DragGAN - "Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold" （DragGAN 全功能实现，在线Demo，本地部署试用，代码、模型已全部开源，支持Windows, macOS, Linux）| | 800|microsoft/LLMLingua !2025-03-2849824|To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.| | 801|Zipstack/unstract !2025-03-2849745|No-code LLM Platform to launch APIs and ETL Pipelines to structure unstructured documents| | 802|OpenBMB/ToolBench !2025-03-2849621|An open platform for training, serving, and evaluating large language model for tool learning.| | 803|Fanghua-Yu/SUPIR !2025-03-2849593|SUPIR aims at developing Practical Algorithms for Photo-Realistic Image Restoration In the Wild| | 804|GaiaNet-AI/gaianet-node !2025-03-2849360|Install and run your own AI agent service| | 805|qodo-ai/qodo-cover !2025-03-284922-1|Qodo-Cover: An AI-Powered Tool for Automated Test Generation and Code Coverage Enhancement! 💻🤖🧪🐞| | 806|Zejun-Yang/AniPortrait !2025-03-2849042|AniPortrait: Audio-Driven Synthesis of Photorealistic Portrait Animation| | 807|lvwzhen/law-cn-ai !2025-03-2848901 |⚖️ AI Legal Assistant| | 808|developersdigest/llm-answer-engine !2025-03-2848740|Build a Perplexity-Inspired Answer Engine Using Next.js, Groq, Mixtral, Langchain, OpenAI, Brave & Serper| | 809|Plachtaa/VITS-fast-fine-tuning !2025-03-2848640|This repo is a pipeline of VITS finetuning for fast speaker adaptation TTS, and many-to-many voice conversion| | 810|espeak-ng/espeak-ng !2025-03-2848601|eSpeak NG is an open source speech synthesizer that supports more than hundred languages and accents.| | 811|ant-research/CoDeF !2025-03-2848581|[CVPR'24 Highlight] Official PyTorch implementation of CoDeF: Content Deformation Fields for Temporally Consistent Video Processing| | 812|deepseek-ai/DeepSeek-V2 !2025-03-2848512|| | 813|XRPLF/rippled !2025-03-2848210|Decentralized cryptocurrency blockchain daemon implementing the XRP Ledger protocol in C++| | 814|AutoMQ/automq !2025-03-28478721|AutoMQ is a cloud-first alternative to Kafka by decoupling durability to S3 and EBS. 10x cost-effective. Autoscale in seconds. Single-digit ms latency.| | 815|AILab-CVC/VideoCrafter !2025-03-2847800|VideoCrafter1: Open Diffusion Models for High-Quality Video Generation| | 816|nautechsystems/nautilustrader !2025-03-2847702|A high-performance algorithmic trading platform and event-driven backtester| | 817|kyegomez/swarms !2025-03-2847563|The Enterprise-Grade Production-Ready Multi-Agent Orchestration Framework Join our Community: https://discord.com/servers/agora-999382051935506503| | 818|Deci-AI/super-gradients !2025-03-2847310 |Easily train or fine-tune SOTA computer vision models with one open source training library. The home of Yolo-NAS.| | 819|QwenLM/Qwen2.5-Coder !2025-03-2847236|Qwen2.5-Coder is the code version of Qwen2.5, the large language model series developed by Qwen team, Alibaba Cloud.| | 820|SCIR-HI/Huatuo-Llama-Med-Chinese !2025-03-2847191 |Repo for HuaTuo (华驼), Llama-7B tuned with Chinese medical knowledge| | 821|togethercomputer/RedPajama-Data !2025-03-2846841 |code for preparing large datasets for training large language models| | 822|mishushakov/llm-scraper !2025-03-2846704|Turn any webpage into structured data using LLMs| | 823|1rgs/jsonformer !2025-03-2846663 |A Bulletproof Way to Generate Structured JSON from Language Models| | 824|anti-work/shortest !2025-03-2846565|QA via natural language AI tests| | 825|dnhkng/GlaDOS !2025-03-2846510|This is the Personality Core for GLaDOS, the first steps towards a real-life implementation of the AI from the Portal series by Valve.| | 826|Nukem9/dlssg-to-fsr3 !2025-03-2846380|Adds AMD FSR3 Frame Generation to games by replacing Nvidia DLSS-G Frame Generation (nvngx_dlssg).| | 827|BuilderIO/ai-shell !2025-03-2846373 |A CLI that converts natural language to shell commands.| | 828|facebookincubator/AITemplate !2025-03-2846220 |AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (NVIDIA GPU) and MatrixCore (AMD GPU) inference.| | 829|terraform-aws-modules/terraform-aws-eks !2025-03-2846030|Terraform module to create AWS Elastic Kubernetes (EKS) resources 🇺🇦| | 830|timescale/pgai !2025-03-2845915|A suite of tools to develop RAG, semantic search, and other AI applications more easily with PostgreSQL| | 831|awslabs/multi-agent-orchestrator !2025-03-2845788|Flexible and powerful framework for managing multiple AI agents and handling complex conversations| | 832|sanchit-gandhi/whisper-jax !2025-03-2845771 |Optimised JAX code for OpenAI's Whisper Model, largely built on the Hugging Face Transformers Whisper implementation| | 833|NVIDIA/NeMo-Guardrails !2025-03-2845755|NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.| | 834|PathOfBuildingCommunity/PathOfBuilding !2025-03-2845480|Offline build planner for Path of Exile.| | 835|UX-Decoder/Segment-Everything-Everywhere-All-At-Once !2025-03-2845412 |Official implementation of the paper "Segment Everything Everywhere All at Once"| | 836|build-trust/ockam !2025-03-2845171|Orchestrate end-to-end encryption, cryptographic identities, mutual authentication, and authorization policies between distributed applications – at massive scale.| | 837|google-research/timesfm !2025-03-2845135|TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.| | 838|luosiallen/latent-consistency-model !2025-03-2844842|Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference| | 839|NVlabs/neuralangelo !2025-03-2844740|Official implementation of "Neuralangelo: High-Fidelity Neural Surface Reconstruction" (CVPR 2023)| | 840|kyegomez/tree-of-thoughts !2025-03-2844720 |Plug in and Play Implementation of Tree of Thoughts: Deliberate Problem Solving with Large Language Models that Elevates Model Reasoning by atleast 70%| | 841|sjvasquez/handwriting-synthesis !2025-03-2844720 |Handwriting Synthesis with RNNs ✏️| | 842| madawei2699/myGPTReader !2025-03-2844420 | A slack bot that can read any webpage, ebook or document and summarize it with chatGPT | | 843|OpenBMB/AgentVerse !2025-03-2844413|🤖 AgentVerse 🪐 provides a flexible framework that simplifies the process of building custom multi-agent environments for large language models (LLMs).| | 844|argmaxinc/WhisperKit !2025-03-2844395|Swift native speech recognition on-device for iOS and macOS applications.| | 845|landing-ai/vision-agent !2025-03-2844346|Vision agent| | 846|InternLM/xtuner !2025-03-2844273|An efficient, flexible and full-featured toolkit for fine-tuning large models (InternLM, Llama, Baichuan, Qwen, ChatGLM)| | 847|google-deepmind/alphageometry !2025-03-284421-1|Solving Olympiad Geometry without Human Demonstrations| | 848|ostris/ai-toolkit !2025-03-2844093|Various AI scripts. Mostly Stable Diffusion stuff.| | 849|LLM-Red-Team/kimi-free-api !2025-03-2844004|🚀 KIMI AI 长文本大模型白嫖服务，支持高速流式输出、联网搜索、长文档解读、图像解析、多轮对话，零配置部署，多路token支持，自动清理会话痕迹。| | 850|argilla-io/argilla !2025-03-2843991|Argilla is a collaboration platform for AI engineers and domain experts that require high-quality outputs, full data ownership, and overall efficiency.| | 851|spring-projects/spring-ai !2025-03-28438419|An Application Framework for AI Engineering| | 852|alibaba-damo-academy/FunClip !2025-03-2843555|Open-source, accurate and easy-to-use video clipping tool, LLM based AI clipping intergrated | | 853|yisol/IDM-VTON !2025-03-2843541|IDM-VTON : Improving Diffusion Models for Authentic Virtual Try-on in the Wild| | 854|fchollet/ARC-AGI !2025-03-2843368|The Abstraction and Reasoning Corpus| | 855|MahmoudAshraf97/whisper-diarization !2025-03-2843064|Automatic Speech Recognition with Speaker Diarization based on OpenAI Whisper| | 856|Speykious/cve-rs !2025-03-2843047|Blazingly 🔥 fast 🚀 memory vulnerabilities, written in 100% safe Rust. 🦀| | 857|Blealtan/efficient-kan !2025-03-2842770|An efficient pure-PyTorch implementation of Kolmogorov-Arnold Network (KAN).| | 858|smol-ai/GodMode !2025-03-284249-1|AI Chat Browser: Fast, Full webapp access to ChatGPT / Claude / Bard / Bing / Llama2! I use this 20 times a day.| | 859|openai/plugins-quickstart !2025-03-284235-4 |Get a ChatGPT plugin up and running in under 5 minutes!| | 860|Doriandarko/maestro !2025-03-2842260|A framework for Claude Opus to intelligently orchestrate subagents.| | 861|philz1337x/clarity-upscaler !2025-03-2842204|Clarity-Upscaler: Reimagined image upscaling for everyone| | 862|facebookresearch/co-tracker !2025-03-2842142|CoTracker is a model for tracking any point (pixel) on a video.| | 863|xlang-ai/OpenAgents !2025-03-2842031|OpenAgents: An Open Platform for Language Agents in the Wild| | 864|alibaba/higress !2025-03-28419514|🤖 AI Gateway | | 865|ray-project/llm-numbers !2025-03-2841920 |Numbers every LLM developer should know| | 866|fudan-generative-vision/champ !2025-03-2841820|Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance| | 867|NVIDIA/garak !2025-03-2841795|the LLM vulnerability scanner| | 868|leetcode-mafia/cheetah !2025-03-2841740 |Whisper & GPT-based app for passing remote SWE interviews| | 869|ragapp/ragapp !2025-03-2841710|The easiest way to use Agentic RAG in any enterprise| | 870|collabora/WhisperSpeech !2025-03-2841692|An Open Source text-to-speech system built by inverting Whisper.| | 871|Facico/Chinese-Vicuna !2025-03-2841520 |Chinese-Vicuna: A Chinese Instruction-following LLaMA-based Model| | 872|openai/grok !2025-03-2841381|| | 873|CrazyBoyM/llama3-Chinese-chat !2025-03-2841361|Llama3 Chinese Repository with modified versions, and training and deployment resources| | 874|luban-agi/Awesome-AIGC-Tutorials !2025-03-2841301|Curated tutorials and resources for Large Language Models, AI Painting, and more.| | 875|damo-vilab/AnyDoor !2025-03-2841192|Official implementations for paper: Anydoor: zero-shot object-level image customization| | 876|raspberrypi/pico-sdk !2025-03-2841072|| | 877|mshumer/gpt-llm-trainer !2025-03-284097-1|| | 878|metavoiceio/metavoice-src !2025-03-284076-1|AI for human-level speech intelligence| | 879|intelowlproject/IntelOwl !2025-03-2840763|IntelOwl: manage your Threat Intelligence at scale| | 880|a16z-infra/ai-getting-started !2025-03-2840682|A Javascript AI getting started stack for weekend projects, including image/text models, vector stores, auth, and deployment configs| | 881|MarkFzp/mobile-aloha !2025-03-2840641|Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperation| | 882| keijiro/AICommand !2025-03-2840380 | ChatGPT integration with Unity Editor | | 883|Tencent/HunyuanDiT !2025-03-2840214|Hunyuan-DiT : A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding| | 884|hengyoush/kyanos !2025-03-2840061|Visualize the time packets spend in the kernel, watch & analyze in command line.| | 885|agiresearch/AIOS !2025-03-2840045|AIOS: LLM Agent Operating System| | 886|truefoundry/cognita !2025-03-2839773|RAG (Retrieval Augmented Generation) Framework for building modular, open source applications for production by TrueFoundry| | 887|X-PLUG/MobileAgent !2025-03-2839557|Mobile-Agent: Autonomous Multi-Modal Mobile Device Agent with Visual Perception| | 888|jackMort/ChatGPT.nvim !2025-03-2839231|ChatGPT Neovim Plugin: Effortless Natural Language Generation with OpenAI's ChatGPT API| | 889|microsoft/RD-Agent !2025-03-28388422|Research and development (R&D) is crucial for the enhancement of industrial productivity, especially in the AI era, where the core aspects of R&D are mainly focused on data and models. We are committed to automate these high-value generic R&D processes through our open source R&D automation tool RD-Agent, which let AI drive data-driven AI.| | 890|Significant-Gravitas/Auto-GPT-Plugins !2025-03-283882-1 |Plugins for Auto-GPT| | 891|apple/ml-mgie !2025-03-2838770|| | 892|OpenDriveLab/UniAD !2025-03-2838727|[CVPR 2023 Best Paper] Planning-oriented Autonomous Driving| | 893|llSourcell/DoctorGPT !2025-03-2838640|DoctorGPT is an LLM that can pass the US Medical Licensing Exam. It works offline, it's cross-platform, & your health data stays private.| | 894|FlagAI-Open/FlagAI !2025-03-2838601|FlagAI (Fast LArge-scale General AI models) is a fast, easy-to-use and extensible toolkit for large-scale model.| | 895|krishnaik06/Roadmap-To-Learn-Generative-AI-In-2024 !2025-03-2838513|Roadmap To Learn Generative AI In 2024| | 896|SysCV/sam-hq !2025-03-2838491|Segment Anything in High Quality| | 897|google/security-research !2025-03-2838420|This project hosts security advisories and their accompanying proof-of-concepts related to research conducted at Google which impact non-Google owned code.| | 898|shroominic/codeinterpreter-api !2025-03-2838330|Open source implementation of the ChatGPT Code Interpreter 👾| | 899|Yonom/assistant-ui !2025-03-2838308|React Components for AI Chat 💬 🚀| | 900|nucleuscloud/neosync !2025-03-2838262|Open source data anonymization and synthetic data orchestration for developers. Create high fidelity synthetic data and sync it across your environments.| | 901|ravenscroftj/turbopilot !2025-03-2838230 |Turbopilot is an open source large-language-model based code completion engine that runs locally on CPU| | 902|NVlabs/Sana !2025-03-28380810|SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer| | 903|huggingface/distil-whisper !2025-03-2838061|Distilled variant of Whisper for speech recognition. 6x faster, 50% smaller, within 1% word error rate.| | 904|Codium-ai/AlphaCodium !2025-03-2837971|code generation tool that surpasses most human competitors in CodeContests| | 905|fixie-ai/ultravox !2025-03-2837710|A fast multimodal LLM for real-time voice| | 906|unit-mesh/auto-dev !2025-03-28375715|🧙‍AutoDev: The AI-powered coding wizard with multilingual support 🌐, auto code generation 🏗️, and a helpful bug-slaying assistant 🐞! Customizable prompts 🎨 and a magic Auto Dev/Testing/Document/Agent feature 🧪 included! 🚀| | 907|Marker-Inc-Korea/AutoRAG !2025-03-2837432|AutoML tool for RAG| | 908|deepseek-ai/DeepSeek-VL !2025-03-283734-1|DeepSeek-VL: Towards Real-World Vision-Language Understanding| | 909|hiyouga/ChatGLM-Efficient-Tuning !2025-03-283692-1|Fine-tuning ChatGLM-6B with PEFT | | 910| Yue-Yang/ChatGPT-Siri !2025-03-2836921 | Shortcuts for Siri using ChatGPT API gpt-3.5-turbo model | | 911|0hq/WebGPT !2025-03-2836901 |Run GPT model on the browser with WebGPU. An implementation of GPT inference in less than ~2000 lines of vanilla Javascript.| | 912|cvg/LightGlue !2025-03-2836903|LightGlue: Local Feature Matching at Light Speed (ICCV 2023)| | 913|deanxv/coze-discord-proxy !2025-03-2836791|代理Discord-Bot对话Coze-Bot，实现API形式请求GPT4对话模型/微调模型| | 914|MervinPraison/PraisonAI !2025-03-2836764|PraisonAI application combines AutoGen and CrewAI or similar frameworks into a low-code solution for building and managing multi-agent LLM systems, focusing on simplicity, customisation, and efficient human-agent collaboration.| | 915|Ironclad/rivet !2025-03-2836345 |The open-source visual AI programming environment and TypeScript library| | 916|BasedHardware/OpenGlass !2025-03-2835851|Turn any glasses into AI-powered smart glasses| | 917|ricklamers/gpt-code-ui !2025-03-2835840 |An open source implementation of OpenAI's ChatGPT Code interpreter| | 918|whoiskatrin/chart-gpt !2025-03-2835830 |AI tool to build charts based on text input| | 919|github/CopilotForXcode !2025-03-2835788|Xcode extension for GitHub Copilot| | 920|hemansnation/God-Level-Data-Science-ML-Full-Stack !2025-03-2835570 |A collection of scientific methods, processes, algorithms, and systems to build stories & models. This roadmap contains 16 Chapters, whether you are a fresher in the field or an experienced professional who wants to transition into Data Science & AI| | 921|pytorch/torchchat !2025-03-2835461|Run PyTorch LLMs locally on servers, desktop and mobile| | 922| Kent0n-Li/ChatDoctor !2025-03-2835451 | A Medical Chat Model Fine-tuned on LLaMA Model using Medical Domain Knowledge | | 923|xtekky/chatgpt-clone !2025-03-283519-1 |ChatGPT interface with better UI| | 924|jupyterlab/jupyter-ai !2025-03-2835120|A generative AI extension for JupyterLab| | 925|pytorch/torchtitan !2025-03-2835064|A native PyTorch Library for large model training| | 926|minimaxir/simpleaichat !2025-03-2835031|Python package for easily interfacing with chat apps, with robust features and minimal code complexity.| | 927|srush/Tensor-Puzzles !2025-03-2834930|Solve puzzles. Improve your pytorch.| | 928|Helicone/helicone !2025-03-2834918|🧊 Open source LLM-Observability Platform for Developers. One-line integration for monitoring, metrics, evals, agent tracing, prompt management, playground, etc. Supports OpenAI SDK, Vercel AI SDK, Anthropic SDK, LiteLLM, LLamaIndex, LangChain, and more. 🍓 YC W23| | 929|run-llama/llama-hub !2025-03-2834740|A library of data loaders for LLMs made by the community -- to be used with LlamaIndex and/or LangChain| | 930|NExT-GPT/NExT-GPT !2025-03-2834700|Code and models for NExT-GPT: Any-to-Any Multimodal Large Language Model| | 931|souzatharsis/podcastfy !2025-03-2834661|An Open Source Python alternative to NotebookLM's podcast feature: Transforming Multimodal Content into Captivating Multilingual Audio Conversations with GenAI| | 932|Dataherald/dataherald !2025-03-2834450|Interact with your SQL database, Natural Language to SQL using LLMs| | 933|iryna-kondr/scikit-llm !2025-03-2834350 |Seamlessly integrate powerful language models like ChatGPT into scikit-learn for enhanced text analysis tasks.| | 934|Netflix/maestro !2025-03-2834230|Maestro: Netflix’s Workflow Orchestrator| | 935|CanadaHonk/porffor !2025-03-2833560|A from-scratch experimental AOT JS engine, written in JS| | 936|hustvl/Vim !2025-03-2833323|Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model| | 937|pashpashpash/vault-ai !2025-03-2833250 |OP Vault ChatGPT: Give ChatGPT long-term memory using the OP Stack (OpenAI + Pinecone Vector Database). Upload your own custom knowledge base files (PDF, txt, etc) using a simple React frontend.| | 938|tencentmusic/supersonic !2025-03-28330611|SuperSonic is the next-generation BI platform that integrates Chat BI (powered by LLM) and Headless BI (powered by semantic layer) paradigms.| | 939|billmei/every-chatgpt-gui !2025-03-2832981|Every front-end GUI client for ChatGPT| | 940|microsoft/torchgeo !2025-03-2832772|TorchGeo: datasets, samplers, transforms, and pre-trained models for geospatial data| | 941|LLMBook-zh/LLMBook-zh.github.io !2025-03-28326110|《大语言模型》作者：赵鑫，李军毅，周昆，唐天一，文继荣| | 942|dvlab-research/MiniGemini !2025-03-2832601|Official implementation for Mini-Gemini| | 943|rashadphz/farfalle !2025-03-2832460|🔍 AI search engine - self-host with local or cloud LLMs| | 944|Luodian/Otter !2025-03-2832450|🦦 Otter, a multi-modal model based on OpenFlamingo (open-sourced version of DeepMind's Flamingo), trained on MIMIC-IT and showcasing improved instruction-following and in-context learning ability.| | 945|AprilNEA/ChatGPT-Admin-Web !2025-03-2832370 | ChatGPT WebUI with user management and admin dashboard system| | 946|MarkFzp/act-plus-plus !2025-03-2832365|Imitation Learning algorithms with Co-traing for Mobile ALOHA: ACT, Diffusion Policy, VINN| | 947|ethen8181/machine-learning !2025-03-2832310|🌎 machine learning tutorials (mainly in Python3)| | 948|opengeos/segment-geospatial !2025-03-2832312 |A Python package for segmenting geospatial data with the Segment Anything Model (SAM)| | 949|iusztinpaul/hands-on-llms !2025-03-283225-2|🦖 𝗟𝗲𝗮𝗿𝗻 about 𝗟𝗟𝗠𝘀, 𝗟𝗟𝗠𝗢𝗽𝘀, and 𝘃𝗲𝗰𝘁𝗼𝗿 𝗗𝗕𝘀 for free by designing, training, and deploying a real-time financial advisor LLM system ~ 𝘴𝘰𝘶𝘳𝘤𝘦 𝘤𝘰𝘥𝘦 + 𝘷𝘪𝘥𝘦𝘰 & 𝘳𝘦𝘢𝘥𝘪𝘯𝘨 𝘮𝘢𝘵𝘦𝘳𝘪𝘢𝘭𝘴| | 950|ToTheBeginning/PuLID !2025-03-2832221|Official code for PuLID: Pure and Lightning ID Customization via Contrastive Alignment| | 951|neo4j-labs/llm-graph-builder !2025-03-2832164|Neo4j graph construction from unstructured data using LLMs| | 952|OpenGVLab/InternGPT !2025-03-2832150 |InternGPT (iGPT) is an open source demo platform where you can easily showcase your AI models. Now it supports DragGAN, ChatGPT, ImageBind, multimodal chat like GPT-4, SAM, interactive image editing, etc. Try it at igpt.opengvlab.com (支持DragGAN、ChatGPT、ImageBind、SAM的在线Demo系统)| | 953|PKU-YuanGroup/Video-LLaVA !2025-03-2832060 |Video-LLaVA: Learning United Visual Representation by Alignment Before Projection| | 954|DataTalksClub/llm-zoomcamp !2025-03-2832030|LLM Zoomcamp - a free online course about building an AI bot that can answer questions about your knowledge base| | 955|gptscript-ai/gptscript !2025-03-2832010|Natural Language Programming| |!green-up-arrow.svg 956|isaac-sim/IsaacLab !2025-03-28320113|Unified framework for robot learning built on NVIDIA Isaac Sim| |!red-down-arrow 957|ai-boost/Awesome-GPTs !2025-03-2832003|Curated list of awesome GPTs 👍.| | 958|huggingface/safetensors !2025-03-2831901|Simple, safe way to store and distribute tensors| | 959|linyiLYi/bilibot !2025-03-2831771|A local chatbot fine-tuned by bilibili user comments.| | 960| project-baize/baize-chatbot !2025-03-283168-1 | Let ChatGPT teach your own chatbot in hours with a single GPU! | | 961|Azure-Samples/cognitive-services-speech-sdk !2025-03-2831280|Sample code for the Microsoft Cognitive Services Speech SDK| | 962|microsoft/Phi-3CookBook !2025-03-2831231|This is a Phi-3 book for getting started with Phi-3. Phi-3, a family of open AI models developed by Microsoft. Phi-3 models are the most capable and cost-effective small language models (SLMs) available, outperforming models of the same size and next size up across a variety of language, reasoning, coding, and math benchmarks.| | 963|neuralmagic/deepsparse !2025-03-2831180|Sparsity-aware deep learning inference runtime for CPUs| | 964|sugarforever/chat-ollama !2025-03-2831000|ChatOllama is an open source chatbot based on LLMs. It supports a wide range of language models, and knowledge base management.| | 965|amazon-science/chronos-forecasting !2025-03-2830974|Chronos: Pretrained (Language) Models for Probabilistic Time Series Forecasting| | 966|damo-vilab/i2vgen-xl !2025-03-2830902|Official repo for VGen: a holistic video generation ecosystem for video generation building on diffusion models| | 967|google-deepmind/gemma !2025-03-2830733|Open weights LLM from Google DeepMind.| | 968|iree-org/iree !2025-03-2830733|A retargetable MLIR-based machine learning compiler and runtime toolkit.| | 969|NVlabs/VILA !2025-03-2830724|VILA - a multi-image visual language model with training, inference and evaluation recipe, deployable from cloud to edge (Jetson Orin and laptops)| | 970|microsoft/torchscale !2025-03-2830661|Foundation Architecture for (M)LLMs| | 971|openai/openai-realtime-console !2025-03-2830656|React app for inspecting, building and debugging with the Realtime API| | 972|daveshap/OpenAIAgentSwarm !2025-03-2830610|HAAS = Hierarchical Autonomous Agent Swarm - "Resistance is futile!"| | 973|microsoft/PromptWizard !2025-03-2830555|Task-Aware Agent-driven Prompt Optimization Framework| | 974|CVI-SZU/Linly !2025-03-2830490 |Chinese-LLaMA basic model; ChatFlow Chinese conversation model; NLP pre-training/command fine-tuning dataset| | 975|cohere-ai/cohere-toolkit !2025-03-2830130|Toolkit is a collection of prebuilt components enabling users to quickly build and deploy RAG applications.| | 976|adamcohenhillel/ADeus !2025-03-2830131|An open source AI wearable device that captures what you say and hear in the real world and then transcribes and stores it on your own server. You can then chat with Adeus using the app, and it will have all the right context about what you want to talk about - a truly personalized, personal AI.| | 977|Lightning-AI/LitServe !2025-03-2830132|Lightning-fast serving engine for AI models. Flexible. Easy. Enterprise-scale.| | 978|potpie-ai/potpie !2025-03-2829973|Prompt-To-Agent : Create custom engineering agents for your codebase| | 979|ant-design/x !2025-03-28299529|Craft AI-driven interfaces effortlessly 🤖| | 980|meta-llama/PurpleLlama !2025-03-2829832|Set of tools to assess and improve LLM security.| | 981|williamyang1991/RerenderAVideo !2025-03-2829800|[SIGGRAPH Asia 2023] Rerender A Video: Zero-Shot Text-Guided Video-to-Video Translation| | 982|baichuan-inc/Baichuan-13B !2025-03-2829790|A 13B large language model developed by Baichuan Intelligent Technology| | 983|Stability-AI/stable-audio-tools !2025-03-2829761|Generative models for conditional audio generation| | 984|li-plus/chatglm.cpp !2025-03-2829720|C++ implementation of ChatGLM-6B & ChatGLM2-6B & ChatGLM3 & more LLMs| | 985|NVIDIA/GenerativeAIExamples !2025-03-2829546|Generative AI reference workflows optimized for accelerated infrastructure and microservice architecture.| | 986|Josh-XT/AGiXT !2025-03-2829521 |AGiXT is a dynamic AI Automation Platform that seamlessly orchestrates instruction management and complex task execution across diverse AI providers. Combining adaptive memory, smart features, and a versatile plugin system, AGiXT delivers efficient and comprehensive AI solutions.| | 987|MrForExample/ComfyUI-3D-Pack !2025-03-2829515|An extensive node suite that enables ComfyUI to process 3D inputs (Mesh & UV Texture, etc) using cutting edge algorithms (3DGS, NeRF, etc.)| | 988|olimorris/codecompanion.nvim !2025-03-28295111|✨ AI-powered coding, seamlessly in Neovim. Supports Anthropic, Copilot, Gemini, Ollama, OpenAI and xAI LLMs| | 989|salesforce/CodeT5 !2025-03-282940-1 |Home of CodeT5: Open Code LLMs for Code Understanding and Generation| | 990|facebookresearch/ijepa !2025-03-2829391|Official codebase for I-JEPA, the Image-based Joint-Embedding Predictive Architecture. First outlined in the CVPR paper, "Self-supervised learning from images with a joint-embedding predictive architecture."| | 991|eureka-research/Eureka !2025-03-2829351|Official Repository for "Eureka: Human-Level Reward Design via Coding Large Language Models"| | 992|NVIDIA/trt-llm-rag-windows !2025-03-282934-1|A developer reference project for creating Retrieval Augmented Generation (RAG) chatbots on Windows using TensorRT-LLM| | 993|gmpetrov/databerry !2025-03-282930-1|The no-code platform for building custom LLM Agents| | 994|AI4Finance-Foundation/FinRobot !2025-03-28291946|FinRobot: An Open-Source AI Agent Platform for Financial Applications using LLMs 🚀 🚀 🚀| | 995|nus-apr/auto-code-rover !2025-03-2829013|A project structure aware autonomous software engineer aiming for autonomous program improvement| | 996|deepseek-ai/DreamCraft3D !2025-03-2828921|[ICLR 2024] Official implementation of DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior| | 997|mlabonne/llm-datasets !2025-03-2828848|High-quality datasets, tools, and concepts for LLM fine-tuning.| | 998|facebookresearch/jepa !2025-03-2828712|PyTorch code and models for V-JEPA self-supervised learning from video.| | 999|facebookresearch/habitat-sim !2025-03-2828604|A flexible, high-performance 3D simulator for Embodied AI research.| | 1000|xenova/whisper-web !2025-03-2828581|ML-powered speech recognition directly in your browser| | 1001|cvlab-columbia/zero123 !2025-03-2828530|Zero-1-to-3: Zero-shot One Image to 3D Object: https://zero123.cs.columbia.edu/| | 1002|yuruotong1/autoMate !2025-03-28285121|Like Manus, Computer Use Agent(CUA) and Omniparser, we are computer-using agents.AI-driven local automation assistant that uses natural language to make computers work by themselves| | 1003|muellerberndt/mini-agi !2025-03-282845-1 |A minimal generic autonomous agent based on GPT3.5/4. Can analyze stock prices, perform network security tests, create art, and order pizza.| | 1004|allenai/open-instruct !2025-03-2828432|| | 1005|CodingChallengesFYI/SharedSolutions !2025-03-2828360|Publicly shared solutions to Coding Challenges| | 1006|hegelai/prompttools !2025-03-2828220|Open-source tools for prompt testing and experimentation, with support for both LLMs (e.g. OpenAI, LLaMA) and vector databases (e.g. Chroma, Weaviate).| | 1007|mazzzystar/Queryable !2025-03-2828222|Run CLIP on iPhone to Search Photos.| | 1008|Doubiiu/DynamiCrafter !2025-03-2828173|DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors| | 1009|SamurAIGPT/privateGPT !2025-03-282805-1 |An app to interact privately with your documents using the power of GPT, 100% privately, no data leaks| | 1010|facebookresearch/Pearl !2025-03-2827951|A Production-ready Reinforcement Learning AI Agent Library brought by the Applied Reinforcement Learning team at Meta.| | 1011|intuitem/ciso-assistant-community !2025-03-2827954|CISO Assistant is a one-stop-shop for GRC, covering Risk, AppSec and Audit Management and supporting +70 frameworks worldwide with auto-mapping: NIST CSF, ISO 27001, SOC2, CIS, PCI DSS, NIS2, CMMC, PSPF, GDPR, HIPAA, Essential Eight, NYDFS-500, DORA, NIST AI RMF, 800-53, 800-171, CyFun, CJIS, AirCyber, NCSC, ECC, SCF and so much more| | 1012|facebookresearch/audio2photoreal !2025-03-2827840|Code and dataset for photorealistic Codec Avatars driven from audio| | 1013|Azure/azure-rest-api-specs !2025-03-2827770|The source for REST API specifications for Microsoft Azure.| | 1014|SCUTlihaoyu/open-chat-video-editor !2025-03-2827690 |Open source short video automatic generation tool| | 1015|Alpha-VLLM/LLaMA2-Accessory !2025-03-2827642|An Open-source Toolkit for LLM Development| | 1016|johnma2006/mamba-minimal !2025-03-2827601|Simple, minimal implementation of the Mamba SSM in one file of PyTorch.| | 1017|nerfstudio-project/gsplat !2025-03-2827576|CUDA accelerated rasterization of gaussian splatting| | 1018|Physical-Intelligence/openpi !2025-03-28274617|| | 1019|leptonai/leptonai !2025-03-2827246|A Pythonic framework to simplify AI service building| |!green-up-arrow.svg 1020|joanrod/star-vector !2025-03-28271149|StarVector is a foundation model for SVG generation that transforms vectorization into a code generation task. Using a vision-language modeling architecture, StarVector processes both visual and textual inputs to produce high-quality SVG code with remarkable precision.| |!red-down-arrow 1021|jqnatividad/qsv !2025-03-2827092|CSVs sliced, diced & analyzed.| | 1022|FranxYao/chain-of-thought-hub !2025-03-2826991|Benchmarking large language models' complex reasoning ability with chain-of-thought prompting| | 1023|princeton-nlp/SWE-bench !2025-03-2826965|[ICLR 2024] SWE-Bench: Can Language Models Resolve Real-world Github Issues?| | 1024|elastic/otel-profiling-agent !2025-03-2826930|The production-scale datacenter profiler| | 1025|src-d/hercules !2025-03-2826900|Gaining advanced insights from Git repository history.| | 1026|lanqian528/chat2api !2025-03-2826695|A service that can convert ChatGPT on the web to OpenAI API format.| | 1027|ishan0102/vimGPT !2025-03-2826681|Browse the web with GPT-4V and Vimium| | 1028|TMElyralab/MuseV !2025-03-2826650|MuseV: Infinite-length and High Fidelity Virtual Human Video Generation with Visual Conditioned Parallel Denoising| | 1029|georgia-tech-db/eva !2025-03-2826600 |AI-Relational Database System | | 1030|kubernetes-sigs/controller-runtime !2025-03-2826590|Repo for the controller-runtime subproject of kubebuilder (sig-apimachinery)| | 1031|gptlink/gptlink !2025-03-2826550 |Build your own free commercial ChatGPT environment in 10 minutes. The setup is simple and includes features such as user management, orders, tasks, and payments| | 1032|pytorch/executorch !2025-03-2826534|On-device AI across mobile, embedded and edge for PyTorch| | 1033|NVIDIA/nv-ingest !2025-03-2826290|NVIDIA Ingest is an early access set of microservices for parsing hundreds of thousands of complex, messy unstructured PDFs and other enterprise documents into metadata and text to embed into retrieval systems.| | 1034|SuperTux/supertux !2025-03-2826081|SuperTux source code| | 1035|abi/secret-llama !2025-03-2826050|Fully private LLM chatbot that runs entirely with a browser with no server needed. Supports Mistral and LLama 3.| | 1036|liou666/polyglot !2025-03-2825841 |Desktop AI Language Practice Application| | 1037|janhq/nitro !2025-03-2825821|A fast, lightweight, embeddable inference engine to supercharge your apps with local AI. OpenAI-compatible API| | 1038|deepseek-ai/DeepSeek-Math !2025-03-2825825|DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models| | 1039|anthropics/prompt-eng-interactive-tutorial !2025-03-2825781|Anthropic's Interactive Prompt Engineering Tutorial| | 1040|microsoft/promptbench !2025-03-2825741|A unified evaluation framework for large language models| | 1041|baaivision/Painter !2025-03-2825580 |Painter & SegGPT Series: Vision Foundation Models from BAAI| | 1042|OpenPipe/OpenPipe !2025-03-2825581|Turn expensive prompts into cheap fine-tuned models| | 1043|TracecatHQ/tracecat !2025-03-2825531|😼 The AI-native, open source alternative to Tines / Splunk SOAR.| | 1044|JoshuaC215/agent-service-toolkit !2025-03-2825528|Full toolkit for running an AI agent service built with LangGraph, FastAPI and Streamlit| | 1045|databricks/dbrx !2025-03-2825460|Code examples and resources for DBRX, a large language model developed by Databricks| | 1046|lamini-ai/lamini !2025-03-2825271 |Official repo for Lamini's data generator for generating instructions to train instruction-following LLMs| | 1047|mshumer/gpt-author !2025-03-282510-1|| | 1048|TMElyralab/MusePose !2025-03-2824971|MusePose: a Pose-Driven Image-to-Video Framework for Virtual Human Generation| | 1049|Kludex/fastapi-tips !2025-03-2824974|FastAPI Tips by The FastAPI Expert!| | 1050|openai/simple-evals !2025-03-2824813|| | 1051|iterative/datachain !2025-03-2824732|AI-data warehouse to enrich, transform and analyze data from cloud storages| | 1052|girafe-ai/ml-course !2025-03-2824703|Open Machine Learning course| | 1053|kevmo314/magic-copy !2025-03-2824620 |Magic Copy is a Chrome extension that uses Meta's Segment Anything Model to extract a foreground object from an image and copy it to the clipboard.| | 1054|Eladlev/AutoPrompt !2025-03-2824432|A framework for prompt tuning using Intent-based Prompt Calibration| | 1055|OpenBMB/CPM-Bee !2025-03-282434-1 |A bilingual large-scale model with trillions of parameters| | 1056|IDEA-Research/T-Rex !2025-03-2824310|T-Rex2: Towards Generic Object Detection via Text-Visual Prompt Synergy| | 1057|microsoft/genaiscript !2025-03-2824202|Automatable GenAI Scripting| | 1058|paulpierre/RasaGPT !2025-03-2824090 |💬 RasaGPT is the first headless LLM chatbot platform built on top of Rasa and Langchain. Built w/ Rasa, FastAPI, Langchain, LlamaIndex, SQLModel, pgvector, ngrok, telegram| | 1059|ashishpatel26/LLM-Finetuning !2025-03-2823911|LLM Finetuning with peft| | 1060|SoraWebui/SoraWebui !2025-03-2823570|SoraWebui is an open-source Sora web client, enabling users to easily create videos from text with OpenAI's Sora model.| | 1061|6drf21e/ChatTTScolab !2025-03-2823491|🚀 一键部署（含离线整合包）！基于 ChatTTS ，支持音色抽卡、长音频生成和分角色朗读。简单易用，无需复杂安装。| | 1062|Azure/PyRIT !2025-03-2823343|The Python Risk Identification Tool for generative AI (PyRIT) is an open access automation framework to empower security professionals and machine learning engineers to proactively find risks in their generative AI systems.| | 1063|tencent-ailab/V-Express !2025-03-2823201|V-Express aims to generate a talking head video under the control of a reference image, an audio, and a sequence of V-Kps images.| | 1064|THUDM/CogVLM2 !2025-03-2823170|GPT4V-level open-source multi-modal model based on Llama3-8B| | 1065|dvmazur/mixtral-offloading !2025-03-2823001|Run Mixtral-8x7B models in Colab or consumer desktops| | 1066|semanser/codel !2025-03-2822950|✨ Fully autonomous AI Agent that can perform complicated tasks and projects using terminal, browser, and editor.| | 1067|mshumer/gpt-investor !2025-03-2822590|| | 1068|aixcoder-plugin/aiXcoder-7B !2025-03-2822550|official repository of aiXcoder-7B Code Large Language Model| | 1069|Azure-Samples/graphrag-accelerator !2025-03-2822503|One-click deploy of a Knowledge Graph powered RAG (GraphRAG) in Azure| | 1070|emcf/engshell !2025-03-2821830 |An English-language shell for any OS, powered by LLMs| | 1071|hncboy/chatgpt-web-java !2025-03-2821771|ChatGPT project developed in Java, based on Spring Boot 3 and JDK 17, supports both AccessToken and ApiKey modes| | 1072|openai/consistencydecoder !2025-03-2821692|Consistency Distilled Diff VAE| | 1073|Alpha-VLLM/Lumina-T2X !2025-03-2821681|Lumina-T2X is a unified framework for Text to Any Modality Generation| | 1074|bghira/SimpleTuner !2025-03-2821612|A general fine-tuning kit geared toward Stable Diffusion 2.1, Stable Diffusion 3, DeepFloyd, and SDXL.| | 1075|JiauZhang/DragGAN !2025-03-2821530 |Implementation of DragGAN: Interactive Point-based Manipulation on the Generative Image Manifold| | 1076|cgpotts/cs224u !2025-03-2821390|Code for Stanford CS224u| | 1077|PKU-YuanGroup/MoE-LLaVA !2025-03-2821300|Mixture-of-Experts for Large Vision-Language Models| | 1078|darrenburns/elia !2025-03-2820831|A snappy, keyboard-centric terminal user interface for interacting with large language models. Chat with ChatGPT, Claude, Llama 3, Phi 3, Mistral, Gemma and more.| | 1079|ageerle/ruoyi-ai !2025-03-28207898|RuoYi AI 是一个全栈式 AI 开发平台，旨在帮助开发者快速构建和部署个性化的 AI 应用。| | 1080|NVIDIA/gpu-operator !2025-03-2820510|NVIDIA GPU Operator creates/configures/manages GPUs atop Kubernetes| | 1081|BAAI-Agents/Cradle !2025-03-2820481|The Cradle framework is a first attempt at General Computer Control (GCC). Cradle supports agents to ace any computer task by enabling strong reasoning abilities, self-improvment, and skill curation, in a standardized general environment with minimal requirements.| | 1082|microsoft/aici !2025-03-2820080|AICI: Prompts as (Wasm) Programs| | 1083|PRIS-CV/DemoFusion !2025-03-2820040|Let us democratise high-resolution generation! (arXiv 2023)| | 1084|apple/axlearn !2025-03-2820012|An Extensible Deep Learning Library| | 1085|naver/mast3r !2025-03-2819685|Grounding Image Matching in 3D with MASt3R| | 1086|liltom-eth/llama2-webui !2025-03-281958-1|Run Llama 2 locally with gradio UI on GPU or CPU from anywhere (Linux/Windows/Mac). Supporting Llama-2-7B/13B/70B with 8-bit, 4-bit. Supporting GPU inference (6 GB VRAM) and CPU inference.| | 1087|GaParmar/img2img-turbo !2025-03-2819582|One-step image-to-image with Stable Diffusion turbo: sketch2image, day2night, and more| | 1088|Niek/chatgpt-web !2025-03-2819560|ChatGPT web interface using the OpenAI API| | 1089|huggingface/cookbook !2025-03-2819421|Open-source AI cookbook| | 1090|pytorch/ao !2025-03-2819241|PyTorch native quantization and sparsity for training and inference| | 1091|emcie-co/parlant !2025-03-2819053|The behavior guidance framework for customer-facing LLM agents| | 1092|ymcui/Chinese-LLaMA-Alpaca-3 !2025-03-2818980|中文羊驼大模型三期项目 (Chinese Llama-3 LLMs) developed from Meta Llama 3| | 1093|Nutlope/notesGPT !2025-03-2818811|Record voice notes & transcribe, summarize, and get tasks| | 1094|InstantStyle/InstantStyle !2025-03-2818791|InstantStyle: Free Lunch towards Style-Preserving in Text-to-Image Generation 🔥| | 1095|idaholab/moose !2025-03-2818771|Multiphysics Object Oriented Simulation Environment| | 1096|The-OpenROAD-Project/OpenROAD !2025-03-2818351|OpenROAD's unified application implementing an RTL-to-GDS Flow. Documentation at https://openroad.readthedocs.io/en/latest/| | 1097|alibaba/spring-ai-alibaba !2025-03-281831121|Agentic AI Framework for Java Developers| | 1098|ytongbai/LVM !2025-03-2817990|Sequential Modeling Enables Scalable Learning for Large Vision Models| | 1099|microsoft/sample-app-aoai-chatGPT !2025-03-2817981|[PREVIEW] Sample code for a simple web chat experience targeting chatGPT through AOAI.| | 1100|AI-Citizen/SolidGPT !2025-03-2817830|Chat everything with your code repository, ask repository level code questions, and discuss your requirements. AI Scan and learning your code repository, provide you code repository level answer🧱 🧱| | 1101|YangLing0818/RPG-DiffusionMaster !2025-03-2817784|Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs (PRG)| | 1102|kyegomez/BitNet !2025-03-2817710|Implementation of "BitNet: Scaling 1-bit Transformers for Large Language Models" in pytorch| | 1103|eloialonso/diamond !2025-03-2817671|DIAMOND (DIffusion As a Model Of eNvironment Dreams) is a reinforcement learning agent trained in a diffusion world model.| | 1104|flowdriveai/flowpilot !2025-03-2817250|flow-pilot is an openpilot based driver assistance system that runs on linux, windows and android powered machines.| | 1105|xlang-ai/OSWorld !2025-03-2817200|OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments| | 1106|linyiLYi/snake-ai !2025-03-2817031|An AI agent that beats the classic game "Snake".| | 1107|baaivision/Emu !2025-03-2816991|Emu Series: Generative Multimodal Models from BAAI| | 1108|kevmo314/scuda !2025-03-2816870|SCUDA is a GPU over IP bridge allowing GPUs on remote machines to be attached to CPU-only machines.| | 1109|SharifiZarchi/IntroductiontoMachineLearning !2025-03-2816701|دوره‌ی مقدمه‌ای بر یادگیری ماشین، برای دانشجویان| | 1110|google/maxtext !2025-03-2816670|A simple, performant and scalable Jax LLM!| | 1111|ml-explore/mlx-swift-examples !2025-03-2816471|Examples using MLX Swift| | 1112|unitreerobotics/unitreerlgym !2025-03-2816256|| | 1113|collabora/WhisperFusion !2025-03-2815901|WhisperFusion builds upon the capabilities of WhisperLive and WhisperSpeech to provide a seamless conversations with an AI.| | 1114|lichao-sun/Mora !2025-03-2815520|Mora: More like Sora for Generalist Video Generation| | 1115|GoogleCloudPlatform/localllm !2025-03-2815370|Run LLMs locally on Cloud Workstations| | 1116|TencentARC/BrushNet !2025-03-2815330|The official implementation of paper "BrushNet: A Plug-and-Play Image Inpainting Model with Decomposed Dual-Branch Diffusion"| | 1117|ai-christianson/RA.Aid !2025-03-2815288|Develop software autonomously.| | 1118|stephansturges/WALDO !2025-03-2815170|Whereabouts Ascertainment for Low-lying Detectable Objects. The SOTA in FOSS AI for drones!| | 1119|skills/copilot-codespaces-vscode !2025-03-2815112|Develop with AI-powered code suggestions using GitHub Copilot and VS Code| | 1120|andrewnguonly/Lumos !2025-03-2814920|A RAG LLM co-pilot for browsing the web, powered by local LLMs| | 1121|TeamNewPipe/NewPipeExtractor !2025-03-2814811|NewPipe's core library for extracting data from streaming sites| | 1122|mhamilton723/FeatUp !2025-03-2814770|Official code for "FeatUp: A Model-Agnostic Frameworkfor Features at Any Resolution" ICLR 2024| | 1123|AnswerDotAI/fsdpqlora !2025-03-2814671|Training LLMs with QLoRA + FSDP| | 1124|jgravelle/AutoGroq !2025-03-2814330|| | 1125|OpenGenerativeAI/llm-colosseum !2025-03-2814130|Benchmark LLMs by fighting in Street Fighter 3! The new way to evaluate the quality of an LLM| | 1126|microsoft/vscode-ai-toolkit !2025-03-2814000|| | 1127|McGill-NLP/webllama !2025-03-2813930|Llama-3 agents that can browse the web by following instructions and talking to you| | 1128|lucidrains/self-rewarding-lm-pytorch !2025-03-2813760|Implementation of the training framework proposed in Self-Rewarding Language Model, from MetaAI| | 1129|ishaan1013/sandbox !2025-03-2813650|A cloud-based code editing environment with an AI copilot and real-time collaboration.| | 1130|goatcorp/Dalamud !2025-03-2813275|FFXIV plugin framework and API| | 1131|Lightning-AI/lightning-thunder !2025-03-2813151|Make PyTorch models Lightning fast! Thunder is a source to source compiler for PyTorch. It enables using different hardware executors at once.| | 1132|PKU-YuanGroup/MagicTime !2025-03-2813052|MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators| | 1133|SakanaAI/evolutionary-model-merge !2025-03-2813000|Official repository of Evolutionary Optimization of Model Merging Recipes| | 1134|a-real-ai/pywinassistant !2025-03-2812950|The first open source Large Action Model generalist Artificial Narrow Intelligence that controls completely human user interfaces by only using natural language. PyWinAssistant utilizes Visualization-of-Thought Elicits Spatial Reasoning in Large Language Models.| | 1135|TraceMachina/nativelink !2025-03-2812630|NativeLink is an open source high-performance build cache and remote execution server, compatible with Bazel, Buck2, Reclient, and other RBE-compatible build systems. It offers drastically faster builds, reduced test flakiness, and significant infrastructure cost savings.| | 1136|MLSysOps/MLE-agent !2025-03-2812500|🤖 MLE-Agent: Your intelligent companion for seamless AI engineering and research. 🔍 Integrate with arxiv and paper with code to provide better code/research plans 🧰 OpenAI, Ollama, etc supported. 🎆 Code RAG| | 1137|wpilibsuite/allwpilib !2025-03-2811610|Official Repository of WPILibJ and WPILibC| | 1138|elfvingralf/macOSpilot-ai-assistant !2025-03-2811470|Voice + Vision powered AI assistant that answers questions about any application, in context and in audio.| | 1139|langchain-ai/langchain-extract !2025-03-2811210|🦜⛏️ Did you say you like data?| | 1140|FoundationVision/GLEE !2025-03-2811120|【CVPR2024】GLEE: General Object Foundation Model for Images and Videos at Scale| | 1141|Profluent-AI/OpenCRISPR !2025-03-2810990|AI-generated gene editing systems| | 1142|zju3dv/EasyVolcap !2025-03-2810821|[SIGGRAPH Asia 2023 (Technical Communications)] EasyVolcap: Accelerating Neural Volumetric Video Research| | 1143|PaddlePaddle/PaddleHelix !2025-03-2810560|Bio-Computing Platform Featuring Large-Scale Representation Learning and Multi-Task Deep Learning “螺旋桨”生物计算工具集| | 1144|myshell-ai/JetMoE !2025-03-289800|Reaching LLaMA2 Performance with 0.1M Dollars| | 1145|likejazz/llama3.np !2025-03-289770|llama3.np is pure NumPy implementation for Llama 3 model.| | 1146|mustafaaljadery/gemma-2B-10M !2025-03-289500|Gemma 2B with 10M context length using Infini-attention.| | 1147|HITsz-TMG/FilmAgent !2025-03-289382|Resources of our paper "FilmAgent: A Multi-Agent Framework for End-to-End Film Automation in Virtual 3D Spaces". New versions in the making!| | 1148|aws-samples/amazon-bedrock-samples !2025-03-289362|This repository contains examples for customers to get started using the Amazon Bedrock Service. This contains examples for all available foundational models| | 1149|Akkudoktor-EOS/EOS !2025-03-2893154|This repository features an Energy Optimization System (EOS) that optimizes energy distribution, usage for batteries, heat pumps& household devices. It includes predictive models for electricity prices (planned), load forecasting& dynamic optimization to maximize energy efficiency & minimize costs. Founder Dr. Andreas Schmitz (YouTube @akkudoktor)| Tip: | symbol| rule | | :----| :---- | |🔥 | 256 1k| |!green-up-arrow.svg !red-down-arrow | ranking up / down| |⭐ | on trending page today| [Back to Top] Tools | No. | Tool | Description | | ----:|:----------------------------------------------- |:------------------------------------------------------------------------------------------- | | 1 | ChatGPT | A sibling model to InstructGPT, which is trained to follow instructions in a prompt and provide a detailed response | | 2 | DALL·E 2 | Create original, realistic images and art from a text description | | 3 | Murf AI | AI enabled, real people's voices| | 4 | Midjourney | An independent research lab that produces an artificial intelligence program under the same name that creates images from textual descriptions, used in Discord | 5 | Make-A-Video | Make-A-Video is a state-of-the-art AI system that generates videos from text | | 6 | Creative Reality™ Studio by D-ID| Use generative AI to create future-facing videos| | 7 | chat.D-ID| The First App Enabling Face-to-Face Conversations with ChatGPT| | 8 | Notion AI| Access the limitless power of AI, right inside Notion. Work faster. Write better. Think bigger. | | 9 | Runway| Text to Video with Gen-2 | | 10 | Resemble AI| Resemble’s AI voice generator lets you create human–like voice overs in seconds | | 11 | Cursor| Write, edit, and chat about your code with a powerful AI | | 12 | Hugging Face| Build, train and deploy state of the art models powered by the reference open source in machine learning | | 13 | Claude | A next-generation AI assistant for your tasks, no matter the scale | | 14 | Poe| Poe lets you ask questions, get instant answers, and have back-and-forth conversations with AI. Gives access to GPT-4, gpt-3.5-turbo, Claude from Anthropic, and a variety of other bots| [Back to Top] Websites | No. | WebSite |Description | | ----:|:------------------------------------------ |:---------------------------------------------------------------------------------------- | | 1 | OpenAI | An artificial intelligence research lab | | 2 | Bard | Base Google's LaMDA chatbots and pull from internet | | 3 | ERNIE Bot | Baidu’s new generation knowledge-enhanced large language model is a new member of the Wenxin large model family | | 4 | DALL·E 2 | An AI system that can create realistic images and art from a description in natural language | | 5 | Whisper | A general-purpose speech recognition model | | 6| CivitAI| A platform that makes it easy for people to share and discover resources for creating AI art| | 7|D-ID| D-ID’s Generative AI enables users to transform any picture or video into extraordinary experiences| | 8| Nvidia eDiff-I| Text-to-Image Diffusion Models with Ensemble of Expert Denoisers | | 9| Stability AI| The world's leading open source generative AI company which opened source Stable Diffusion | | 10| Meta AI| Whether it be research, product or infrastructure development, we’re driven to innovate responsibly with AI to benefit the world | | 11| ANTHROPIC| AI research and products that put safety at the frontier | [Back to Top] Reports&Papers | No. | Report&Paper | Description | |:---- |:-------------------------------------------------------------------------------------------------------------- |:---------------------------------------------------- | | 1 | GPT-4 Technical Report | GPT-4 Technical Report | | 2 | mli/paper-reading | Deep learning classics and new papers are read carefully paragraph by paragraph. | | 3 | labmlai/annotateddeeplearningpaperimplementations| A collection of simple PyTorch implementations of neural networks and related algorithms, which are documented with explanations | | 4 | Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models | Talking, Drawing and Editing with Visual Foundation Models | | 5 | OpenAI Research | The latest research report and papers from OpenAI | | 6 | Make-A-Video: Text-to-Video Generation without Text-Video Data|Meta's Text-to-Video Generation| | 7 | eDiff-I: Text-to-Image Diffusion Models with Ensemble of Expert Denoisers| Nvidia eDiff-I - New generation of generative AI content creation tool | | 8 | Training an Assistant-style Chatbot with Large Scale Data Distillation from GPT-3.5-Turbo | 2023 GPT4All Technical Report | | 9 | Segment Anything| Meta Segment Anything | | 10 | LLaMA: Open and Efficient Foundation Language Models| LLaMA: a collection of foundation language models ranging from 7B to 65B parameters| | 11 | papers-we-love/papers-we-love |Papers from the computer science community to read and discuss| | 12 | CVPR 2023 papers |The most exciting and influential CVPR 2023 papers| [Back to Top] Tutorials | No. | Tutorial | Description| |:---- |:---------------------------------------------------------------- | --- | | 1 | Coursera - Machine Learning | The Machine Learning Specialization Course taught by Dr. Andrew Ng| | 2 | microsoft/ML-For-Beginners | 12 weeks, 26 lessons, 52 quizzes, classic Machine Learning for all| | 3 | ChatGPT Prompt Engineering for Developers | This short course taught by Isa Fulford (OpenAI) and Andrew Ng (DeepLearning.AI) will teach how to use a large language model (LLM) to quickly build new and powerful applications | | 4 | Dive into Deep Learning |Targeting Chinese readers, functional and open for discussion. The Chinese and English versions are used for teaching in over 400 universities across more than 60 countries | | 5 | AI Expert Roadmap | Roadmap to becoming an Artificial Intelligence Expert in 2022 | | 6 | Computer Science courses |List of Computer Science courses with video lectures| | 7 | Machine Learning with Python | Machine Learning with Python Certification on freeCodeCamp| | 8 | Building Systems with the ChatGPT API | This short course taught by Isa Fulford (OpenAI) and Andrew Ng (DeepLearning.AI), you will learn how to automate complex workflows using chain calls to a large language model| | 9 | LangChain for LLM Application Development | This short course taught by Harrison Chase (Co-Founder and CEO at LangChain) and Andrew Ng. you will gain essential skills in expanding the use cases and capabilities of language models in application development using the LangChain framework| | 10 | How Diffusion Models Work | This short course taught by Sharon Zhou (CEO, Co-founder, Lamini). you will gain a deep familiarity with the diffusion process and the models which carry it out. More than simply pulling in a pre-built model or using an API, this course will teach you to build a diffusion model from scratch| | 11 | Free Programming Books For AI |📚 Freely available programming books for AI | | 12 | microsoft/AI-For-Beginners |12 Weeks, 24 Lessons, AI for All!| | 13 | hemansnation/God-Level-Data-Science-ML-Full-Stack |A collection of scientific methods, processes, algorithms, and systems to build stories & models. This roadmap contains 16 Chapters, whether you are a fresher in the field or an experienced professional who wants to transition into Data Science & AI| | 14 | datawhalechina/prompt-engineering-for-developers |Chinese version of Andrew Ng's Big Model Series Courses, including "Prompt Engineering", "Building System", and "LangChain"| | 15 | ossu/computer-science |🎓 Path to a free self-taught education in Computer Science!| | 16 | microsoft/Data-Science-For-Beginners | 10 Weeks, 20 Lessons, Data Science for All! | |17 |jwasham/coding-interview-university !2023-09-29268215336 |A complete computer science study plan to become a software engineer.| [Back to Top] Thanks If this project has been helpful to you in any way, please give it a ⭐️ by clicking on the star.

#github #aitreasurebox

#github #production-level-deep-learning

0.619

0.8326638433689385

alirezadir•Mar 28, 2025

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

#github #generative-ai-use-cases-jp

0.548

0.27921589729164453

microsoft•Mar 28, 2025

RD-Agent

🖥️ Live Demo | 🎥 Demo Video ▶️YouTube | 📖 Documentation | 📃 Papers Data Science Agent Preview Check out our demo video showcasing the current progress of our Data Science Agent under development: https://github.com/user-attachments/assets/3eccbecb-34a4-4c81-bce4-d3f8862f7305 📰 News | 🗞️ News | 📝 Description | | -- | ------ | | Support LiteLLM Backend | We now fully support LiteLLM as a backend for integration with multiple LLM providers. | | More General Data Science Agent | 🚀Coming soon! | | Kaggle Scenario release | We release Kaggle Agent, try the new features! | | Official WeChat group release | We created a WeChat group, welcome to join! (🗪QR Code) | | Official Discord release | We launch our first chatting channel in Discord (🗪) | | First release | RDAgent is released on GitHub | 🌟 Introduction RDAgent aims to automate the most critical and valuable aspects of the industrial R&D process, and we begin with focusing on the data-driven scenarios to streamline the development of models and data. Methodologically, we have identified a framework with two key components: 'R' for proposing new ideas and 'D' for implementing them. We believe that the automatic evolution of R&D will lead to solutions of significant industrial value. R&D is a very general scenario. The advent of RDAgent can be your 💰 Automatic Quant Factory (🎥Demo Video|▶️YouTube) 🤖 Data Mining Agent: Iteratively proposing data & models (🎥Demo Video 1|▶️YouTube) (🎥Demo Video 2|▶️YouTube) and implementing them by gaining knowledge from data. 🦾 Research Copilot: Auto read research papers (🎥Demo Video|▶️YouTube) / financial reports (🎥Demo Video|▶️YouTube) and implement model structures or building datasets. 🤖 Kaggle Agent: Auto Model Tuning and Feature Engineering([🎥Demo Video Coming Soon...]()) and implementing them to achieve more in competitions. ... You can click the links above to view the demo. We're continuously adding more methods and scenarios to the project to enhance your R&D processes and boost productivity. Additionally, you can take a closer look at the examples in our 🖥️ Live Demo. ⚡ Quick start You can try above demos by running the following command: 🐳 Docker installation. Users must ensure Docker is installed before attempting most scenarios. Please refer to the official 🐳Docker page for installation instructions. Ensure the current user can run Docker commands without using sudo. You can verify this by executing docker run hello-world. 🐍 Create a Conda Environment Create a new conda environment with Python (3.10 and 3.11 are well-tested in our CI): Activate the environment: 🛠️ Install the RDAgent You can directly install the RDAgent package from PyPI: 💊 Health check rdagent provides a health check that currently checks two things. whether the docker installation was successful. whether the default port used by the rdagent ui is occupied. ⚙️ Configuration The demos requires following ability: ChatCompletion json_mode embedding query For example: If you are using the OpenAI API, you have to configure your GPT model in the .env file like this. However, not every API services support these features by default. For example: AZURE OpenAI, you have to configure your GPT model in the .env file like this. We now support LiteLLM as a backend for integration with multiple LLM providers. If you use LiteLLM Backend to use models, you can configure as follows: For more configuration information, please refer to the documentation. 🚀 Run the Application The 🖥️ Live Demo is implemented by the following commands(each item represents one demo, you can select the one you prefer): Run the Automated Quantitative Trading & Iterative Factors Evolution: Qlib self-loop factor proposal and implementation application Run the Automated Quantitative Trading & Iterative Model Evolution: Qlib self-loop model proposal and implementation application Run the Automated Medical Prediction Model Evolution: Medical self-loop model proposal and implementation application (1) Apply for an account at PhysioNet. (2) Request access to FIDDLE preprocessed data: FIDDLE Dataset. (3) Place your username and password in .env. Run the Automated Quantitative Trading & Factors Extraction from Financial Reports: Run the Qlib factor extraction and implementation application based on financial reports Run the Automated Model Research & Development Copilot: model extraction and implementation application Run the Automated Kaggle Model Tuning & Feature Engineering: self-loop model proposal and feature engineering implementation application Using sf-crime (San Francisco Crime Classification) as an example. Register and login on the Kaggle website. Configuring the Kaggle API. (1) Click on the avatar (usually in the top right corner of the page) -> Settings -> Create New Token, A file called kaggle.json will be downloaded. (2) Move kaggle.json to ~/.config/kaggle/ (3) Modify the permissions of the kaggle.json file. Reference command: chmod 600 ~/.config/kaggle/kaggle.json Join the competition: Click Join the competition -> I Understand and Accept at the bottom of the competition details page. Description of the above example: Kaggle competition data, contains two parts: competition description file (json file) and competition dataset (zip file). We prepare the competition description file for you, the competition dataset will be downloaded automatically when you run the program, as in the example. If you want to download the competition description file automatically, you need to install chromedriver, The instructions for installing chromedriver can be found in the documentation. The Competition List Available can be found here. 🖥️ Monitor the Application Results You can run the following command for our demo program to see the run logs. Note: Although port 19899 is not commonly used, but before you run this demo, you need to check if port 19899 is occupied. If it is, please change it to another port that is not occupied. You can check if a port is occupied by running the following command. 🏭 Scenarios We have applied RD-Agent to multiple valuable data-driven industrial scenarios. 🎯 Goal: Agent for Data-driven R&D In this project, we are aiming to build an Agent to automate Data-Driven R\&D that can 📄 Read real-world material (reports, papers, etc.) and extract key formulas, descriptions of interested features and models, which are the key components of data-driven R&D . 🛠️ Implement the extracted formulas (e.g., features, factors, and models) in runnable codes. Due to the limited ability of LLM in implementing at once, build an evolving process for the agent to improve performance by learning from feedback and knowledge. 💡 Propose new ideas based on current knowledge and observations. 📈 Scenarios/Demos In the two key areas of data-driven scenarios, model implementation and data building, our system aims to serve two main roles: 🦾Copilot and 🤖Agent. The 🦾Copilot follows human instructions to automate repetitive tasks. The 🤖Agent, being more autonomous, actively proposes ideas for better results in the future. The supported scenarios are listed below: | Scenario/Target | Model Implementation | Data Building | | -- | -- | -- | | 💹 Finance | 🤖 Iteratively Proposing Ideas & Evolving▶️YouTube | 🤖 Iteratively Proposing Ideas & Evolving ▶️YouTube 🦾 Auto reports reading & implementation▶️YouTube | | 🩺 Medical | 🤖 Iteratively Proposing Ideas & Evolving▶️YouTube | - | | 🏭 General | 🦾 Auto paper reading & implementation▶️YouTube 🤖 Auto Kaggle Model Tuning | 🤖Auto Kaggle feature Engineering | RoadMap: Currently, we are working hard to add new features to the Kaggle scenario. Different scenarios vary in entrance and configuration. Please check the detailed setup tutorial in the scenarios documents. Here is a gallery of successful explorations (5 traces showed in 🖥️ Live Demo). You can download and view the execution trace using this command from the documentation. Please refer to 📖readthedocs_scen for more details of the scenarios. ⚙️ Framework Automating the R&D process in data science is a highly valuable yet underexplored area in industry. We propose a framework to push the boundaries of this important research field. The research questions within this framework can be divided into three main categories: | Research Area | Paper/Work List | |--------------------|-----------------| | Benchmark the R&D abilities | Benchmark | | Idea proposal: Explore new ideas or refine existing ones | Research | | Ability to realize ideas: Implement and execute ideas | Development | We believe that the key to delivering high-quality solutions lies in the ability to evolve R&D capabilities. Agents should learn like human experts, continuously improving their R&D skills. More documents can be found in the 📖 readthedocs. 📃 Paper/Work list 📊 Benchmark Towards Data-Centric Automatic R&D !image 🔍 Research In a data mining expert's daily research and development process, they propose a hypothesis (e.g., a model structure like RNN can capture patterns in time-series data), design experiments (e.g., finance data contains time-series and we can verify the hypothesis in this scenario), implement the experiment as code (e.g., Pytorch model structure), and then execute the code to get feedback (e.g., metrics, loss curve, etc.). The experts learn from the feedback and improve in the next iteration. Based on the principles above, we have established a basic method framework that continuously proposes hypotheses, verifies them, and gets feedback from the real-world practice. This is the first scientific research automation framework that supports linking with real-world verification. For more detail, please refer to our 🖥️ Live Demo page. 🛠️ Development Collaborative Evolving Strategy for Automatic Data-Centric Development !image 🤝 Contributing We welcome contributions and suggestions to improve RD-Agent. Please refer to the Contributing Guide for more details on how to contribute. Before submitting a pull request, ensure that your code passes the automatic CI checks. 📝 Guidelines This project welcomes contributions and suggestions. Contributing to this project is straightforward and rewarding. Whether it's solving an issue, addressing a bug, enhancing documentation, or even correcting a typo, every contribution is valuable and helps improve RDAgent. To get started, you can explore the issues list, or search for TODO: comments in the codebase by running the command grep -r "TODO:". Before we released RD-Agent as an open-source project on GitHub, it was an internal project within our group. Unfortunately, the internal commit history was not preserved when we removed some confidential code. As a result, some contributions from our group members, including Haotian Chen, Wenjun Feng, Haoxue Wang, Zeqi Ye, Xinjie Shen, and Jinhui Li, were not included in the public commits. ⚖️ Legal disclaimer The RD-agent is provided “as is”, without warranty of any kind, express or implied, including but not limited to the warranties of merchantability, fitness for a particular purpose and noninfringement. The RD-agent is aimed to facilitate research and development process in the financial industry and not ready-to-use for any financial investment or advice. Users shall independently assess and test the risks of the RD-agent in a specific use scenario, ensure the responsible use of AI technology, including but not limited to developing and integrating risk mitigation measures, and comply with all applicable laws and regulations in all applicable jurisdictions. The RD-agent does not provide financial opinions or reflect the opinions of Microsoft, nor is it designed to replace the role of qualified financial professionals in formulating, assessing, and approving finance products. The inputs and outputs of the RD-agent belong to the users and users shall assume all liability under any theory of liability, whether in contract, torts, regulatory, negligence, products liability, or otherwise, associated with use of the RD-agent and any inputs and outputs thereof.

aws-samples•Mar 28, 2025

generative-ai-use-cases-jp

Generative AI Use Cases JP (略称:GenU) 生成 AI を安全に業務活用するための、ビジネスユースケース集を備えたアプリケーション実装 [!IMPORTANT] GenU は 2025/01 に v3 にアップグレードされました。いくつかの破壊的変更を伴いますので、アップグレード前にリリースノートをご確認ください。 GenU 活用パターン集 GenU の機能やオプションを活用パターンごとに紹介いたします。網羅的なデプロイオプションに関してはこちらをご参照ください。 [!TIP] 活用パターンをクリックして詳細を確認してください生成 AI のユースケースを体験したい GenU は生成 AI を活用した多様なユースケースを標準で提供しています。それらのユースケースは、生成 AI を業務活用するためのアイデアの種となったり、そのまま業務で活用できるものなど、さまざまです。今後もさらにブラッシュアップされたユースケースを随時追加予定です。また、不要であれば特定のユースケースを非表示にするオプションで非表示にすることもできます。デフォルトで提供しているユースケース一覧はこちらです。ユースケース説明チャット大規模言語モデル (LLM) とチャット形式で対話することができます。LLM と直接対話するプラットフォームが存在するおかげで、細かいユースケースや新しいユースケースに迅速に対応することができます。また、プロンプトエンジニアリングの検証用環境としても有効です。文章生成あらゆるコンテキストで文章を生成することは LLM が最も得意とするタスクの 1 つです。記事・レポート・メールなど、あらゆる文章を生成します。要約 LLM は、大量の文章を要約するタスクを得意としています。ただ要約するだけでなく、文章をコンテキストとして与えた上で、必要な情報を対話形式で引き出すこともできます。例えば、契約書を読み込ませて「XXX の条件は？」「YYY の金額は？」といった情報を取得することが可能です。執筆 LLM は、誤字脱字のチェックだけでなく、文章の流れや内容を考慮したより客観的な視点から改善点を提案できます。人に見せる前に LLM に自分では気づかなかった点を客観的にチェックしてもらいクオリティを上げる効果が期待できます。翻訳多言語で学習した LLM は、翻訳を行うことも可能です。また、ただ翻訳するだけではなく、カジュアルさ・対象層など様々な指定されたコンテキスト情報を翻訳に反映させることが可能です。 Web コンテンツ抽出ブログやドキュメントなどの Web コンテンツから必要な情報を抽出します。LLMによって不要な情報を除去し、整った文章として整形します。抽出したコンテンツは要約、翻訳などの別のユースケースで利用できます。画像生成画像生成 AI は、テキストや画像を元に新しい画像を生成できます。アイデアを即座に可視化することができ、デザイン作業などの効率化を期待できます。こちらの機能では、プロンプトの作成を LLM に支援してもらうことができます。動画生成動画生成 AI はテキストから短い動画を生成します。生成した動画は素材としてさまざまなシーンで活用できます。映像分析マルチモーダルモデルによってテキストのみではなく、画像を入力することが可能になりました。こちらの機能では、映像の画像フレームとテキストを入力として LLM に分析を依頼します。ダイアグラム生成ダイアグラム生成は、あらゆるトピックに関する文章や内容を最適な図を用いて視覚化します。テキストベースで簡単に図を生成でき、プログラマーやデザイナーでなくても効率的にフローチャートなどの図を作成できます。 RAG がしたい RAG は LLM が苦手な最新の情報やドメイン知識を外部から伝えることで、本来なら回答できない内容にも答えられるようにする手法です。社内に蓄積された PDF, Word, Excel などのファイルが情報ソースになります。 RAG は根拠に基づいた回答のみを許すため、LLM にありがちな「それっぽい間違った情報」を回答させないという効果もあります。 GenU は RAG チャットというユースケースを提供しています。また RAG チャットの情報ソースとして Amazon Kendra と Knowledge Base の 2 種類が利用可能です。 Amazon Kendra を利用する場合は、手動で作成した S3 Bucket や Kendra Index をそのまま利用することが可能です。 Knowledge Base を利用する場合は、Advanced Parsing・チャンク戦略の選択・クエリ分解・リランキングなど高度な RAG が利用可能です。また Knowledge Base では、メタデータフィルターの設定も可能です。例えば「組織ごとにアクセス可能なデータソースを切り替えたい」や「UI からユーザーがフィルタを設定したい」といった要件を満たすことが可能です。独自に作成した AI エージェントや Bedrock Flows などを社内で利用したい GenU でエージェントを有効化すると Web 検索エージェントと Code Interpreter エージェントが作成されます。 Web 検索エージェントは、ユーザーの質問に回答するための情報を Web で検索し、回答します。例えば「AWS の GenU ってなに？」という質問に回答できます。 Code Interpreter エージェントは、ユーザーからのリクエストに応えるためにコードが実行できます。例えば「適当なダミーデータで散布図を描いて」といったリクエストに応えられます。 Web 検索エージェントと Code Interpreter エージェントはエージェントとしては基本的なものですので、中にはもっと業務に寄り添った実践的なエージェントを使いたいという要望もあると思います。 GenU では手動で作成したエージェントや別のアセットで作成したエージェントをインポートする機能を提供しております。 GenU をエージェント活用のプラットフォームとして利用することで、GenU が提供する豊富なセキュリティオプションや SAML認証などを活用し、実践的なエージェントを社内に普及させることができます。また、オプションで不要な標準ユースケースを非表示にしたり、エージェントをインライン表示することで、よりエージェントに特化したプラットフォームとして GenU をご利用いただくことが可能です。 Bedrock Flows に関しても同様にインポート機能がございますので、ぜひご活用ください。独自のユースケースを作成したい GenU はプロンプトテンプレートを自然言語で記述することで独自のユースケースを作成できる「ユースケースビルダー」という機能を提供しています。プロンプトテンプレートだけで独自のユースケース画面が自動生成されるため、GenU 本体のコード変更は一切不要です。作成したユースケースは、個人利用だけではなく、アプリケーションにログインできる全ユーザーに共有することもできます。ユースケースビルダーは不要であれば無効化することも可能です。ユースケースビルダーについての詳細は、ぜひこちらのブログをご覧ください。ユースケースビルダーではフォームにテキストを入力したりファイルを添付するユースケースが作成できますが、要件によってはチャットの UI が良い場合もあると思います。そのようなケースでは「チャット」ユースケースのシステムプロンプト保存機能をご活用ください。システムプロンプトを保存しておくことで、ワンクリックで業務に必要な "ボット" が作成できます。例えば「ソースコードを入力するとひたすらレビューしてくれるボット」や「入力した内容からひたすらメールアドレスを抽出してくれるボット」などが作成できます。また、チャットの会話履歴はログインユーザーにシェアすることが可能で、シェアされた会話履歴からシステムプロンプトをインポートすることもできます。 GenU は OSS ですので、カスタマイズして独自のユースケースを追加するということも可能です。その場合は GenU の main ブランチとのコンフリクトにお気をつけてください。デプロイ [!IMPORTANT] /packages/cdk/cdk.json に記載されている modelRegion リージョンの modelIds (テキスト生成) 及び imageGenerationModelIds (画像生成) を有効化してください。(Amazon Bedrock の Model access 画面) GenU のデプロイには AWS Cloud Development Kit（以降 CDK）を利用します。CDK の実行環境が用意できない場合は、以下のデプロイ方法を参照してください。 AWS CloudShell を利用したデプロイ方法 (手元の環境を用意することが難しい場合) Workshop まず、以下のコマンドを実行してください。全てのコマンドはリポジトリのルートで実行してください。 CDK を利用したことがない場合、初回のみ Bootstrap 作業が必要です。すでに Bootstrap された環境では以下のコマンドは不要です。続いて、以下のコマンドで AWS リソースをデプロイします。デプロイが完了するまで、お待ちください（20 分程度かかる場合があります）。アーキテクチャ !arch.drawio.png その他デプロイオプションアップデート方法ローカル開発環境構築手順リソースの削除方法ネイティブアプリのように利用する方法ブラウザ拡張機能を利用する料金試算 GenU をご利用いただく際の、構成と料金試算例を公開しております。(従量課金制となっており、実際の料金はご利用内容により変動いたします。) シンプル版 (RAG なし) 試算 RAG (Amazon Kendra) あり試算 RAG (Knowledge Base) あり試算お客様事例 | Customer | Quote | |:--------|:---------| | | 株式会社やさしい手 GenU のおかげで、利用者への付加価値提供と従業員の業務効率向上が実現できました。従業員にとって「いままでの仕事」が楽しい仕事に変化していく「サクサクからワクワクへ」更に進化を続けます！・事例の詳細を見る・事例のページを見る| | | タキヒヨー株式会社生成 AI を活用し社内業務効率化と 450 時間超の工数削減を実現。Amazon Bedrock を衣服デザイン等に適用、デジタル人材育成を推進。・事例のページを見る| | | 株式会社サルソニードソリューションとして用意されている GenU を活用することで、生成 AI による業務プロセスの改善に素早く取り掛かることができました。・事例の詳細を見る・適用サービス| | | 株式会社タムラ製作所 AWS が Github に公開しているアプリケーションサンプルは即テスト可能な機能が豊富で、そのまま利用することで自分たちにあった機能の選定が難なくでき、最終システムの開発時間を短縮することができました。・事例の詳細を見る | | | 株式会社JDSC Amazon Bedrock ではセキュアにデータを用い LLM が活用できます。また、用途により最適なモデルを切り替えて利用できるので、コストを抑えながら速度・精度を高めることができました。・事例の詳細を見る | | | アイレット株式会社株式会社バンダイナムコアミューズメントの生成 AI 活用に向けて社内のナレッジを蓄積・体系化すべく、AWS が提供している Generative AI Use Cases JP を活用したユースケースサイトを開発。アイレット株式会社が本プロジェクトの設計・構築・開発を支援。・株式会社バンダイナムコアミューズメント様のクラウドを活用した導入事例 | | | 株式会社アイデアログ M従来の生成 AI ツールよりもさらに業務効率化ができていると感じます。入出力データをモデルの学習に使わない Amazon Bedrock を使っているので、セキュリティ面も安心です。・事例の詳細を見る・適用サービス| | | 株式会社エスタイル GenU を活用して短期間で生成 AI 環境を構築し、社内のナレッジシェアを促進することができました。・事例の詳細を見る | | | 株式会社明電舎 Amazon Bedrock や Amazon Kendra など AWS のサービスを利用することで、生成 AI の利用環境を迅速かつセキュアに構築することができました。議事録の自動生成や社内情報の検索など、従業員の業務効率化に貢献しています。・事例の詳細を見る | | | 三協立山株式会社社内に埋もれていた情報が Amazon Kendra の活用で素早く探せるようになりました。GenU を参考にすることで求めていた議事録生成などの機能を迅速に提供できました。・事例の詳細を見る | | | オイシックス・ラ・大地株式会社 GenU を活用したユースケースの開発プロジェクトを通して、必要なリソース、プロジェクト体制、外部からの支援、人材育成などを把握するきっかけとなり、生成 AI の社内展開に向けたイメージを明確につかむことができました。・事例のページを見る | | | 株式会社サンエー Amazon Bedrock を活用することでエンジニアの生産性が劇的に向上し、内製で構築してきた当社特有の環境のクラウドへの移行を加速できました。・事例の詳細を見る・事例のページを見る | 活用事例を掲載させて頂ける場合は、Issueよりご連絡ください。参照ブログ: 生成 AI アプリをノーコードで作成・社内配布できる GenU ユースケースビルダーブログ: RAG プロジェクトを成功させる方法 #1 ~ あるいは早く失敗しておく方法 ~ ブログ: RAG チャットで精度向上のためのデバッグ方法ブログ: Amazon Q Developer CLI を利用してノーコーディングで GenU をカスタマイズブログ: Generative AI Use Cases JP をカスタマイズする方法ブログ: 無茶振りは生成 AI に断ってもらおう ~ ブラウザに生成 AI を組み込んでみた ~ ブログ: Amazon Bedrock で Interpreter を開発! 動画: 生成 AI ユースケースを考え倒すための Generative AI Use Cases JP (GenU) の魅力と使い方 Security See CONTRIBUTING for more information. License This library is licensed under the MIT-0 License. See the LICENSE file.

0.527

0.11594284776995417

robocorp•Mar 28, 2025

rpaframework

RPA Framework ============= REQUEST for user input! We are looking at improving our keyword usage to cover situations where developer might be struggling to smoothly write task for a Robot. Describe the situation where your implementation speed slows due to the lack of easier syntax. Comment HERE _ .. contents:: Table of Contents :local: :depth: 1 .. include-docs-readme Introduction RPA Framework is a collection of open-source libraries and tools for Robotic Process Automation (RPA), and it is designed to be used with both Robot Framework and Python. The goal is to offer well-documented and actively maintained core libraries for Software Robot Developers. Learn more about RPA at Robocorp Documentation_. The project is: 100% Open Source Sponsored by Robocorp_ Optimized for Robocorp Control Room and Developer Tools Accepting external contributions .. _Robot Framework: https://robotframework.org .. _Robot Framework Foundation: https://robotframework.org/foundation/ .. _Python: https://www.python.org/ .. _Robocorp: https://robocorp.com .. _Robocorp Documentation: https://robocorp.com/docs-robot-framework .. _Control Room: https://robocorp.com/docs/control-room .. _Developer Tools: https://robocorp.com/downloads .. _Installing Python Packages: https://robocorp.com/docs/setup/installing-python-package-dependencies Links ^^^^^ Homepage: `_ Documentation: _ PyPI: _ Release notes: _ RSS feed: _ .. image:: https://img.shields.io/github/actions/workflow/status/robocorp/rpaframework/main.yaml?style=for-the-badge :target: https://github.com/robocorp/rpaframework/actions/workflows/main.yaml :alt: Status .. image:: https://img.shields.io/pypi/dw/rpaframework?style=for-the-badge :target: https://pypi.python.org/pypi/rpaframework :alt: rpaframework .. image:: https://img.shields.io/pypi/l/rpaframework.svg?style=for-the-badge&color=brightgreen :target: http://www.apache.org/licenses/LICENSE-2.0.html :alt: License Packages .. image:: https://img.shields.io/pypi/v/rpaframework.svg?label=rpaframework&style=for-the-badge :target: https://pypi.python.org/pypi/rpaframework :alt: rpaframework latest version .. image:: https://img.shields.io/pypi/v/rpaframework-assistant.svg?label=rpaframework-assistant&style=for-the-badge :target: https://pypi.python.org/pypi/rpaframework-assistant :alt: rpaframework-assistant latest version .. image:: https://img.shields.io/pypi/v/rpaframework-aws.svg?label=rpaframework-aws&style=for-the-badge :target: https://pypi.python.org/pypi/rpaframework-aws :alt: rpaframework-aws latest version .. image:: https://img.shields.io/pypi/v/rpaframework-core.svg?label=rpaframework-core&style=for-the-badge :target: https://pypi.python.org/pypi/rpaframework-core :alt: rpaframework-core latest version .. image:: https://img.shields.io/pypi/v/rpaframework-google.svg?label=rpaframework-google&style=for-the-badge&color=blue :target: https://pypi.python.org/pypi/rpaframework-google :alt: rpaframework-google latest version .. image:: https://img.shields.io/pypi/v/rpaframework-hubspot.svg?label=rpaframework-hubspot&style=for-the-badge&color=blue :target: https://pypi.python.org/pypi/rpaframework-hubspot :alt: rpaframework-hubspot latest version .. image:: https://img.shields.io/pypi/v/rpaframework-openai.svg?label=rpaframework-openai&style=for-the-badge&color=blue :target: https://pypi.python.org/pypi/rpaframework-openai :alt: rpaframework-openai latest version .. image:: https://img.shields.io/pypi/v/rpaframework-pdf.svg?label=rpaframework-pdf&style=for-the-badge&color=blue :target: https://pypi.python.org/pypi/rpaframework-pdf :alt: rpaframework-pdf latest version .. image:: https://img.shields.io/pypi/v/rpaframework-recognition.svg?label=rpaframework-recognition&style=for-the-badge&color=blue :target: https://pypi.python.org/pypi/rpaframework-recognition :alt: rpaframework-recognition latest version .. image:: https://img.shields.io/pypi/v/rpaframework-windows.svg?label=rpaframework-windows&style=for-the-badge&color=blue :target: https://pypi.python.org/pypi/rpaframework-windows :alt: rpaframework-windows latest version From the above packages, rpaframework-core and rpaframework-recognition are support packages, which alone do not contain any libraries. Libraries The RPA Framework project currently includes the following libraries: The x in the PACKAGE column means that library is included in the rpaframework package and for example. x,pdf means that RPA.PDF library is provided in both the rpaframework and rpaframework-pdf packages. +----------------------------+-------------------------------------------------------+------------------------+ | LIBRARY NAME | DESCRIPTION | PACKAGE | +----------------------------+-------------------------------------------------------+------------------------+ | Archive_ | Archiving TAR and ZIP files | x | +----------------------------+-------------------------------------------------------+------------------------+ | Assistant_ | Display information to a user and request input. | assistant | +----------------------------+-------------------------------------------------------+------------------------+ | Browser.Selenium_ | Control browsers and automate the web | x | +----------------------------+-------------------------------------------------------+------------------------+ | Browser.Playwright_ | Newer way to control browsers | special (more below) | +----------------------------+-------------------------------------------------------+------------------------+ | Calendar_ | For date and time manipulations | x | +----------------------------+-------------------------------------------------------+------------------------+ | Cloud.AWS_ | Use Amazon AWS services | x,aws | +----------------------------+-------------------------------------------------------+------------------------+ | Cloud.Azure_ | Use Microsoft Azure services | x | +----------------------------+-------------------------------------------------------+------------------------+ | Cloud.Google_ | Use Google Cloud services | google | +----------------------------+-------------------------------------------------------+------------------------+ | Crypto_ | Common hashing and encryption operations | x | +----------------------------+-------------------------------------------------------+------------------------+ | Database_ | Interact with databases | x | +----------------------------+-------------------------------------------------------+------------------------+ | Desktop_ | Cross-platform desktop automation | x | +----------------------------+-------------------------------------------------------+------------------------+ | Desktop.Clipboard_ | Interact with the system clipboard | x | +----------------------------+-------------------------------------------------------+------------------------+ | Desktop.OperatingSystem_ | Read OS information and manipulate processes | x | +----------------------------+-------------------------------------------------------+------------------------+ | DocumentAI_ | Intelligent Document Processing wrapper | x | +----------------------------+-------------------------------------------------------+------------------------+ | DocumentAI.Base64AI_ | Intelligent Document Processing service | x | +----------------------------+-------------------------------------------------------+------------------------+ | DocumentAI.Nanonets_ | Intelligent Document Processing service | x | +----------------------------+-------------------------------------------------------+------------------------+ | Email.Exchange_ | E-Mail operations (Exchange protocol) | x | +----------------------------+-------------------------------------------------------+------------------------+ | Email.ImapSmtp_ | E-Mail operations (IMAP & SMTP) | x | +----------------------------+-------------------------------------------------------+------------------------+ | Excel.Application_ | Control the Excel desktop application | x | +----------------------------+-------------------------------------------------------+------------------------+ | Excel.Files_ | Manipulate Excel files directly | x | +----------------------------+-------------------------------------------------------+------------------------+ | FileSystem_ | Read and manipulate files and paths | x | +----------------------------+-------------------------------------------------------+------------------------+ | FTP_ | Interact with FTP servers | x | +----------------------------+-------------------------------------------------------+------------------------+ | HTTP_ | Interact directly with web APIs | x | +----------------------------+-------------------------------------------------------+------------------------+ | Hubspot_ | Access HubSpot CRM data objects | hubspot | +----------------------------+-------------------------------------------------------+------------------------+ | Images_ | Manipulate images | x | +----------------------------+-------------------------------------------------------+------------------------+ | JavaAccessBridge_ | Control Java applications | x | +----------------------------+-------------------------------------------------------+------------------------+ | JSON_ | Manipulate JSON objects | x | +----------------------------+-------------------------------------------------------+------------------------+ | MFA_ | Authenticate using one-time passwords (OTP) & OAuth2 | x | +----------------------------+-------------------------------------------------------+------------------------+ | Notifier_ | Notify messages using different services | x | +----------------------------+-------------------------------------------------------+------------------------+ | OpenAI_ | Artificial Intelligence service | openai | +----------------------------+-------------------------------------------------------+------------------------+ | Outlook.Application_ | Control the Outlook desktop application | x | +----------------------------+-------------------------------------------------------+------------------------+ | PDF_ | Read and create PDF documents | x,pdf | +----------------------------+-------------------------------------------------------+------------------------+ | Robocorp.Process_ | Use the Robocorp Process API | x | +----------------------------+-------------------------------------------------------+------------------------+ | Robocorp.WorkItems_ | Use the Robocorp Work Items API | x | +----------------------------+-------------------------------------------------------+------------------------+ | Robocorp.Vault_ | Use the Robocorp Secrets API | x | +----------------------------+-------------------------------------------------------+------------------------+ | Robocorp.Storage_ | Use the Robocorp Asset Storage API | x | +----------------------------+-------------------------------------------------------+------------------------+ | Salesforce_ | Salesforce operations | x | +----------------------------+-------------------------------------------------------+------------------------+ | SAP_ | Control SAP GUI desktop client | x | +----------------------------+-------------------------------------------------------+------------------------+ | Smartsheet_ | Access Smartsheet sheets | x | +----------------------------+-------------------------------------------------------+------------------------+ | Tables_ | Manipulate, sort, and filter tabular data | x | +----------------------------+-------------------------------------------------------+------------------------+ | Tasks_ | Control task execution | x | +----------------------------+-------------------------------------------------------+------------------------+ | Twitter_ | Twitter API interface | x | +----------------------------+-------------------------------------------------------+------------------------+ | Windows_ | Alternative library for Windows automation | x,windows | +----------------------------+-------------------------------------------------------+------------------------+ | Word.Application_ | Control the Word desktop application | x | +----------------------------+-------------------------------------------------------+------------------------+ .. _Archive: https://rpaframework.org/libraries/archive/ .. _Assistant: https://rpaframework.org/libraries/assistant/ .. Browser.Playwright: https://rpaframework.org/libraries/browserplaywright/ .. Browser.Selenium: https://rpaframework.org/libraries/browserselenium/ .. _Calendar: https://rpaframework.org/libraries/calendar/ .. Cloud.AWS: https://rpaframework.org/libraries/cloudaws/ .. Cloud.Azure: https://rpaframework.org/libraries/cloudazure/ .. Cloud.Google: https://rpaframework.org/libraries/cloudgoogle/ .. _Crypto: https://rpaframework.org/libraries/crypto/ .. _Database: https://rpaframework.org/libraries/database/ .. _Desktop: https://rpaframework.org/libraries/desktop/ .. Desktop.Clipboard: https://rpaframework.org/libraries/desktopclipboard/ .. Desktop.Operatingsystem: https://rpaframework.org/libraries/desktopoperatingsystem/ .. _DocumentAI: https://rpaframework.org/libraries/documentai .. DocumentAI.Base64AI: https://rpaframework.org/libraries/documentaibase64ai/ .. DocumentAI.Nanonets: https://rpaframework.org/libraries/documentainanonets/ .. Email.Exchange: https://rpaframework.org/libraries/emailexchange/ .. Email.ImapSmtp: https://rpaframework.org/libraries/emailimapsmtp/ .. Excel.Application: https://rpaframework.org/libraries/excelapplication/ .. Excel.Files: https://rpaframework.org/libraries/excelfiles/ .. _FileSystem: https://rpaframework.org/libraries/filesystem/ .. _FTP: https://rpaframework.org/libraries/ftp/ .. _HTTP: https://rpaframework.org/libraries/http/ .. _Hubspot: https://rpaframework.org/libraries/hubspot/ .. _Images: https://rpaframework.org/libraries/images/ .. _JavaAccessBridge: https://rpaframework.org/libraries/javaaccessbridge/ .. _JSON: https://rpaframework.org/libraries/json/ .. _MFA: https://rpaframework.org/libraries/mfa/ .. _Notifier: https://rpaframework.org/libraries/notifier/ .. _OpenAI: https://rpaframework.org/libraries/openai/ .. Outlook.Application: https://rpaframework.org/libraries/outlookapplication/ .. _PDF: https://rpaframework.org/libraries/pdf/ .. Robocorp.Process: https://rpaframework.org/libraries/robocorpprocess/ .. Robocorp.WorkItems: https://rpaframework.org/libraries/robocorpworkitems/ .. Robocorp.Vault: https://rpaframework.org/libraries/robocorpvault/ .. Robocorp.Storage: https://rpaframework.org/libraries/robocorpstorage/ .. _Salesforce: https://rpaframework.org/libraries/salesforce/ .. _SAP: https://rpaframework.org/libraries/sap/ .. _Smartsheet: https://rpaframework.org/libraries/smartsheet/ .. _Tables: https://rpaframework.org/libraries/tables/ .. _Tasks: https://rpaframework.org/libraries/tasks/ .. _Twitter: https://rpaframework.org/libraries/twitter/ .. _Windows: https://rpaframework.org/libraries/windows/ .. Word.Application: https://rpaframework.org/libraries/wordapplication/ Installation of RPA.Browser.Playwright The RPA.Browser.Playwright at the moment requires special installation, because of the package size and the post install step it needs to be fully installed. Minimum required conda.yaml to install Playwright: .. code-block:: yaml channels: conda-forge dependencies: python=3.10.14 nodejs=22.9.0 pip=24.0 pip: robotframework-browser==18.8.1 rpaframework==28.6.3 rccPostInstall: rfbrowser init Installation Learn about installing Python packages at Installing Python Packages_. Default installation method with Robocorp Developer Tools_ using conda.yaml: .. code-block:: yaml channels: conda-forge dependencies: python=3.10.14 pip=24.0 pip: rpaframework==28.6.3 To install all extra packages (including Playwright dependencies), you can use: .. code-block:: yaml channels: conda-forge dependencies: python=3.10.14 tesseract=5.4.1 nodejs=22.9.0 pip=24.0 pip: robotframework-browser==18.8.1 rpaframework==28.6.3 rpaframework-aws==5.3.3 rpaframework-google==9.0.2 rpaframework-recognition==5.2.5 rccPostInstall: rfbrowser init Separate installation of AWS, PDF and Windows libraries without the main rpaframework: .. code-block:: yaml channels: conda-forge dependencies: python=3.10.14 pip=24.0 pip: rpaframework-aws==5.3.3 included in the rpaframework as an extra rpaframework-pdf==7.3.3 included in the rpaframework by default rpaframework-windows==7.5.2 included in the rpaframework by default Installation method with pip using Python venv_: .. code-block:: shell python -m venv .venv source .venv/bin/activate pip install rpaframework .. note:: Python 3.8 or higher is required Example After installation the libraries can be directly imported inside Robot Framework_: .. code:: robotframework Settings Library RPA.Browser.Selenium Tasks Login as user Open available browser https://example.com Input text id:user-name ${USERNAME} Input text id:password ${PASSWORD} The libraries are also available inside Python_: .. code:: python from RPA.Browser.Selenium import Selenium lib = Selenium() lib.openavailablebrowser("https://example.com") lib.input_text("id:user-name", username) lib.input_text("id:password", password) Support and contact rpaframework.org _ for library documentation Robocorp Documentation_ for guides and tutorials #rpaframework channel in Robot Framework Slack_ if you have open questions or want to contribute Communicate with your fellow Software Robot Developers and Robocorp experts at Robocorp Developers Slack_ .. _Robot Framework Slack: https://robotframework-slack-invite.herokuapp.com/ .. _Robocorp Developers Slack: https://robocorp-developers.slack.com Contributing Found a bug? Missing a critical feature? Interested in contributing? Head over to the Contribution guide _ to see where to get started. Development Repository development is Python_ based and requires at minimum Python version 3.8+ installed on the development machine. The default Python version used in the Robocorp Robot template is 3.10.14 so it is a good choice for the version to install. Not recommended versions are 3.7.6 and 3.8.1, because they have issues with some of the dependencies related to rpaframework. At the time the newer Python versions starting from 3.12 are also not recommended, because some of the dependencies might cause issues. Repository development tooling is based on poetry and invoke. Poetry is the underlying tool used for compiling, building and running the package. Invoke is used for scripting purposes, for example for linting, testing and publishing tasks. Before writing any code, please read and acknowledge our extensive Dev Guide_. .. _Dev Guide: https://github.com/robocorp/rpaframework/blob/master/docs/source/contributing/development.md First steps to start developing: initial poetry configuration .. code:: shell poetry config virtualenvs.path null poetry config virtualenvs.in-project true poetry config repositories.devpi "https://devpi.robocorp.cloud/ci/test" git clone the repository #. create a new Git branch or switch to correct branch or stay in master branch some branch naming conventions feature/name-of-feature, hotfix/name-of-the-issue, release/number-of-release #. poetry install which install package with its dependencies into the .venv directory of the package, for example packages/main/.venv #. if testing against Robocorp Robot which is using devdata/env.json set environment variables or poetry build and use resulting .whl file (in the dist/ directory) in the Robot conda.yaml or poetry build and push resulting .whl file (in the dist/ directory) into a repository and use raw url to include it in the Robot conda.yaml another possibility for Robocorp internal development is to use Robocorp devpi instance, by poetry publish --ci and point conda.yaml to use rpaframework version in devpi #. poetry run python -m robot common ROBOT_ARGS from Robocorp Robot template: --report NONE --outputdir output --logtitle "Task log" #. poetry run python #. invoke lint to make sure that code formatting is according to rpaframework repository guidelines. It is possible and likely that Github action will fail the if developer has not linted the code changes. Code formatting is based on black and flake8 and those are run with the invoke lint. #. the library documentation can be created in the repository root (so called "meta" package level). The documentation is built by the docgen tools using the locally installed version of the project, local changes for the main package will be reflected each time you generate the docs, but if you want to see local changes for optional packages, you must utilize invoke install-local --package using the appropriate package name (e.g., rpaframework-aws). This will reinstall that package as a local editable version instead of from PyPI. Multiple such packages can be added by repeating the use of the --package option. In order to reset this, use invoke install --reset. poetry update and/or invoke install-local --package make docs open docs/build/html/index.html with the browser to view the changes or execute make local and navigate to localhost:8000 to view docs as a live local webpage. .. code-block:: toml Before [tool.poetry.dependencies] python = "^3.8" rpaframework = { path = "packages/main", extras = ["cv", "playwright", "aws"] } rpaframework-google = "^4.0.0" rpaframework-windows = "^4.0.0" After [tool.poetry.dependencies] python = "^3.8" rpaframework = { path = "packages/main", extras = ["cv", "playwright"] } rpaframework-aws = { path = "packages/aws" } rpaframework-google = "^4.0.0" rpaframework-windows = "^4.0.0" #. invoke test (this will run both Python unittests and robotframework tests defined in the packages tests/ directory) to run specific Python test: poetry run pytest path/to/test.py::test_function to run specific Robotframework test: inv testrobot -r -t #. git commit changes #. git push changes to remote #. create pull request from the branch describing changes included in the description #. update docs/source/releasenotes.rst with changes (commit and push) Packaging and publishing are done after changes have been merged into master branch. All the following steps should be done within master branch. #. git pull latest changes into master branch #. in the package directory containing changes execute invoke lint and invoke test #. update pyproject.toml with new version according to semantic versioning #. update docs/source/releasenotes.rst with changes #. in the repository root (so called "meta" package level) run command poetry update #. git commit changed poetry.lock files (on meta and target package level), releasenotes.rst and pyproject.toml with message "PACKAGE. version x.y.z" #. git push #. invoke publish after Github action on master branch is all green Some recommended tools for development Visual Studio Code_ as a code editor with following extensions: Sema4.ai_ Robot Framework Language Server_ GitLens_ Python extension_ GitHub Desktop_ will make version management less prone to errors .. _poetry: https://python-poetry.org .. _invoke: https://www.pyinvoke.org .. _Visual Studio Code: https://code.visualstudio.com .. _GitHub Desktop: https://desktop.github.com .. _Sema4.ai: https://marketplace.visualstudio.com/items?itemName=sema4ai.sema4ai .. _Robot Framework Language Server: https://marketplace.visualstudio.com/items?itemName=robocorp.robotframework-lsp .. _GitLens: https://marketplace.visualstudio.com/items?itemName=eamodio.gitlens .. _Python extension: https://marketplace.visualstudio.com/items?itemName=ms-python.python .. _black: https://pypi.org/project/black/ .. _flake8: https://pypi.org/project/flake8/ .. _venv: https://docs.python.org/3/library/venv.html License This project is open-source and licensed under the terms of the Apache License 2.0 `_.

#github #rpaframework

CrewAI-Studio

CrewAI Studio Welcome to CrewAI Studio! This application provides a user-friendly interface written in Streamlit for interacting with CrewAI, suitable even for those who don't want to write any code. Follow the steps below to install and run the application using Docker/docker-compose or Conda/venv. Features Multi-platform support: Works on Windows, Linux and MacOS. No coding required: User-friendly interface for interacting with CrewAI. Conda and virtual environment support: Choose between Conda and a Python virtual environment for installation. Results history: You can view previous results. Knowledge sources: You can add knowledge sources for your crews CrewAI tools You can use crewai tools to interact with real world. ~~Crewai studio uses a forked version of crewai-tools with some bugfixes and enhancements (https://github.com/strnad/crewAI-tools)~~ (bugfixes already merged to crewai-tools) Custom Tools Custom tools for calling APIs, writing files, enhanced code interpreter, enhanced web scraper... More will be added soon LLM providers supported: Currently OpenAI, Groq, Anthropic, ollama, Grok and LM Studio backends are supported. OpenAI key is probably still needed for embeddings in many tools. Don't forget to load an embedding model when using LM Studio. Single Page app export: Feature to export crew as simple single page streamlit app. Threaded crew run: Crews can run in background and can be stopped. Support CrewAI Studio Your support helps fund the development and growth of our project. Every contribution is greatly appreciated! Donate with Bitcoin Sponsor via GitHub Screenshots Installation Using Virtual Environment For Virtual Environment: Ensure you have Python installed. If you dont have python instaled, you can simply use the conda installer. On Linux or MacOS Clone the repository (or use downloaded ZIP file): Run the installation script: Run the application: On Windows Clone the repository (or use downloaded ZIP file): Run the Conda installation script: Run the application: Using Conda Conda will be installed locally in the project folder. No need for a pre-existing Conda installation. On Linux Clone the repository (or use downloaded ZIP file): Run the Conda installation script: Run the application: On Windows Clone the repository (or use downloaded ZIP file): Run the Conda installation script: Run the application: One-Click Deployment Running with Docker Compose To quickly set up and run CrewAI-Studio using Docker Compose, follow these steps: Prerequisites Ensure Docker and Docker Compose are installed on your system. Steps Clone the repository: Create a .env file for configuration. Edit for your own configuration: Start the application with Docker Compose: Access the application: http://localhost:8501 Configuration Before running the application, ensure you update the .env file with your API keys and other necessary configurations. An example .env file is provided for reference. Troubleshooting In case of problems: Delete the venv/miniconda folder and reinstall crewai-studio. Rename crewai.db (it contains your crews but sometimes new versions can break compatibility). Raise an issue and I will help you. Video tutorial Video tutorial on CrewAI Studio made by Josh Poco Star History

#github #crewai-studio

#github #awesome-ai-in-finance

0.539

0.20972324263626374

beehive-lab•Mar 28, 2025

TornadoVM

TornadoVM !TornadoVM version TornadoVM is a plug-in to OpenJDK and GraalVM that allows programmers to automatically run Java programs on heterogeneous hardware. TornadoVM targets OpenCL, PTX and SPIR-V compatible devices which include multi-core CPUs, dedicated GPUs (Intel, NVIDIA, AMD), integrated GPUs (Intel HD Graphics and ARM Mali), and FPGAs (Intel and Xilinx). TornadoVM has three backends that generate OpenCL C, NVIDIA CUDA PTX assembly, and SPIR-V binary. Developers can choose which backends to install and run. Website: tornadovm.org Documentation: https://tornadovm.readthedocs.io/en/latest/ For a quick introduction please read the following FAQ. Latest Release: TornadoVM 1.0.10 - 31/01/2025 : See CHANGELOG. Installation In Linux and macOS, TornadoVM can be installed automatically with the installation script. For example: NOTE Select the desired backend: opencl: Enables the OpenCL backend (requires OpenCL drivers) ptx: Enables the PTX backend (requires NVIDIA CUDA drivers) spirv: Enables the SPIRV backend (requires Intel Level Zero drivers) Example of installation: Alternatively, TornadoVM can be installed either manually from source or by using Docker. If you are planning to use Docker with TornadoVM on GPUs, you can also follow these guidelines. You can also run TornadoVM on Amazon AWS CPUs, GPUs, and FPGAs following the instructions here. Usage Instructions TornadoVM is currently being used to accelerate machine learning and deep learning applications, computer vision, physics simulations, financial applications, computational photography, and signal processing. Featured use-cases: kfusion-tornadovm: Java application for accelerating a computer-vision application using the Tornado-APIs to run on discrete and integrated GPUs. Java Ray-Tracer: Java application accelerated with TornadoVM for real-time ray-tracing. We also have a set of examples that includes NBody, DFT, KMeans computation and matrix computations. Additional Information General Documentation Benchmarks How TornadoVM executes reductions Execution Flags FPGA execution Profiler Usage Programming Model TornadoVM exposes to the programmer task-level, data-level and pipeline-level parallelism via a light Application Programming Interface (API). In addition, TornadoVM uses single-source property, in which the code to be accelerated and the host code live in the same Java program. Compute-kernels in TornadoVM can be programmed using two different approaches (APIs): a) Loop Parallel API Compute kernels are written in a sequential form (tasks programmed for a single thread execution). To express parallelism, TornadoVM exposes two annotations that can be used in loops and parameters: a) @Parallel for annotating parallel loops; and b) @Reduce for annotating parameters used in reductions. The following code snippet shows a full example to accelerate Matrix-Multiplication using TornadoVM and the loop-parallel API: To run TornadoVM, you need to either install the TornadoVM extension for GraalVM/OpenJDK, or run with our Docker images. Additional Resources Here you can find videos, presentations, tech-articles and artefacts describing TornadoVM, and how to use it. Academic Publications If you are using TornadoVM >= 0.2 (which includes the Dynamic Reconfiguration, the initial FPGA support and CPU/GPU reductions), please use the following citation: If you are using Tornado 0.1 (Initial release), please use the following citation in your work. Selected publications can be found here. Acknowledgments This work is partially funded by Intel corporation. In addition, it has been supported by the following EU & UKRI grants (most recent first): EU Horizon Europe & UKRI AERO 101092850. EU Horizon Europe & UKRI INCODE 101093069. EU Horizon Europe & UKRI ENCRYPT 101070670. EU Horizon Europe & UKRI TANGO 101070052. EU Horizon 2020 ELEGANT 957286. EU Horizon 2020 E2Data 780245. EU Horizon 2020 ACTiCLOUD 732366. Furthermore, TornadoVM has been supported by the following EPSRC grants: PAMELA EP/K008730/1. AnyScale Apps EP/L000725/1. Contributions and Collaborations We welcome collaborations! Please see how to contribute to the project in the CONTRIBUTING page. Write your questions and proposals: Additionally, you can open new proposals on the GitHub discussions page. Alternatively, you can share a Google document with us. Collaborations: For Academic & Industry collaborations, please contact here. TornadoVM Team Visit our website to meet the team. Licenses Per Module To use TornadoVM, you can link the TornadoVM API to your application which is under Apache 2. Each Java TornadoVM module is licensed as follows: | Module | License | |--------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------| | Tornado-API | | | Tornado-Runtime | | | Tornado-Assembly | | | Tornado-Drivers | | | Tornado-Drivers-OpenCL-Headers | | | Tornado-scripts | | | Tornado-Annotation | | | Tornado-Unittests | | | Tornado-Benchmarks | | | Tornado-Examples | | | Tornado-Matrices | | | | |

georgezouq•Mar 28, 2025

awesome-ai-in-finance

Awesome AI in Finance There are millions of trades made in the global financial market every day. Data grows very quickly and people are hard to understand. With the power of the latest artificial intelligence research, people analyze & trade automatically and intelligently. This list contains the research, tools and code that people use to beat the market. [中文资源] Contents LLMs Papers Courses & Books Strategies & Research Time Series Data Portfolio Management High Frequency Trading Event Drive Crypto Currencies Strategies Technical Analysis Lottery & Gamble Arbitrage Data Sources Research Tools Trading System TA Lib Exchange API Articles Others LLMs 🌟🌟 MarS - A Financial Market Simulation Engine Powered by Generative Foundation Model. 🌟🌟 Financial Statement Analysis with Large Language Models - GPT-4 can outperform professional financial analysts in predicting future earnings changes, generating useful narrative insights, and resulting in superior trading strategies with higher Sharpe ratios and alphas, thereby suggesting a potential central role for LLMs in financial decision-making. PIXIU - An open-source resource providing a financial large language model, a dataset with 136K instruction samples, and a comprehensive evaluation benchmark. FinGPT - Provides a playground for all people interested in LLMs and NLP in Finance. MACD + RSI + ADX Strategy (ChatGPT-powered) by TradeSmart - Asked ChatGPT on which indicators are the most popular for trading. We used all of the recommendations given. A ChatGPT trading algorithm delivered 500% returns in stock market. My breakdown on what this means for hedge funds and retail investors Use chatgpt to adjust strategy parameters Hands-on LLMs: Train and Deploy a Real-time Financial Advisor - Train and deploy a real-time financial advisor chatbot with Falcon 7B and CometLLM. ChatGPT Strategy by OctoBot - Use ChatGPT to determine which cryptocurrency to trade based on technical indicators. Papers The Theory of Speculation L. Bachelier, 1900 - The influences which determine the movements of the Stock Exchange are. Brownian Motion in the Stock Market Osborne, 1959 - The common-stock prices can be regarded as an ensemble of decisions in statistical equilibrium. An Investigation into the Use of Reinforcement Learning Techniques within the Algorithmic Trading Domain, 2015 A Deep Reinforcement Learning Framework for the Financial Portfolio Management Problem Reinforcement Learning for Trading, 1994 Dragon-Kings, Black Swans and the Prediction of Crises Didier Sornette - The power laws in the distributions of event sizes under a broad range of conditions in a large variety of systems. Financial Trading as a Game: A Deep Reinforcement Learning Approach - Deep reinforcement learning provides a framework toward end-to-end training of such trading agent. Machine Learning for Trading - With an appropriate choice of the reward function, reinforcement learning techniques can successfully handle the risk-averse case. Ten Financial Applications of Machine Learning, 2018 - Slides review few important financial ML applications. FinRL: A Deep Reinforcement Learning Library for Automated Stock Trading in Quantitative Finance, 2020 - Introduce a DRL library FinRL that facilitates beginners to expose themselves to quantitative finance and to develop their own stock trading strategies. Deep Reinforcement Learning for Automated Stock Trading: An Ensemble Strategy, 2020 - Propose an ensemble strategy that employs deep reinforcement schemes to learn a stock trading strategy by maximizing investment return. Courses & Books & Blogs 🌟 QuantResearch - Quantitative analysis, strategies and backtests https://letianzj.github.io/ NYU: Overview of Advanced Methods of Reinforcement Learning in Finance Udacity: Artificial Intelligence for Trading AI in Finance - Learn Fintech Online. Advanced-Deep-Trading - Experiments based on "Advances in financial machine learning" book. Advances in Financial Machine Learning - Using advanced ML solutions to overcome real-world investment problems. Build Financial Software with Generative AI - Book about how to build financial software hands-on using generative AI tools like ChatGPT and Copilot. Mastering Python for Finance - Sources codes for: Mastering Python for Finance, Second Edition. MLSys-NYU-2022 - Slides, scripts and materials for the Machine Learning in Finance course at NYU Tandon, 2022. Train and Deploy a Serverless API to predict crypto prices - In this tutorial you won't build an ML system that will make you rich. But you will master the MLOps frameworks and tools you need to build ML systems that, together with tons of experimentation, can take you there. Strategies & Research Time Series Data Price and Volume process with Technology Analysis Indices 🌟🌟 stockpredictionai - A complete process for predicting stock price movements. 🌟 Personae - Implements and environment of Deep Reinforcement Learning & Supervised Learning for Quantitative Trading. 🌟 Ensemble-Strategy - Deep Reinforcement Learning for Automated Stock Trading. FinRL - A Deep Reinforcement Learning Library for Automated Stock Trading in Quantitative Finance. AutomatedStockTrading-DeepQ-Learning - Build a Deep Q-learning reinforcement agent model as automated trading robot. tfdeeprltrader - Trading environment(OpenAI Gym) + PPO(TensorForce). trading-gym - Trading agent to train with episode of short term trading itself. trading-rl - Deep Reinforcement Learning for Financial Trading using Price Trailing. deeprltrader - Trading environment(OpenAI Gym) + DDQN (Keras-RL). Quantitative-Trading - Papers and code implementing Quantitative-Trading. gym-trading - Environment for reinforcement-learning algorithmic trading models. zenbrain - A framework for machine-learning bots. DeepLearningNotes - Machine learning in quant analysis. stockmarketreinforcementlearning - Stock market trading OpenAI Gym environment with Deep Reinforcement Learning using Keras. Chaos Genius - ML powered analytics engine for outlier/anomaly detection and root cause analysis.. mlforecast - Scalable machine learning based time series forecasting. Portfolio Management Deep-Reinforcement-Stock-Trading - A light-weight deep reinforcement learning framework for portfolio management. qtrader - Reinforcement Learning for portfolio management. PGPortfolio - A Deep Reinforcement Learning framework for the financial portfolio management problem. DeepDow - Portfolio optimization with deep learning. skfolio - Python library for portfolio optimization built on top of scikit-learn. High Frequency Trading High-Frequency-Trading-Model-with-IB - A high-frequency trading model using Interactive Brokers API with pairs and mean-reversion. 🌟 SGX-Full-OrderBook-Tick-Data-Trading-Strategy - Solutions for high-frequency trading (HFT) strategies using data science approaches (Machine Learning) on Full Orderbook Tick Data. HFTBitcoin - Analysis of High Frequency Trading on Bitcoin exchanges. Event Drive 🌟🌟 stockpredictionai - Complete process for predicting stock price movements. 🌟 trump2cash - A stock trading bot powered by Trump tweets. Crypto Currencies Strategies LSTM-Crypto-Price-Prediction - Predicting price trends in crypto markets using an LSTM-RNN for trading. tforcebtctrader - TensorForce Bitcoin trading bot. Tensorflow-NeuroEvolution-Trading-Bot - A population model that trade cyrpto and breed and mutate iteratively. gekkoga - Genetic algorithm for solving optimization of trading strategies using Gekko. GekkoANNStrategies - ANN trading strategies for the Gekko trading bot. gekko-neuralnet - Neural network strategy for Gekko. bitcoinprediction - Code for "Bitcoin Prediction" by Siraj Raval on YouTube. Technical Analysis quant-trading - Python quantitative trading strategies. Gekko-Bot-Resources - Gekko bot resources. gekkotools - Gekko strategies, tools etc. gekko RSIWR - Gekko RSIWR strategies. gekko HL - Calculate down peak and trade on. EthTradingAlgorithm - Ethereum trading algorithm using Python 3.5 and the library ZipLine. gekkotradingstuff - Awesome crypto currency trading platform. forex.analytics - Node.js native library performing technical analysis over an OHLC dataset with use of genetic algorithmv. BitcoinMACDStrategy - Bitcoin MACD crossover trading strategy backtest. crypto-signal - Automated crypto trading & technical analysis (TA) bot for Bittrex, Binance, GDAX, and more. Gekko-Strategies - Strategies to Gekko trading bot with backtests results and some useful tools. gekko-gannswing - Gann's Swing trade strategy for Gekko trade bot. Lottery & Gamble LotteryPredict - Use LSTM to predict lottery. Arbitrage ArbitrageBot - Arbitrage bot that currently works on bittrex & poloniex. r2 - Automatic arbitrage trading system powered by Node.js + TypeScript. cryptocurrency-arbitrage - A crypto currency arbitrage opportunity calculator. Over 800 currencies and 50 markets. bitcoin-arbitrage - Bitcoin arbitrage opportunity detector. blackbird - Long / short market-neutral strategy. Data Sources Traditional Markets 🌟 Quandl - Get millions of financial and economic dataset from hundreds of publishers via a single free API. yahoo-finance - Python module to get stock data from Yahoo! Finance. Tushare - Crawling historical data of Chinese stocks. Financial Data - Stock Market and Financial Data API. Crypto Currencies CryptoInscriber - A live crypto currency historical trade data blotter. Download live historical trade data from any crypto exchange. Gekko-Datasets - Gekko trading bot dataset dumps. Download and use history files in SQLite format. Research Tools Synthical - AI-powered collaborative environment for Research. 🌟🌟 TensorTrade - Trade efficiently with reinforcement learning. ML-Quant - Quant resources from ArXiv (sanity), SSRN, RePec, Journals, Podcasts, Videos, and Blogs. JAQS - An open source quant strategies research platform. pyfolio - Portfolio and risk analytics in Python. alphalens - Performance analysis of predictive (alpha) stock factors. empyrical - Common financial risk and performance metrics. Used by Zipline and pyfolio. zvt - Zero vector trader. Trading System For Back Test & Live trading Traditional Market System 🌟🌟🌟 OpenBB - AI-powered opensource research and analytics workspace. 🌟🌟 zipline - A python algorithmic trading library. 🌟 TradingView - Get real-time information and market insights. rqalpha - A extendable, replaceable Python algorithmic backtest & trading framework. backtrader - Python backtesting library for trading strategies. kungfu - Kungfu Master trading system. lean - Algorithmic trading engine built for easy strategy research, backtesting and live trading. Combine & Rebuild pylivetrader - Python live trade execution library with zipline interface. CoinMarketCapBacktesting - As backtest frameworks for coin trading strategy. Crypto Currencies zenbot - Command-line crypto currency trading bot using Node.js and MongoDB. bot18 - High-frequency crypto currency trading bot developed by Zenbot. magic8bot - Crypto currency trading bot using Node.js and MongoDB. catalyst - An algorithmic trading library for Crypto-Assets in python. QuantResearchDev - Quant Research dev & Traders open source project. MACD - Zenbot MACD Auto-Trader. abu - A quant trading system base on python. Plugins CoinMarketCapBacktesting - Tests bt and Quantopian Zipline as backtesting frameworks for coin trading strategy. Gekko-BacktestTool - Batch backtest, import and strategy params optimalization for Gekko Trading Bot. TA Lib pandastalib - A Python Pandas implementation of technical analysis indicators. finta - Common financial technical indicators implemented in Python-Pandas (70+ indicators). tulipnode - Official Node.js wrapper for Tulip Indicators. Provides over 100 technical analysis overlay and indicator functions. techan.js - A visual, technical analysis and charting (Candlestick, OHLC, indicators) library built on D3. Exchange API Do it in real world! IbPy - Python API for the Interactive Brokers on-line trading system. HuobiFeeder - Connect HUOBIPRO exchange, get market/historical data for ABAT trading platform backtest analysis and live trading. ctpwrapper - Shanghai future exchange CTP api. PENDAX - Javascript SDK for Trading/Data API and Websockets for cryptocurrency exchanges like FTX, FTXUS, OKX, Bybit, & More Framework tf-quant-finance - High-performance TensorFlow library for quantitative finance. Visualizing playground - Play with neural networks. netron - Visualizer for deep learning and machine learning models. KLineChart - Highly customizable professional lightweight financial charts GYM Environment 🌟 TradingGym - Trading and Backtesting environment for training reinforcement learning agent. TradzQAI - Trading environment for RL agents, backtesting and training. btgym - Scalable, event-driven, deep-learning-friendly backtesting library. Articles The-Economist - The Economist. nyu-mlif-notes - NYU machine learning in finance notes. Using LSTMs to Turn Feelings Into Trades Others zipline-tensorboard - TensorBoard as a Zipline dashboard. gekko-quasar-ui - An UI port for gekko trading bot using Quasar framework. Floom AI gateway and marketplace for developers, enables streamlined integration and least volatile approach of AI features into products Other Resource 🌟🌟🌟 Stock-Prediction-Models - Stock-Prediction-Models, Gathers machine learning and deep learning models for Stock forecasting, included trading bots and simulations. 🌟🌟 Financial Machine Learning - A curated list of practical financial machine learning (FinML) tools and applications. This collection is primarily in Python. 🌟 Awesome-Quant-Machine-Learning-Trading - Quant / Algorithm trading resources with an emphasis on Machine Learning. awesome-quant - A curated list of insanely awesome libraries, packages and resources for Quants (Quantitative Finance). FinancePy - A Python Finance Library that focuses on the pricing and risk-management of Financial Derivatives, including fixed-income, equity, FX and credit derivatives. Explore Finance Service Libraries & Projects - Explore a curated list of Fintech popular & new libraries, top authors, trending project kits, discussions, tutorials & learning resources on kandi.

0.64

krishnakumarsekar•Mar 27, 2025

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

#github #awesome-quantum-machine-learning

Ultimate-Data-Science-Toolkit---From-Python-Basics-to-GenerativeAI

#github #ultimate-data-science-toolkit---from-python-basics-to-generativeai

0.555

0.3470230117125603

bansalkanav•Mar 27, 2025

Ultimate-Data-Science-Toolkit---From-Python-Basics-to-GenerativeAI

Getting started with Machine Learning and Deep Learning Star this repo if you find it useful :star: Module 1 - Python Programming | Topic Name | What's Covered | | :---: | :---: | | Intro to Python | Applications and Features of Python, Hello World Program, Identifiers and Rules to define identifiers, Data Types (numeric, boolean, strings, list, tuple, set and dict), Comments, Input and Output, Operators - Arithmatic, Reltaional, Equality, Logical, Bitwise, Assignment, Ternary, Identity and Membership | | Data Structures in Python (Strings, List, Tuple, Set, Dictionary) | Strings - Creating a string, Indexing, Slicing, Split, Join, etc, List - Initialization, Indexing, Slicing, Sorting, Appending, etc, Tuple - Initialization, Indexing, Slicing, Count, Index, etc, Set - Initialization, Unordered Sequence, Set Opertaions, etc, Dictionary - Initialization, Updating, Keys, Values, Items, etc | | Control Statements (Conditionals and Loops) | Conditional Statements - Introducing Indentation, if statement, if...else statement, if..elif...else statement, Nested if else statement, Loops - while loops, while...else loop, Membership operator, for loop, for...else loop, Nested Loops, Break and Continue Statement, Why else? | | Functions and Modules | Functions - Introduction to Python Functions, Function Definition and Calling, Functions with Arguments/Parameters, Return Statement, Scope of a Variable, Global Variables, Modules - Introduction to Modules, Importing a Module, Aliasing, from...import statement, import everything, Some important modules - math, platform, random, webbrowser, etc | | Object Oriented Programming | Classes and Objects - Creating a class, Instantiating an Object, Constructor, Class Members - Variables and Mentods, Types of Variables - Instance, Static and Local Variables, Types of Methods - Instance, Class and Static Methods, Access Modifiers - Public, Private and Protected, Pillars of Object Oriented Programming - Inheritance, Polymorphism, Abstraction and Encapsulation, Setters and Getters, Inheritance vs Association | | Exception Handling | Errors vs Exception, Syntax and Indentation Errors, try...except block, Control Flow in try...except block, try with multiple except, finally block, try...except...else, Nested try...except...finally, User Defined Exception | | File Handling | Introduction to File Handling, Opening and Closing a File, File Object Properties, Read Data from Text Files, Write Data to Text Files, with statement, Renaming and Deleting Files | | Web API | Application Programming Interface, Indian Space Station API, API Request, Status Code, Query Parameters, Getting JSON from an API Request, Working with JSON - dump and load, Working with Twitter API | | Databases | Introduction to Databases, SQLite3 - Connecting Python with SQLite3, Performing CRUD Opertations, MySQL - Connecting Python with MySQL, Performing CRUD Opertations, MongoDB - Connecting Python with MongoDB, Performing CRUD Opertations, Object Relation Mapping - SQLAlchemy ORM, CRUD operations and Complex DB operations | | List Comprehension, Lambda, Filter, Map, Reduce) | List Comprehension, Anonymous Functions, Filter, Map, Reduce, Function Aliasing | | Problem Solving for Interviews | Swapping two numbers, Factorial of a number, Prime Number, Fibbonnacci Sequence, Armstrong Number, Palindrome Number, etc | Module 2 - Python for Data Analysis | Topic Name | What's Covered | | :---: | :---: | | Data Analytics Framework | Data Collection, Business Understanding, Exploratory Data Analysis, Data Preparation, Model Building, Model Evaluation, Deployment, Understanding Cross Industry Standard Process for Data Mining (CRISP-DM) and Microsoft's Team Data Science Process (TDSP) | | Numpy | Array Oriented Numerical Computations using Numpy, Creating a Numpy Array, Basic Operations on Numpy Array - Check Dimensions, Shape, Datatypes and ItemSize, Why Numpy, Various ways to create Numpy Array, Numpy arange() function, Numpy Random Module - rand(), randn(), randint(), uniform(), etc, Indexing and Slicing in Numpy Arrays, Applying Mathematical Operations on Numpy Array - add(), subtract(), multiply(), divide(), dot(), matmul(), sum(), log(), exp(), etc, Statistical Operations on Numpy Array - min(), max(), mean(), median(), var(), std(), corrcoef(), etc, Reshaping a Numpy Array, Miscellaneous Topics - Linspace, Sorting, Stacking, Concatenation, Append, Where and Numpy Broadcasting | | Pandas for Beginners | Pandas Data Structures - Series, Dataframe and Panel, Creating a Series, Data Access, Creating a Dataframe using Tuples and Dictionaries, DataFrame Attributes - columns, shape, dtypes, axes, values, etc, DataFrame Methods - head(), tail(), info(), describe(), Working with .csv and .xlsx - readcsv() and readexcel(), DataFrame to .csv and .xlsx - tocsv() and toexcel() | | Advance Pandas Operations | What's Covered | | Case Study - Pandas Manipulation | What's Covered | | Missing Value Treatment | What's Covered | | Visuallization Basics - Matplotlib and Seaborn | What's Covered | | Case Study - Covid19TimeSeries | What's Covered | | Plotly and Express | What's Covered | | Outliers - Coming Soon | What's Covered | Module 3 - Statistics for Data Analysis | Topic Name | What's Covered | | :---: | :---: | | Normal Distribution | What's Covered | | Central Limit Theorem | What's Covered | | Hypothesis Testing | What's Covered | | Chi Square Testing | What's Covered | | Performing Statistical Test | What's Covered | Module 4 - Machine Learning Data Preparation and Modelling with SKLearn Working with Text Data Working with Image Data Supervised ML Algorithms K - Nearest Neighbours Linear Regression Logistic Regression Gradient Descent Decision Trees Support Vector Machines Models with Feature Engineering Hyperparameter Tuning Ensembles Unsupervised ML Algorithms Clustering Principal Component Analysis Module 5 - MLOPs | Topic Name | What's Covered | | :---: | :---: | | Model Serialization and Deserialization | What's Covered | | Application Integration | What's Covered | | MLFlow - Experiment Tracking and Model Management | What's Covered | | Prefect - Orchestrate ML Pipeline | What's Covered | Module 6 - Case Studies | Topic Name | What's Covered | | :---: | :---: | | Car Price Prediction (Regression) | What's Covered | | Airline Sentiment Analysis (NLP - Classification) | What's Covered | | Adult Income Prediction (Classification) | What's Covered | | Web App Development + Serialization and Deserialization | What's Covered | | AWS Deployment | What's Covered | | Streamlit Heroku Deployment | What's Covered | | Customer Segmentation | What's Covered | | Web Scrapping | What's Covered | Module 7 - Deep Learning | Topic Name | What's Covered | | :---: | :---: | | Introduction to Deep Learning | What's Covered | | Training a Deep Neural Network + TensorFlow.Keras | What's Covered | | Convolutional Neural Network + TensorFlow.Keras | What's Covered | | Auto Encoders for Image Compression) | What's Covered | | Recurrent Neural Network (Coming Soon) | What's Covered |

GregSommerville•Mar 27, 2025

0.42

0.022610872675250356

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

#github #machine-learning-blackjack-solution

youtube

0.369

0.71

Brodie Robertson•Mar 26, 2025

Vibe Coding Is Very Not A Joke

Yes there are actually people listing vibe coding jobs, I know that sounds insane and it kind of is, but welcome to world of 2025 where people are programming with AI and have no engineering knowledge. ==========Support The Channel========== ► Patreon: https://brodierobertson.xyz/patreon ► Paypal: https://brodierobertson.xyz/paypal ► Liberapay: https://brodierobertson.xyz/liberapay ► Amazon USA: https://brodierobertson.xyz/amazonusa ==========Resources========== Vibe Coding Careers: https://www.vibecodecareers.com/ =========Video Platforms========== 🎥 Odysee: https://brodierobertson.xyz/odysee 🎥 Podcast: https://techovertea.xyz/youtube 🎮 Gaming: https://brodierobertson.xyz/gaming ==========Social Media========== 🎤 Discord: https://brodierobertson.xyz/discord 🐦 Twitter: https://brodierobertson.xyz/twitter 🌐 Mastodon: https://brodierobertson.xyz/mastodon 🖥️ GitHub: https://brodierobertson.xyz/github ==========Credits========== 🎨 Channel Art: Profile Picture: https://www.instagram.com/supercozman_draws/ #VibeCoding #AI #LLM #Coding #Programming 🎵 Ending music Track: Debris & Jonth - Game Time [NCS Release] Music provided by NoCopyrightSounds. Watch: https://www.youtube.com/watch?v=yDTvvOTie0w Free Download / Stream: http://ncs.io/GameTime DISCLOSURE: Wherever possible I use referral links, which means if you click one of the links in this video or description and make a purchase I may receive a small commission or other compensation.

solagent99•Mar 25, 2025

Solana_AIAgent_Trading

Solana AI Agent Trading Tool An open-source trading toolkit for connecting AI agents to Solana protocols. Now, any agent, using any model can autonomously perform 15+ Solana actions: Trade tokens Launch new tokens Lend assets Send compressed airdrops Execute blinks Launch tokens on AMMs And more... 💬 Contact Me If you have any question or something, feel free to reach out me anytime via telegram, discord or twitter. 🌹 You're always welcome 🌹 Telegram: @Leo Replit template created by Arpit Singh 🔧 Core Blockchain Features Token Operations Deploy SPL tokens by Metaplex Transfer assets Balance checks Stake SOL Zk compressed Airdrop by Light Protocol and Helius NFTs on 3.Land Create your own collection NFT creation and automatic listing on 3.land List your NFT for sale in any SPL token NFT Management via Metaplex Collection deployment NFT minting Metadata management Royalty configuration DeFi Integration Jupiter Exchange swaps Launch on Pump via PumpPortal Raydium pool creation (CPMM, CLMM, AMMv4) Orca Whirlpool integration Manifest market creation, and limit orders Meteora Dynamic AMM, DLMM Pool, and Alpha Vault Openbook market creation Register and Resolve SNS Jito Bundles Pyth Price feeds for fetching Asset Prices Register/resolve Alldomains Perpetuals Trading with Adrena Protocol Drift Vaults, Perps, Lending and Borrowing Solana Blinks Lending by Lulo (Best APR for USDC) Send Arcade Games JupSOL staking Solayer SOL (sSOL)staking Non-Financial Actions Gib Work for registering bounties 🤖 AI Integration Features LangChain Integration Ready-to-use LangChain tools for blockchain operations Autonomous agent support with React framework Memory management for persistent interactions Streaming responses for real-time feedback Vercel AI SDK Integration Vercel AI SDK for AI agent integration Framework agnostic support Quick and easy toolkit setup Autonomous Modes Interactive chat mode for guided operations Autonomous mode for independent agent actions Configurable action intervals Built-in error handling and recovery AI Tools DALL-E integration for NFT artwork generation Natural language processing for blockchain commands Price feed integration for market analysis Automated decision-making capabilities 📃 Documentation You can view the full documentation of the kit at docs.solanaagentkit.xyz 📦 Installation Quick Start Usage Examples Deploy a New Token Create NFT Collection on 3Land Create NFT on 3Land When creating an NFT using 3Land's tool, it automatically goes for sale on 3.land website Create NFT Collection Swap Tokens Lend Tokens Stake SOL Stake SOL on Solayer Send an SPL Token Airdrop via ZK Compression Fetch Price Data from Pyth Open PERP Trade Close PERP Trade Close Empty Token Accounts Create a Drift account Create a drift account with an initial token deposit. Create a Drift Vault Create a drift vault. Deposit into a Drift Vault Deposit tokens into a drift vault. Deposit into your Drift account Deposit tokens into your drift account. Derive a Drift Vault address Derive a drift vault address. Do you have a Drift account Check if agent has a drift account. Get Drift account information Get drift account information. Request withdrawal from Drift vault Request withdrawal from drift vault. Carry out a perpetual trade using a Drift vault Open a perpertual trade using a drift vault that is delegated to you. Carry out a perpetual trade using your Drift account Open a perpertual trade using your drift account. Update Drift vault parameters Update drift vault parameters. Withdraw from Drift account Withdraw tokens from your drift account. Borrow from Drift Borrow tokens from drift. Repay Drift loan Repay a loan from drift. Withdraw from Drift vault Withdraw tokens from a drift vault after the redemption period has elapsed. Update the address a Drift vault is delegated to Update the address a drift vault is delegated to. Get Voltr Vault Position Values Get the current position values and total value of assets in a Voltr vault. Deposit into Voltr Strategy Deposit assets into a specific strategy within a Voltr vault. Withdraw from Voltr Strategy Withdraw assets from a specific strategy within a Voltr vault. Get a Solana asset by its ID Get a price inference from Allora Get the price for a given token and timeframe from Allora's API List all topics from Allora Get an inference for an specific topic from Allora Examples LangGraph Multi-Agent System The repository includes an advanced example of building a multi-agent system using LangGraph and Solana Agent Kit. Located in examples/agent-kit-langgraph, this example demonstrates: Multi-agent architecture using LangGraph's StateGraph Specialized agents for different tasks: General purpose agent for basic queries Transfer/Swap agent for transaction operations Read agent for blockchain data queries Manager agent for routing and orchestration Fully typed TypeScript implementation Environment-based configuration Check out the LangGraph example for a complete implementation of an advanced Solana agent system. Dependencies The toolkit relies on several key Solana and Metaplex libraries: @solana/web3.js @solana/spl-token @metaplex-foundation/digital-asset-standard-api @metaplex-foundation/mpl-token-metadata @metaplex-foundation/mpl-core @metaplex-foundation/umi @lightprotocol/compressed-token @lightprotocol/stateless.js Contributing Contributions are welcome! Please feel free to submit a Pull Request. Refer to CONTRIBUTING.md for detailed guidelines on how to contribute to this project. Contributors Star History License Apache-2 License Funding If you wanna give back any tokens or donations to the OSS community -- The Public Solana Agent Kit Treasury Address: Solana Network : EKHTbXpsm6YDgJzMkFxNU1LNXeWcUW7Ezf8mjUNQQ4Pa Security This toolkit handles private keys and transactions. Always ensure you're using it in a secure environment and never share your private keys.

#github #solana_aiagent_trading

rphilipzhang•Mar 25, 2025

0.472

0.0922477795435268

AI-PhD-S24

Artificial Intelligence for Business Research (Spring 2024) Scribed Lecture Notes Class Recordings (You need to apply for access.) Teaching Team Instructor*: Renyu (Philip) Zhang, Associate Professor, Department of Decisions, Operations and Technology, CUHK Business School, philipzhang@cuhk.edu.hk, @911 Cheng Yu Tung Building. Teaching Assistant*: Leo Cao, Full-time TA, Department of Decisions, Operations and Technology, CUHK Business School, yinglyucao@cuhk.edu.hk. Please be noted that Leo will help with any issues related to the logistics, but not the content, of this course. Tutorial Instructor*: Qiansiqi Hu, MSBA Student, Department of Decisions, Operations and Technology, CUHK Business School, 1155208353@link.cuhk.edu.hk. BS in ECE, Shanghai Jiaotong University Michigan Institute. Basic Information Website: https://github.com/rphilipzhang/AI-PhD-S24 Time: Tuesday, 12:30pm-3:15pm, from Jan 9, 2024 to Apr 16, 2024, except for Feb 13 (Chinese New Year) and Mar 5 (Final Project Discussion) Location: Cheng Yu Tung Building (CYT) LT5 About Welcome to the mono-repo of the PhD course AI for Business Research (DSME 6635) at CUHK Business School in Spring 2024. You may download the Syllabus of this course first. The purpose of this course is to learn the following: Have a basic understanding of the fundamental concepts/methods in machine learning (ML) and artificial intelligence (AI) that are used (or potentially useful) in business research. Understand how business researchers have utilized ML/AI and what managerial questions have been addressed by ML/AI in the recent decade. Nurture a taste of what the state-of-the-art AI/ML technologies can do in the ML/AI community and, potentially, in your own research field. We will meet each Tuesday at 12:30pm in Cheng Yu Tung Building (CYT) LT5 (please pay attention to this room change). Please ask for my approval if you need to join us via the following Zoom links: Zoom link, Meeting ID 996 4239 3764, Passcode 386119. Most of the code in this course will be distributed through the Google CoLab cloud computing environment to avoid the incompatibility and version control issues on your local individual computer. On the other hand, you can always download the Jupyter Notebook from CoLab and run it your own computer. The CoLab files of this course can be found at this folder. The Google Sheet to sign up for groups and group tasks can be found here. The overleaf template for scribing the lecture notes of this course can be found here. If you have any feedback on this course, please directly contact Philip at philipzhang@cuhk.edu.hk and we will try our best to address it. Brief Schedule Subject to modifications. All classes start at 12:30pm and end at 3:15pm. |Session|Date |Topic|Key Words| |:-------:|:-------------:|:----:|:-:| |1|1.09|AI/ML in a Nutshell|Course Intro, ML Models, Model Evaluations| |2|1.16|Intro to DL|DL Intro, Neural Nets, Computational Issues in DL| |3|1.23|Prediction and Traditional NLP|Prediction in Biz Research, Pre-processing| |4|1.30|NLP (II): Traditional NLP|$N$-gram, NLP Performance Evaluations, Naïve Bayes| |5|2.06|NLP (III): Word2Vec|CBOW, Skip Gram| |6|2.20|NLP (IV): RNN|Glove, Language Model Evaluation, RNN| |7|2.27|NLP (V): Seq2Seq|LSTM, Seq2Seq, Attention Mechanism| |7.5|3.05|NLP (V.V): Transformer|The Bitter Lesson, Attention is All You Need| |8|3.12|NLP (VI): Pre-training|Computational Tricks in DL, BERT, GPT| |9|3.19|NLP (VII): LLM|Emergent Abilities, Chain-of-Thought, In-context Learning, GenAI in Business Research| |10|3.26|CV (I): Image Classification|CNN, AlexNet, ResNet, ViT| |11|4.02|CV (II): Image Segmentation and Video Analysis|R-CNN, YOLO, 3D-CNN| |12|4.09|Unsupervised Learning (I): Clustering & Topic Modeling|GMM, EM Algorithm, LDA| |13|4.16|Unsupervised Learning (II): Diffusion Models|VAE, DDPM, LDM, DiT| Important Dates All problem sets are due at 12:30pm right before class. |Date| Time|Event|Note| |:--:|:-:|:---:|:--:| |1.10| 11:59pm|Group Sign-Ups|Each group has at most two students.| |1.12| 7:00pm-9:00pm|Python Tutorial|Given by Qiansiqi Hu, Python Tutorial CoLab| |1.19| 7:00pm-9:00pm|PyTorch Tutorial|Given by Qiansiqi Hu, PyTorch Tutorial CoLab| |3.05|9:00am-6:00pm|Final Project Discussion|Please schedule a meeting with Philip.| |3.12| 12:30pm|Final Project Proposal|1-page maximum| |4.30| 11:59pm|Scribed Lecture Notes|Overleaf link| |5.12|11:59pm|Project Paper, Slides, and Code|Paper page limit: 10| Useful Resources Find more on the Syllabus. Books: ESL, Deep Learning, Dive into Deep Learning, ML Fairness, Applied Causal Inference Powered by ML and AI Courses: ML Intro by Andrew Ng, DL Intro by Andrew Ng, NLP (CS224N) by Chris Manning, CV (CS231N) by Fei-Fei Li, Deep Unsupervised Learning by Pieter Abbeel, DLR by Sergey Levine, DL Theory by Matus Telgarsky, LLM by Danqi Chen, Generative AI by Andrew Ng, Machine Learning and Big Data by Melissa Dell and Matthew Harding, Digital Economics and the Economics of AI by Martin Beraja, Chiara Farronato, Avi Goldfarb, and Catherine Tucker Detailed Schedule The following schedule is tentative and subject to changes. Session 1. Artificial Intelligence and Machine Learning in a Nutshell (Jan/09/2024) Keywords: Course Introduction, Machine Learning Basics, Bias-Variance Trade-off, Cross Validation, $k$-Nearest Neighbors, Decision Tree, Ensemble Methods Slides: Course Introduction, Machine Learning Basics CoLab Notebook Demos: k-Nearest Neighbors, Decision Tree Homework: Problem Set 1: Bias-Variance Trade-Off Online Python Tutorial: Python Tutorial CoLab, 7:00pm-9:00pm, Jan/12/2024 (Friday), given by Qiansiqi Hu, 1155208353@link.cuhk.edu.hk. Zoom Link, Meeting ID: 923 4642 4433, Pass code: 178146 References: The Elements of Statistical Learning (2nd Edition), 2009, by Trevor Hastie, Robert Tibshirani, Jerome Friedman, https://hastie.su.domains/ElemStatLearn/. Probabilistic Machine Learning: An Introduction, 2022, by Kevin Murphy, https://probml.github.io/pml-book/book1.html. Mullainathan, Sendhil, and Jann Spiess. 2017. Machine learning: an applied econometric approach. Journal of Economic Perspectives 31(2): 87-106. Athey, Susan, and Guido W. Imbens. 2019. Machine learning methods that economists should know about. Annual Review of Economics 11: 685-725. Hofman, Jake M., et al. 2021. Integrating explanation and prediction in computational social science. Nature 595.7866: 181-188. Bastani, Hamsa, Dennis Zhang, and Heng Zhang. 2022. Applied machine learning in operations management. Innovative Technology at the Interface of Finance and Operations. Springer: 189-222. Kelly, Brian, and Dacheng Xiu. 2023. Financial machine learning, SSRN, https://ssrn.com/abstract=4501707. The Bitter Lesson, by Rich Sutton, which develops so far the most critical insight of AI: "The biggest lesson that can be read from 70 years of AI research is that general methods that leverage computation are ultimately the most effective, and by a large margin." Session 2. Introduction to Deep Learning (Jan/16/2024) Keywords: Random Forests, eXtreme Gradient Boosting Trees, Deep Learning Basics, Neural Nets Models, Computational Issues of Deep Learning Slides: Machine Learning Basics, Deep Learning Basics CoLab Notebook Demos: Random Forest, Extreme Gradient Boosting Tree, Gradient Descent, Chain Rule Presentation: By Xinyu Li and Qingyu Xu. Gu, Shihao, Brian Kelly, and Dacheng Xiu. 2020. Empirical asset pricing via machine learning. Review of Financial Studies 33: 2223-2273. Link to the paper. Homework: Problem Set 2: Implementing Neural Nets Online PyTorch Tutorial: PyTorch Tutorial CoLab, 7:00pm-9:00pm, Jan/19/2024 (Friday), given by Qiansiqi Hu, 1155208353@link.cuhk.edu.hk. Zoom Link, Meeting ID: 923 4642 4433, Pass code: 178146 References: Deep Learning, 2016, by Ian Goodfellow, Yoshua Bengio and Aaron Courville, https://www.deeplearningbook.org/. Dive into Deep Learning (2nd Edition), 2023, by Aston Zhang, Zack Lipton, Mu Li, and Alex J. Smola, https://d2l.ai/. Probabilistic Machine Learning: Advanced Topics, 2023, by Kevin Murphy, https://probml.github.io/pml-book/book2.html. Deep Learning with PyTorch, 2020, by Eli Stevens, Luca Antiga, and Thomas Viehmann. Gu, Shihao, Brian Kelly, and Dacheng Xiu. 2020. Empirical asset pricing with machine learning. Review of Financial Studies 33: 2223-2273. Session 3. DL Basics, Predictions in Business Research, and Traditonal NLP (Jan/23/2024) Keywords: Optimization and Computational Issues of Deep Learning, Prediction Problems in Business Research, Pre-processing and Word Representations in Traditional Natural Language Processing Slides: Deep Learning Basics, Prediction Problems in Business Research, NLP(I): Pre-processing and Word Representations.pdf) CoLab Notebook Demos: He Initialization, Dropout, Micrograd, NLP Pre-processing Presentation: By Letian Kong and Liheng Tan. Mullainathan, Sendhil, and Jann Spiess. 2017. Machine learning: an applied econometric approach. Journal of Economic Perspectives 31(2): 87-106. Link to the paper. Homework: Problem Set 2: Implementing Neural Nets, due at 12:30pm, Jan/30/2024 (Tuesday). References: Kleinberg, Jon, Jens Ludwig, Sendhil Mullainathan, and Ziad Obermeyer. 2015. Prediction policy problems. American Economic Review 105(5): 491-495. Mullainathan, Sendhil, and Jann Spiess. 2017. Machine learning: an applied econometric approach. Journal of Economic Perspectives 31(2): 87-106. Kleinberg, Jon, Himabindu Lakkaraju, Jure Leskovec, Jens Ludwig, and Sendhil Mullainathan. 2018. Human decisions and machine predictions. Quarterly Journal of Economics 133(1): 237-293. Bajari, Patrick, Denis Nekipelov, Stephen P. Ryan, and Miaoyu Yang. 2015. Machine learning methods for demand estimation. American Economic Review, 105(5): 481-485. Farias, Vivek F., and Andrew A. Li. 2019. Learning preferences with side information. Management Science 65(7): 3131-3149. Cui, Ruomeng, Santiago Gallino, Antonio Moreno, and Dennis J. Zhang. 2018. The operational value of social media information. Production and Operations Management, 27(10): 1749-1769. Gentzkow, Matthew, Bryan Kelly, and Matt Taddy. 2019. Text as data. Journal of Economic Literature, 57(3): 535-574. Chapter 2, Introduction to Information Retrieval, 2008, Cambridge University Press, by Christopher D. Manning, Prabhakar Raghavan and Hinrich Schutze, https://nlp.stanford.edu/IR-book/information-retrieval-book.html. Chapter 2, Speech and Language Processing (3rd ed. draft), 2023, by Dan Jurafsky and James H. Martin, https://web.stanford.edu/~jurafsky/slp3/. Parameter Initialization and Batch Normalization (in Chinese) GPU Comparisons-vs-NVIDIA-H100-(PCIe)-vs-NVIDIA-RTX-6000-Ada/624vs632vs640) GitHub Repo for Micrograd, by Andrej Karpathy. Hand Written Notes Session 4. Traditonal NLP (Jan/30/2024) Keywords: Pre-processing and Word Representations in NLP, N-Gram, Naïve Bayes, Language Model Evaluation, Traditional NLP Applied to Business/Econ Research Slides: NLP(I): Pre-processing and Word Representations.pdf), NLP(II): N-Gram, Naïve Bayes, and Language Model Evaluation.pdf) CoLab Notebook Demos: NLP Pre-processing, N-Gram, Naïve Bayes Presentation: By Zhi Li and Boya Peng. Hansen, Stephen, Michael McMahon, and Andrea Prat. 2018. Transparency and deliberation within the FOMC: A computational linguistics approach. Quarterly Journal of Economics, 133(2): 801-870. Link to the paper. Homework: Problem Set 3: Implementing Traditional NLP Techniques, due at 12:30pm, Feb/6/2024 (Tuesday). References: Gentzkow, Matthew, Bryan Kelly, and Matt Taddy. 2019. Text as data. Journal of Economic Literature, 57(3): 535-574. Hansen, Stephen, Michael McMahon, and Andrea Prat. 2018. Transparency and deliberation within the FOMC: A computational linguistics approach. Quarterly Journal of Economics, 133(2): 801-870. Chapters 2, 12, & 13, Introduction to Information Retrieval, 2008, Cambridge University Press, by Christopher D. Manning, Prabhakar Raghavan and Hinrich Schutze, https://nlp.stanford.edu/IR-book/information-retrieval-book.html. Chapter 2, 3 & 4, Speech and Language Processing (3rd ed. draft), 2023, by Dan Jurafsky and James H. Martin, https://web.stanford.edu/~jurafsky/slp3/. Natural Language Tool Kit (NLTK) Documentation Hand Written Notes Session 5. Deep-Learning-Based NLP: Word2Vec (Feb/06/2024) Keywords: Traditional NLP Applied to Business/Econ Research, Word2Vec: Continuous Bag of Words and Skip-Gram Slides: NLP(II): N-Gram, Naïve Bayes, and Language Model Evaluation.pdf), NLP(III): Word2Vec.pdf) CoLab Notebook Demos: Word2Vec: CBOW, Word2Vec: Skip-Gram Presentation: By Xinyu Xu and Shu Zhang. Timoshenko, Artem, and John R. Hauser. 2019. Identifying customer needs from user-generated content. Marketing Science, 38(1): 1-20. Link to the paper. Homework: No homework this week. Probably you should think about your final project when enjoying your Lunar New Year Holiday. References: Gentzkow, Matthew, Bryan Kelly, and Matt Taddy. 2019. Text as data. Journal of Economic Literature, 57(3): 535-574. Tetlock, Paul. 2007. Giving content to investor sentiment: The role of media in the stock market. Journal of Finance, 62(3): 1139-1168. Baker, Scott, Nicholas Bloom, and Steven Davis, 2016. Measuring economic policy uncertainty. Quarterly Journal of Economics, 131(4): 1593-1636. Gentzkow, Matthew, and Jesse Shapiro. 2010. What drives media slant? Evidence from US daily newspapers. Econometrica, 78(1): 35-71. Timoshenko, Artem, and John R. Hauser. 2019. Identifying customer needs from user-generated content. Marketing Science, 38(1): 1-20. Mikolov, Tomas, Kai Chen, Greg Corrado, and Jeff Dean. 2013. Efficient estimation of word representations in vector space. ArXiv Preprint, arXiv:1301.3781. Mikolov, Tomas, Ilya Sutskever, Kai Chen, Greg Corrado, and Jeff Dean. 2013. Distributed representations of words and phrases and their compositionality. Advances in Neural Information Processing Systems (NeurIPS) 26. Parts I - II, Lecture Notes and Slides for CS224n: Natural Language Processing with Deep Learning, by Christopher D. Manning, Diyi Yang, and Tatsunori Hashimoto, https://web.stanford.edu/class/cs224n/. Word Embeddings Trained on Google News Corpus Hand Written Notes Session 6. Deep-Learning-Based NLP: RNN and Seq2Seq (Feb/20/2024) Keywords: Word2Vec: GloVe, Word Embedding and Language Model Evaluations, Word2Vec and RNN Applied to Business/Econ Research, RNN Slides: Guest Lecture Announcement, NLP(III): Word2Vec.pdf), NLP(IV): RNN & Seq2Seq.pdf) CoLab Notebook Demos: Word2Vec: CBOW, Word2Vec: Skip-Gram Presentation: By Qiyu Dai and Yifan Ren. Huang, Allen H., Hui Wang, and Yi Yang. 2023. FinBERT: A large language model for extracting information from financial text. Contemporary Accounting Research, 40(2): 806-841. Link to the paper. Link to GitHub Repo. Homework: Problem Set 4 - Word2Vec & LSTM for Sentiment Analysis References: Ash, Elliot, and Stephen Hansen. 2023. Text algorithms in economics. Annual Review of Economics, 15: 659-688. Associated GitHub with Code Demonstrations. Li, Kai, Feng Mai, Rui Shen, and Xinyan Yan. 2021. Measuring corporate culture using machine learning. Review of Financial Studies, 34(7): 3265-3315. Chen, Fanglin, Xiao Liu, Davide Proserpio, and Isamar Troncoso. 2022. Product2Vec: Leveraging representation learning to model consumer product choice in large assortments. Available at SSRN 3519358. Pennington, Jeffrey, Richard Socher, and Christopher Manning. 2014. Glove: Global vectors for word representation. Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP) (pp. 1532-1543). Parts 2 and 5, Lecture Notes and Slides for CS224n: Natural Language Processing with Deep Learning, by Christopher D. Manning, Diyi Yang, and Tatsunori Hashimoto, https://web.stanford.edu/class/cs224n/. Chapters 9 and 10, Dive into Deep Learning (2nd Edition), 2023, by Aston Zhang, Zack Lipton, Mu Li, and Alex J. Smola, https://d2l.ai/. RNN and LSTM Visualizations Hand Written Notes Session 7. Deep-Learning-Based NLP: Attention and Transformer (Feb/27/2024) Keywords: RNN and its Applications to Business/Econ Research, LSTM, Seq2Seq, Attention Mechanism Slides: Final Project, NLP(IV): RNN & Seq2Seq.pdf), NLP(V): Attention & Transformer.pdf) CoLab Notebook Demos: RNN & LSTM, Attention Mechanism Presentation: By Qinghe Gui and Chaoyuan Jiang. Zhang, Mengxia and Lan Luo. 2023. Can consumer-posted photos serve as a leading indicator of restaurant survival? Evidence from Yelp. Management Science 69(1): 25-50. Link to the paper. Homework: Problem Set 4 - Word2Vec & LSTM for Sentiment Analysis References: Qi, Meng, Yuanyuan Shi, Yongzhi Qi, Chenxin Ma, Rong Yuan, Di Wu, Zuo-Jun (Max) Shen. 2023. A Practical End-to-End Inventory Management Model with Deep Learning. Management Science, 69(2): 759-773. Sarzynska-Wawer, Justyna, Aleksander Wawer, Aleksandra Pawlak, Julia Szymanowska, Izabela Stefaniak, Michal Jarkiewicz, and Lukasz Okruszek. 2021. Detecting formal thought disorder by deep contextualized word representations. Psychiatry Research, 304, 114135. Hansen, Stephen, Peter J. Lambert, Nicholas Bloom, Steven J. Davis, Raffaella Sadun, and Bledi Taska. 2023. Remote work across jobs, companies, and space (No. w31007). National Bureau of Economic Research. Sutskever, Ilya, Oriol Vinyals, and Quoc V. Le. 2014. Sequence to sequence learning with neural networks. Advances in neural information processing systems, 27. Bahdanau, Dzmitry, Kyunghyun Cho, and Yoshua Bengio. 2015. Neural machine translation by jointly learning to align and translate. ICLR Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., ... and Polosukhin, I. (2017). Attention is all you need. Advances in neural information processing systems, 30. Parts 5, 6, and 8, Lecture Notes and Slides for CS224n: Natural Language Processing with Deep Learning, by Christopher D. Manning, Diyi Yang, and Tatsunori Hashimoto, https://web.stanford.edu/class/cs224n/. Chapters 9, 10, and 11, Dive into Deep Learning (2nd Edition), 2023, by Aston Zhang, Zack Lipton, Mu Li, and Alex J. Smola, https://d2l.ai/. RNN and LSTM Visualizations PyTorch's Tutorial of Seq2Seq for Machine Translation Illustrated Transformer Transformer from Scratch, with the Code on GitHub Hand Written Notes Session 7.5. Deep-Learning-Based NLP: Attention is All You Need (Mar/05/2024) Keywords: Bitter Lesson: Power of Computation in AI, Attention Mechanism, Transformer Slides: The Bitter Lesson, NLP(V): Attention & Transformer.pdf) CoLab Notebook Demos: Attention Mechanism, Transformer Homework: One-page Proposal for Your Final Project References: The Bitter Lesson, by Rich Sutton Bahdanau, Dzmitry, Kyunghyun Cho, and Yoshua Bengio. 2015. Neural machine translation by jointly learning to align and translate. ICLR Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., ... and Polosukhin, I. (2017). Attention is all you need. Advances in neural information processing systems, 30. Part 8, Lecture Notes and Slides for CS224n: Natural Language Processing with Deep Learning, by Christopher D. Manning, Diyi Yang, and Tatsunori Hashimoto, https://web.stanford.edu/class/cs224n/. Chapter 11, Dive into Deep Learning (2nd Edition), 2023, by Aston Zhang, Zack Lipton, Mu Li, and Alex J. Smola, https://d2l.ai/. Illustrated Transformer Transformer from Scratch, with the Code on GitHub Andrej Karpathy's Lecture to Build Transformers Hand Written Notes Session 8. Deep-Learning-Based NLP: Pretraining (Mar/12/2024) Keywords: Computations in AI, BERT (Bidirectional Encoder Representations from Transformers), GPT (Generative Pretrained Transformers) Slides: Guest Lecture by Dr. Liubo Li on Deep Learning Computation, Pretraining.pdf) CoLab Notebook Demos: Crafting Intelligence: The Art of Deep Learning Modeling, BERT API @ Hugging Face Presentation: By Zhankun Chen and Yiyi Zhao. Noy, Shakked and Whitney Zhang. 2023. Experimental evidence on the productivity effects of generative artificial intelligence. Science, 381: 187-192. Link to the Paper Homework: Problem Set 5 - Sentiment Analysis with Hugging Face, due at 12:30pm, March 26, Tuesday. References: Devlin, Jacob, Ming-Wei Chang, Kenton Lee, Kristina Toutanova. 2018. BERT: Pre-training of deep bidirectional transformers for language understanding. ArXiv preprint arXiv:1810.04805. GitHub Repo Radford, Alec, Karthik Narasimhan, Tim Salimans, and Ilya Sutskever. 2018. Improving language understanding by generative pre-training, (GPT-1) PDF link, GitHub Repo Radford, Alec, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, Ilya Sutskever. 2019. Language models are unsupervised multitask learners. OpenAI blog, 1(8), 9. (GPT-2) PDF Link, GitHub Repo Brown, Tom, et al. 2020. Language models are few-shot learners. Advances in neural information processing systems, 33, 1877-1901. (GPT-3) GitHub Repo Huang, Allen H., Hui Wang, and Yi Yang. 2023. FinBERT: A large language model for extracting information from financial text. Contemporary Accounting Research, 40(2): 806-841. GitHub Repo Part 9, Lecture Notes and Slides for CS 224N: Natural Language Processing with Deep Learning, by Christopher D. Manning, Diyi Yang, and Tatsunori Hashimoto. Link to CS 224N Part 2 & 4, Slides for COS 597G: Understanding Large Language Models, by Danqi Chen. Link to COS 597G A Visual Guide to BERT, How GPT-3 Works Andrej Karpathy's Lecture to Build GPT-2 (124M) from Scratch Hand Written Notes Session 9. Deep-Learning-Based NLP: Large Language Models (Mar/19/2024) Keywords: Large Language Models, Generative AI, Emergent Ababilities, Instruction Fine-Tuning (IFT), Reinforcement Learning with Human Feedback (RLHF), In-Context Learning, Chain-of-Thought (CoT) Slides: What's Next, Pretraining.pdf), Large Language Models.pdf) CoLab Notebook Demos: BERT API @ Hugging Face Presentation: By Jia Liu. Liu, Liu, Dzyabura, Daria, Mizik, Natalie. 2020. Visual listening in: Extracting brand image portrayed on social media. Marketing Science, 39(4): 669-686. Link to the Paper Homework: Problem Set 5 - Sentiment Analysis with Hugging Face, due at 12:30pm, March 26, Tuesday (soft-deadline). References: Wei, Jason, et al. 2021. Finetuned language models are zero-shot learners. ArXiv preprint arXiv:2109.01652, link to the paper. Wei, Jason, et al. 2022. Emergent abilities of large language models. ArXiv preprint arXiv:2206.07682, link to the paper. Ouyang, Long, et al. 2022. Training language models to follow instructions with human feedback. Advances in Neural Information Processing Systems, 35, 27730-27744. Wei, Jason, et al. 2022. Chain-of-thought prompting elicits reasoning in large language models. Advances in Neural Information Processing Systems, 35, 24824-24837. Kaplan, Jared. 2020. Scaling laws for neural language models. ArXiv preprint arXiv:2001.08361, link to the paper. Hoffmann, Jordan, et al. 2022. Training compute-optimal large language models. ArXiv preprint arXiv:2203.15556, link to the paper. Shinn, Noah, et al. 2023. Reflexion: Language agents with verbal reinforcement learning. ArXiv preprint arXiv:2303.11366, link to the paper. Reisenbichler, Martin, Thomas Reutterer, David A. Schweidel, and Daniel Dan. 2022. Frontiers: Supporting content marketing with natural language generation. Marketing Science, 41(3): 441-452. Romera-Paredes, B., Barekatain, M., Novikov, A. et al. 2023. Mathematical discoveries from program search with large language models. Nature, link to the paper. Part 10, Lecture Notes and Slides for CS224N: Natural Language Processing with Deep Learning, by Christopher D. Manning, Diyi Yang, and Tatsunori Hashimoto. Link to CS 224N COS 597G: Understanding Large Language Models, by Danqi Chen. Link to COS 597G Andrej Karpathy's 1-hour Talk on LLM CS224n, Hugging Face Tutorial Session 10. Deep-Learning-Based CV: Image Classification (Mar/26/2024) Keywords: Large Language Models Applications, Convolution Neural Nets (CNN), LeNet, AlexNet, VGG, ResNet, ViT Slides: What's Next, Large Language Models.pdf), Image Classification.pdf) CoLab Notebook Demos: CNN, LeNet, & AlexNet, VGG, ResNet, ViT Presentation: By Yingxin Lin and Zeshen Ye. Netzer, Oded, Alain Lemaire, and Michal Herzenstein. 2019. When words sweat: Identifying signals for loan default in the text of loan applications. Journal of Marketing Research, 56(6): 960-980. Link to the Paper Homework: Problem Set 6 - AlexNet and ResNet, due at 12:30pm, April 9, Tuesday. References: Krizhevsky, Alex, Ilya Sutskever, and Geoffrey E. Hinton. 2012. Imagenet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems, 25. He, Kaiming, Xiangyu Zhang, Shaoqing Ren and Jian Sun. 2016. Deep residual learning for image recognition. Proceedings of the IEEE conference on computer vision and pattern recognition, 770-778. Dosovitskiy, Alexey, et al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. ArXiv preprint, arXiv:2010.11929, link to the paper, link to the GitHub repo. Jean, Neal, Marshall Burke, Michael Xie, Matthew W. Davis, David B. Lobell, and Stefand Ermon. 2016. Combining satellite imagery and machine learning to predict poverty. Science, 353(6301), 790-794. Zhang, Mengxia and Lan Luo. 2023. Can consumer-posted photos serve as a leading indicator of restaurant survival? Evidence from Yelp. Management Science 69(1): 25-50. Course Notes (Lectures 5 & 6) for CS231n: Deep Learning for Computer Vision, by Fei-Fei Li, Ruohan Gao, & Yunzhu Li. Link to CS231n. Chapters 7 and 8, Dive into Deep Learning (2nd Edition), 2023, by Aston Zhang, Zack Lipton, Mu Li, and Alex J. Smola. Link to the book. Fine-Tune ViT for Image Classification with Hugging Face 🤗 Transformers Hugging Face 🤗 ViT CoLab Tutorial Session 11. Deep-Learning-Based CV (II): Object Detection & Video Analysis (Apr/2/2024) Keywords: Image Processing Applications, Localization, R-CNNs, YOLOs, Semantic Segmentation, 3D CNN, Video Analysis Applications Slides: What's Next, Image Classification.pdf), Object Detection and Video Analysis.pdf) CoLab Notebook Demos: Data Augmentation, Faster R-CNN & YOLO v5 Presentation: By Qinlu Hu and Yilin Shi. Yang, Jeremy, Juanjuan Zhang, and Yuhan Zhang. 2023. Engagement that sells: Influencer video advertising on TikTok. Available at SSRN Link to the Paper Homework: Problem Set 6 - AlexNet and ResNet, due at 12:30pm, April 9, Tuesday. References: Girshick, R., Donahue, J., Darrell, T. and Malik, J., 2014. Rich feature hierarchies for accurate object detection and semantic segmentation. Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 580-587). Redmon, Joseph, Santosh Divvala, Ross Girshick, and Ali Farhadi. 2016. You only look once: Unified, real-time object detection. Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 779-788). Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R. and Fei-Fei, L., 2014. Large-scale video classification with convolutional neural networks. Proceedings of the IEEE conference on Computer Vision and Pattern Recognition (pp. 1725-1732). Glaeser, Edward L., Scott D. Kominers, Michael Luca, and Nikhil Naik. 2018. Big data and big cities: The promises and limitations of improved measures of urban life. Economic Inquiry, 56(1): 114-137. Zhang, S., Xu, K. and Srinivasan, K., 2023. Frontiers: Unmasking Social Compliance Behavior During the Pandemic. Marketing Science, 42(3), pp.440-450. Course Notes (Lectures 10 & 11) for CS231n: Deep Learning for Computer Vision, by Fei-Fei Li, Ruohan Gao, & Yunzhu Li. Link to CS231n. Chapter 14, Dive into Deep Learning (2nd Edition), 2023, by Aston Zhang, Zack Lipton, Mu Li, and Alex J. Smola. Link to the book. Hand Written Notes Session 12. Unsupervised Learning: Clustering, Topic Modeling & VAE (Apr/9/2024) Keywords: K-Means, Gaussian Mixture Models, EM-Algorithm, Latent Dirichlet Allocation, Variational Auto-Encoder Slides: What's Next, Clustering, Topic Modeling & VAE.pdf) CoLab Notebook Demos: K-Means, LDA, VAE Homework: Problem Set 7 - Unsupervised Learning (EM & LDA), due at 12:30pm, April 23, Tuesday. References: Blei, David M., Ng, Andrew Y., and Jordan, Michael I. 2003. Latent Dirichlet allocation. Journal of Machine Learning Research, 3(Jan): 993-1022. Kingma, D.P. and Welling, M., 2013. Auto-encoding Variational Bayes. arXiv preprint arXiv:1312.6114. Kingma, D.P. and Welling, M., 2019. An introduction to variational autoencoders. Foundations and Trends® in Machine Learning, 12(4), pp.307-392. Bandiera, O., Prat, A., Hansen, S., & Sadun, R. 2020. CEO behavior and firm performance. Journal of Political Economy, 128(4), 1325-1369. Liu, Jia and Olivier Toubia. 2018. A semantic approach for estimating consumer content preferences from online search queries. Marketing Science, 37(6): 930-952. Mueller, Hannes, and Christopher Rauh. 2018. Reading between the lines: Prediction of political violence using newspaper text. American Political Science Review, 112(2): 358-375. Tian, Z., Dew, R. and Iyengar, R., 2023. Mega or Micro? Influencer Selection Using Follower Elasticity. Journal of Marketing Research. Chapters 8.5 and 14, The Elements of Statistical Learning (2nd Edition), 2009, by Trevor Hastie, Robert Tibshirani, Jerome Friedman, Link to Book. Course Notes (Lectures 1 & 4) for CS294-158-SP24: Deep Unsupervised Learning, taught by Pieter Abbeel, Wilson Yan, Kevin Frans, Philipp Wu. Link to CS294-158-SP24. Hand Written Notes Session 13. Unsupervised Learning: Diffusion Models (Apr/16/2024) Keywords: VAE, Denoised Diffusion Probabilistic Models, Latent Diffusion Models, CLIP, Imagen, Diffusion Transformers Slides: Clustering, Topic Modeling & VAE.pdf), Diffusion Models.pdf), Course Summary CoLab Notebook Demos: VAE, DDPM, DiT Homework: Problem Set 7 - Unsupervised Learning (EM & LDA), due at 12:30pm, April 23, Tuesday. References: Kingma, D.P. and Welling, M., 2013. Auto-encoding Variational Bayes. arXiv preprint arXiv:1312.6114. Kingma, D.P. and Welling, M., 2019. An introduction to variational autoencoders. Foundations and Trends® in Machine Learning, 12(4), pp.307-392. Ho, J., Jain, A. and Abbeel, P., 2020. Denoising diffusion probabilistic models. Advances in neural information processing systems, 33, 6840-6851. Chan, S.H., 2024. Tutorial on Diffusion Models for Imaging and Vision. arXiv preprint arXiv:2403.18103. Peebles, W. and Xie, S., 2023. Scalable diffusion models with transformers. In Proceedings of the IEEE/CVF International Conference on Computer Vision, 4195-4205. Link to GitHub Repo. Tian, Z., Dew, R. and Iyengar, R., 2023. Mega or Micro? Influencer Selection Using Follower Elasticity. Journal of Marketing Research. Ludwig, J. and Mullainathan, S., 2024. Machine learning as a tool for hypothesis generation. Quarterly Journal of Economics, 139(2), 751-827. Burnap, A., Hauser, J.R. and Timoshenko, A., 2023. Product aesthetic design: A machine learning augmentation. Marketing Science, 42(6), 1029-1056. Course Notes (Lecture 6) for CS294-158-SP24: Deep Unsupervised Learning, taught by Pieter Abbeel, Wilson Yan, Kevin Frans, Philipp Wu. Link to CS294-158-SP24. CVPR 2022 Tutorial: Denoising Diffusion-based Generative Modeling: Foundations and Applications, by Karsten Kreis, Ruiqi Gao, and Arash Vahdat Link to the Tutorial Lilian Weng (OpenAI)'s Blog on Diffusion Models Lilian Weng (OpenAI)'s Blog on Diffusion Models for Video Generation Hugging Face Diffusers 🤗 Library Hand Written Notes

voicefilter

VoiceFilter Note from Seung-won (2020.10.25) Hi everyone! It's Seung-won from MINDs Lab, Inc. It's been a long time since I've released this open-source, and I didn't expect this repository to grab such a great amount of attention for a long time. I would like to thank everyone for giving such attention, and also Mr. Quan Wang (the first author of the VoiceFilter paper) for referring this project in his paper. Actually, this project was done by me when it was only 3 months after I started studying deep learning & speech separation without a supervisor in the relevant field. Back then, I didn't know what is a power-law compression, and the correct way to validate/test the models. Now that I've spent more time on deep learning & speech since then (I also wrote a paper published at Interspeech 2020 😊), I can observe some obvious mistakes that I've made. Those issues were kindly raised by GitHub users; please refer to the Issues and Pull Requests for that. That being said, this repository can be quite unreliable, and I would like to remind everyone to use this code at their own risk (as specified in LICENSE). Unfortunately, I can't afford extra time on revising this project or reviewing the Issues / Pull Requests. Instead, I would like to offer some pointers to newer, more reliable resources: VoiceFilter-Lite: This is a newer version of VoiceFilter presented at Interspeech 2020, which is also written by Mr. Quan Wang (and his colleagues at Google). I highly recommend checking this paper, since it focused on a more realistic situation where VoiceFilter is needed. List of VoiceFilter implementation available on GitHub: In March 2019, this repository was the only available open-source implementation of VoiceFilter. However, much better implementations that deserve more attention became available across GitHub. Please check them, and choose the one that meets your demand. PyTorch Lightning: Back in 2019, I could not find a great deep-learning project template for myself, so I and my colleagues had used this project as a template for other new projects. For people who are searching for such project template, I would like to strongly recommend PyTorch Lightning. Even though I had done a lot of effort into developing my own template during 2019 (VoiceFilter -> RandWireNN -> MelNet -> MelGAN), I found PyTorch Lightning much better than my own template. Thanks for reading, and I wish everyone good health during the global pandemic situation. Best regards, Seung-won Park Unofficial PyTorch implementation of Google AI's: VoiceFilter: Targeted Voice Separation by Speaker-Conditioned Spectrogram Masking. Result Training took about 20 hours on AWS p3.2xlarge(NVIDIA V100). Audio Sample Listen to audio sample at webpage: http://swpark.me/voicefilter/ Metric | Median SDR | Paper | Ours | | ---------------------- | ----- | ---- | | before VoiceFilter | 2.5 | 1.9 | | after VoiceFilter | 12.6 | 10.2 | SDR converged at 10, which is slightly lower than paper's. Dependencies Python and packages This code was tested on Python 3.6 with PyTorch 1.0.1. Other packages can be installed by: Miscellaneous ffmpeg-normalize is used for resampling and normalizing wav files. See README.md of ffmpeg-normalize for installation. Prepare Dataset Download LibriSpeech dataset To replicate VoiceFilter paper, get LibriSpeech dataset at http://www.openslr.org/12/. train-clear-100.tar.gz(6.3G) contains speech of 252 speakers, and train-clear-360.tar.gz(23G) contains 922 speakers. You may use either, but the more speakers you have in dataset, the more better VoiceFilter will be. Resample & Normalize wav files First, unzip tar.gz file to desired folder: Next, copy utils/normalize-resample.sh to root directory of unzipped data folder. Then: Edit config.yaml Preprocess wav files In order to boost training speed, perform STFT for each files before training by: This will create 100,000(train) + 1000(test) data. (About 160G) Train VoiceFilter Get pretrained model for speaker recognition system VoiceFilter utilizes speaker recognition system (d-vector embeddings). Here, we provide pretrained model for obtaining d-vector embeddings. This model was trained with VoxCeleb2 dataset, where utterances are randomly fit to time length [70, 90] frames. Tests are done with window 80 / hop 40 and have shown equal error rate about 1%. Data used for test were selected from first 8 speakers of VoxCeleb1 test dataset, where 10 utterances per each speakers are randomly selected. Update: Evaluation on VoxCeleb1 selected pair showed 7.4% EER. The model can be downloaded at this GDrive link. Run After specifying traindir, testdir at config.yaml, run: This will create chkpt/name and logs/name at base directory(-b option, . in default) View tensorboardX Resuming from checkpoint Evaluate Possible improvments Try power-law compressed reconstruction error as loss function, instead of MSE. (See #14) Author Seungwon Park at MINDsLab (yyyyy@snu.ac.kr, swpark@mindslab.ai) License Apache License 2.0 This repository contains codes adapted/copied from the followings: utils/adabound.py from https://github.com/Luolc/AdaBound (Apache License 2.0) utils/audio.py from https://github.com/keithito/tacotron (MIT License) utils/hparams.py from https://github.com/HarryVolek/PyTorchSpeakerVerification (No License specified) utils/normalize-resample.sh from https://unix.stackexchange.com/a/216475

springframeworkguru•Mar 18, 2025

spring-ai-intro

Introduction to Spring AI This repository contains source code examples used to support my on-line courses about the Spring Framework. All Spring Framework Guru Courses Spring Framework 6 Spring Framework 6 - Beginner to Guru Hibernate and Spring Data JPA: Beginner to Guru API First Engineering with Spring Boot Introduction to Kafka with Spring Boot Spring Security: Beginner to Guru Spring Framework 5 Spring Framework 5: Beginner to Guru - Get the most modern and comprehensive course available for the Spring Framework! Join over 17,200 over Guru's in an Slack community exclusive to this course! More than 5,700 students have given this 53 hour course a 5 star review! Spring Boot Microservices with Spring Cloud Beginner to Guru - Master Microservice Architectures Using Spring Boot 2 and Cloud Based Deployments with Spring Cloud and Docker Reactive Programming with Spring Framework 5 - Keep your skills razor sharp and take a deep dive into Reactive Programming! Testing Spring Boot: Beginner to Guru - Best Selling Course Become an expert in testing Java and Spring Applications with JUnit 5, Mockito and much more! SQL SQL Beginner to Guru: MySQL Edition - SQL is a fundamental must have skill, which employers are looking for. Learn to master SQL on MySQL, the worlds most popular database! DevOps Apache Maven: Beginner to Guru - Best Selling Course Take the mystery out of Apache Maven. Learn how to use Maven to build your Java and Spring Boot projects! OpenAPI: Beginner to Guru - Master OpenAPI (formerly Swagger) to Create Specifications for Your APIs OpenAPI: Specification With Redocly Docker for Java Developers - Best Selling Course on Udemy! Learn how you can supercharge your development by leveraging Docker. Collaborate with other students in a Slack community exclusive to the course! Spring Framework DevOps on AWS - Learn how to build and deploy Spring applications on Amazon AWS! Ready for Production with Spring Boot Actuator - Learn how to leverage Spring Boot Actuator to monitor your applications running in production. Web Development with Spring Framework Mastering Thymeleaf with Spring Boot - Once you learn Thymeleaf, you'll never want to go back to using JSPs for web development! Connect with Spring Framework Guru Spring Framework Guru Blog Subscribe to Spring Framework Guru on YouTube Like Spring Framework Guru on Facebook Follow Spring Framework Guru on Twitter Connect with John Thompson on LinkedIn

#github #spring-ai-intro

Vibe Coding is Here - How AI is Changing How We Build Online

Vibe Coding is Here - How AI is Changing How We Build Online

Vibe Coding: The Future of Software Development? (with Yoko Li & Justine Moore | a16z) What if you could build an app just by describing it? That’s the idea behind vibe coding — a new AI-driven approach that’s reshaping software development for engineers and non-technical users alike. Instead of writing detailed code, users guide an AI coding agent with simple prompts like “make this look cleaner” or “I want a button that does X.” In this episode, we sit down with Yoko Li and Justine Moore from a16z to break down the rise of vibe coding, its impact on software development, and why AI-powered text-to-web tools are taking off. We explore: How vibe coding works and why it’s gaining traction The emerging companies leading the space (Cursor, Lovable, Bolt, VZero, and more) Why engineers and total beginners are both using these tools The challenges of AI-driven development (when “vibes” go wrong!) Where this trend is heading—and what it means for the future of coding From software for one to enterprise-level applications, vibe coding is opening up new possibilities for creating on the web. Tune in to learn how it’s changing the way we build. Learn more and check out everything a16z is doing, including articles, projects, and more podcasts here – https://a16z.com/ai-web-app-builders/ Follow everyone on X: Yoko Li - https://x.com/stuffyokodraws Justine Moore - https://x.com/venturetwins Steph Smith - https://x.com/stephsmithio

#github #awesome-ai-tools

0.385

0.0020930582944730723

aliammari1•Feb 21, 2025

Awesome-Ai-Tools

Awesome-Ai-Tools This repo contains AI tools that will help you achieve your goals. The tools are categorized into different sections based on their functionality. Contents Awesome-Ai-Tools Contents Productivity Time Management Task Management Email Management Creativity Art Music Writing Communication Writing Personality Analysis Translation Data Science Machine Learning Data Analysis Data Visualization Natural Language Processing Text Classification Named Entity Recognition Computer Vision Image Classification Object Detection Robotics Robot Simulation Robot Control Miscellaneous Language Models Generative Models Productivity If you're looking to boost your productivity, there are a number of AI tools that can help. Time Management RescueTime - RescueTime is an AI-powered time tracking tool that helps you understand how you're spending your time on your computer. It can help you identify areas where you're wasting time and make adjustments to your workflow to be more productive. Focus@Will - Focus@Will is an AI-powered music service that helps you stay focused and productive while you work. It uses neuroscience to create music that is scientifically optimized to help you concentrate. Clockify - Clockify is an AI-powered time tracking tool that helps you track your time across different projects and tasks. It can help you identify areas where you're spending too much time and make adjustments to your workflow to be more productive. Trello - Trello is an AI-powered task management tool that helps you stay organized and on top of your to-do list. It can help you prioritize tasks, set deadlines, and even collaborate with others on projects. Motion - Motion is an AI-powered calendar and task management tool that automatically schedules your tasks and meetings for optimal productivity. Reclaim.ai - Reclaim is an intelligent calendar assistant that helps you protect your time by automatically scheduling meetings and tasks. Task Management Todoist - Todoist is an AI-powered task management tool that helps you stay organized and on top of your to-do list. It can help you prioritize tasks, set deadlines, and even suggest tasks based on your previous activity. Asana - Asana is an AI-powered task management tool that helps you stay organized and on top of your to-do list. It can help you prioritize tasks, set deadlines, and even collaborate with others on projects. Notion - Notion is an AI-powered productivity tool that can help you manage tasks, take notes, and collaborate with others on projects. It can also be used to create wikis, databases, and other types of content. Taskade - Taskade is an AI-powered productivity tool that can manage tasks and notes for individuals and teams. ClickUp - ClickUp is an AI-enhanced project management tool that helps teams organize work with automated task distributions and smart notifications. Monday.com - Monday.com uses AI to streamline workflow management and automate routine tasks. Email Management Boomerang - Boomerang is an AI-powered email management tool that helps you manage your inbox more efficiently. It can help you schedule emails to be sent later, remind you to follow up on emails, and even suggest responses to emails. SaneBox - SaneBox is an AI-powered email management tool that helps you manage your inbox more efficiently. It can help you prioritize emails, unsubscribe from unwanted emails, and even snooze emails to be dealt with later. Mailstrom - Mailstrom is an AI-powered email management tool that helps you clean up your inbox. It can help you quickly identify and delete unwanted emails, and even unsubscribe from newsletters and other types of email subscriptions. Creativity If you're looking to get more creative, there are a number of AI tools that can help. Art Artbreeder - Artbreeder is an AI-powered tool that allows you to create unique digital art by combining different images and styles. Runway ML - Runway is an AI-powered tool that allows users to edit and generate videos using natural language descriptions. Prisma - Prisma is an AI-powered tool that allows you to transform your photos into works of art using neural networks. Music AIVA - AIVA is an AI-powered music composition tool that can help you create original music for your projects. Writing monica - Monica is a chrome extension powered by ChatGPT API. It is designed to be your personal AI assistant for effortless chatting and copywriting. CopyAI - CopyAI is an AI-powered writing assistant that can help you generate high-quality marketing copy, product descriptions, and more. Grammarly - Grammarly is an AI-powered writing assistant that helps you catch grammar and spelling errors in your writing. It can also suggest improvements to your writing style to help you communicate more effectively. Jasper - Jasper is an AI writing assistant that helps create marketing copy, blog posts, and social media content. Rytr - Rytr is an AI writing tool that helps generate content in different tones and styles. Communication If you're looking to improve your communication skills, there are a number of AI tools that can help. Writing Linguix - Linguix is an AI-powered writing assistant that can help you improve your writing skills. It can catch grammar and spelling errors, suggest improvements to your writing style, and even help you avoid plagiarism. Hemingway Editor - Hemingway Editor is an AI-powered writing tool that helps you simplify your writing and make it more readable. It can help you identify complex sentences, passive voice, and other issues that can make your writing difficult to understand. Personality Analysis Crystal - Crystal is an AI-powered tool that helps you understand the personality of the people you're communicating with. It can provide insights into their communication style and suggest ways to communicate more effectively with them. IBM Watson Personality Insights - IBM Watson Personality Insights is a tool that uses natural language processing and machine learning algorithms to analyze text and provide insights into the personality traits of the author. Translation DeepL - DeepL is an AI-powered translation tool that provides high-quality translations in multiple languages. It uses neural network algorithms to provide more accurate translations than traditional translation tools. Google Translate - Google Translate is a free online translation tool that uses machine learning algorithms to provide translations in over 100 languages. Data Science If you're working with data, there are a number of AI tools that can help you analyze and make sense of it. Machine Learning DataRobot - DataRobot is an AI-powered platform that helps you build and deploy machine learning models. It can help you automate the process of building models and make predictions based on your data. TensorFlow - TensorFlow is an open-source machine learning framework developed by Google. It can help you build and train machine learning models for a variety of applications. PyTorch - PyTorch is another open-source machine learning framework that is popular among researchers and developers. It is known for its ease of use and flexibility. H2O.ai - H2O.ai is an open-source machine learning platform that allows you to build and deploy machine learning models at scale. PyTorch3d - Pytorch 3d is an open-source library for deep learning with 3d data. Auto-sklearn - Auto-sklearn is an automated machine learning toolkit that helps find the best machine learning pipeline for your dataset. Ludwig - Ludwig is a declarative machine learning framework that makes it easy to build and train models without writing code. Data Analysis Pandas - Pandas is an open-source data analysis library for Python. It can help you manipulate and analyze data in a variety of formats, including CSV, Excel, and SQL databases. RapidMiner - RapidMiner is an AI-powered data science platform that allows you to build and deploy predictive models without writing any code. Apache Spark - Apache Spark is an open-source big data processing framework that can help you analyze large datasets in a distributed computing environment. Data Visualization Tableau - Tableau is a data visualization tool that uses AI to help you explore and understand your data. It can help you identify patterns and trends in your data that might not be immediately obvious. Plotly - Plotly is an open-source data visualization library for Python. It can help you create interactive charts and graphs that can be embedded in web pages and other applications. D3.js - D3.js is a JavaScript library for data visualization that allows you to create dynamic and interactive visualizations using web standards like HTML, CSS, and SVG. Natural Language Processing If you're interested in natural language processing, there are a number of AI tools that can help you get started. Text Classification TextBlob - TextBlob is an open-source library for processing textual data in Python. It can help you perform tasks like sentiment analysis, part-of-speech tagging, and text classification. NLTK - NLTK (Natural Language Toolkit) is another open-source library for natural language processing in Python. It can help you perform tasks like tokenization, stemming, and named entity recognition. Amazon Comprehend - Amazon Comprehend is a natural language processing service that uses machine learning to analyze text and provide insights into the content and sentiment of the text. Named Entity Recognition spaCy - spaCy is an open-source library for advanced natural language processing in Python. It can help you build applications that can understand and analyze human language. One of its key features is named entity recognition, which can identify and classify entities like people, organizations, and locations. Google Cloud Natural Language API - Google Cloud Natural Language API is a natural language processing service that can analyze text and provide insights into the sentiment, entities, and syntax of the text. Computer Vision If you're interested in computer vision, there are a number of AI tools that can help you get started. Image Classification Clarifai - Clarifai is an AI-powered image recognition tool that can help you classify images based on their content. It can recognize objects, scenes, and even specific concepts like emotions and colors. Google Cloud Vision API - Google Cloud Vision API is a computer vision service that can analyze images and provide insights into the content of the images, including objects, faces, and text. Object Detection YOLO - YOLO (You Only Look Once) is an open-source object detection system that can detect objects in real-time video streams. It is known for its speed and accuracy. Amazon Rekognition - Amazon Rekognition is a computer vision service that can analyze images and videos and provide insights into the content of the media, including objects, faces, and text. Robotics If you're interested in robotics, there are a number of AI tools that can help you get started. Robot Simulation Gazebo - Gazebo is an open-source robot simulation tool that allows you to simulate robots in a virtual environment. It can help you test and debug your robot control algorithms before deploying them on a physical robot. Webots - Webots is another open-source robot simulation tool that allows you to simulate robots in a virtual environment. It supports a wide range of robots and sensors, and can be used for both research and education. Robot Control ROS - ROS (Robot Operating System) is an open-source framework for building robotics software. It can help you build and control robots using a variety of programming languages. Miscellaneous If you're looking for AI tools that don't fit into any of the above categories, here are a few to check out: Language Models GPT-3 - GPT-3 is an AI-powered language model developed by OpenAI. It can generate human-like text, answer questions, and even write code. BERT - BERT is a language model developed by Google AI. It is trained on a massive dataset of text and code, and can be used for a variety of tasks, including natural language understanding, question answering, and text classification. LLama 2 - LLama 2 models are a collection of pretrained and fine-tuned large language models developed and released by Meta AI . These models are built upon the success of LLama 1 and provide significant improvements, including a larger scale and more extensive context. Claude - Claude is an AI assistant developed by Anthropic that excels at analysis, writing, and coding tasks. PaLM 2 - PaLM 2 is Google's next-generation language model with improved multilingual, reasoning, and coding capabilities. Generative Models StyleGAN - StyleGAN is an AI-powered generative model that can create high-quality images of faces, animals, and other objects. It is known for its ability to create realistic and diverse images. Generative Pre-trained Transformer 3 (GPT-3) - GPT-3 is an AI-powered language model developed by OpenAI. It can generate human-like text, answer questions, and even write code.

bogdanmosica•Jan 23, 2025

0.476

0.11235605711653615

noahgift•Feb 10, 2025

pragmaticai

🎓 Pragmatic AI Labs | Join 1M+ ML Engineers 🔥 Hot Course Offers: 🤖 Master GenAI Engineering - Build Production AI Systems 🦀 Learn Professional Rust - Industry-Grade Development 📊 AWS AI & Analytics - Scale Your ML in Cloud ⚡ Production GenAI on AWS - Deploy at Enterprise Scale 🛠️ Rust DevOps Mastery - Automate Everything 🚀 Level Up Your Career: 💼 Production ML Program - Complete MLOps & Cloud Mastery 🎯 Start Learning Now - Fast-Track Your ML Career 🏢 Trusted by Fortune 500 Teams Learn end-to-end ML engineering from industry veterans at PAIML.COM Pragmatic AI: An Introduction To Cloud-based Machine Learning !pai Book Resources This books was written in partnership with Pragmatic AI Labs. !alt text You can continue learning about these topics by: Foundations of Data Engineering (Specialization: 4 Courses) Publisher: Coursera + Duke Release Date: 4/1/2022 !duke-data Take the Specialization Course1: Python and Pandas for Data Engineering Course2: Linux and Bash for Data Engineering Course3: Scripting with Python and SQL for Data Engineering Course4: Web Development and Command-Line Tools in Python for Data Engineering Cloud Computing (Specialization: 4 Courses) Publisher: Coursera + Duke Release Date: 4/1/2021 Building Cloud Computing Solutions at Scale Specialization Launch Your Career in Cloud Computing. Master strategies and tools to become proficient in developing data science and machine learning (MLOps) solutions in the Cloud What You Will Learn Build websites involving serverless technology and virtual machines, using the best practices of DevOps Apply Machine Learning Engineering to build a Flask web application that serves out Machine Learning predictions Create Microservices using technologies like Flask and Kubernetes that are continuously deployed to a Cloud platform: AWS, Azure or GCP Courses in Specialization Take the Specialization Cloud Computing Foundations Cloud Virtualization, Containers and APIs Cloud Data Engineering Cloud Machine Learning Engineering and MLOps Get the latest content and updates from Pragmatic AI Labs: Subscribe to the mailing list! Taking the course AWS Certified Cloud Practitioner 2020-Real World & Pragmatic. Buying a copy of Pragmatic AI: An Introduction to Cloud-Based Machine Learning Reading book online on Safari: Online Version of Pragmatic AI: An Introduction to Cloud-Based Machine Learning, First Edition Watching 8+ Hour Video Series on Safari: Essential Machine Learning and AI with Python and Jupyter Notebook Viewing more content at noahgift.com Viewing more content at Pragmatic AI Labs Exploring related colab notebooks from Safari Online Training Learning about emerging topics in Hardware AI & Managed/AutoML Viewing more content on the Pragmatic AI Labs YouTube Channel Reading content on Pragmatic AI Medium Attend an upcoming Safari Live Training About Pragmatic AI is the first truly practical guide to solving real-world problems with contemporary machine learning, artificial intelligence, and cloud computing tools. Writing for business professionals, decision-makers, and students who aren’t professional data scientists, Noah Gift demystifies all the tools and technologies you need to get results. He illuminates powerful off-the-shelf cloud-based solutions from Google, Amazon, and Microsoft, as well as accessible techniques using Python and R. Throughout, you’ll find simple, clear, and effective working solutions that show how to apply machine learning, AI and cloud computing together in virtually any organization, creating solutions that deliver results, and offer virtually unlimited scalability. Coverage includes: Getting and configuring all the tools you’ll need Quickly and efficiently deploying AI applications using spreadsheets, R, and Python Mastering the full application lifecycle: Download, Extract, Transform, Model, Serve Results Getting started with Cloud Machine Learning Services, Amazon’s AWS AI Services, and Microsoft’s Cognitive Services API Uncovering signals in Facebook, Twitter and Wikipedia Listening to channels via Slack bots running on AWS Lambda (serverless) Retrieving data via the Twitter API and extract follower relationships Solving project problems and find highly-productive developers for data science projects Forecasting current and future home sales prices with Zillow Using the increasingly popular Jupyter Notebook to create and share documents integrating live code, equations, visualizations, and text And much more Book Chapter Juypter Notebooks Note, it is recommended to also watch companion Video Material: Essential Machine Learning and AI with Python and Jupyter Notebook Chapter 1: Introduction to Pragmatic AI Chapter 2: AI & ML Toolchain Chapter 3: Spartan AI Lifecyle Chapter 4: Cloud AI Development with Google Cloud Platform Chapter 5: Cloud AI Development with Amazon Web Services Chapter 6: Social Power NBA Chapter 7: Creating an Intelligent Slack Bot on AWS Chapter 8: Finding Project Management Insights from A Github Organization Chapter 9: Dynamically Optimizing EC2 Instances on AWS Chapter 10: Real Estate Chapter 11: Production AI for User Generated Content (UGC) License This code is released under the MIT license Text The text content of notebooks is released under the CC-BY-NC-ND license Additional Related Topics from Noah Gift His most recent books are: Pragmatic A.I.: An introduction to Cloud-Based Machine Learning (Pearson, 2018) Python for DevOps (O'Reilly, 2020). Cloud Computing for Data Analysis, 2020 Testing in Python, 2020 His most recent video courses are: Essential Machine Learning and A.I. with Python and Jupyter Notebook LiveLessons (Pearson, 2018) AWS Certified Machine Learning-Specialty (ML-S) (Pearson, 2019) Python for Data Science Complete Video Course Video Training (Pearson, 2019) AWS Certified Big Data - Specialty Complete Video Course and Practice Test Video Training (Pearson, 2019) Building A.I. Applications on Google Cloud Platform (Pearson, 2019) Pragmatic AI and Machine Learning Core Principles (Pearson, 2019) Data Engineering with Python and AWS Lambda (Pearson, 2019) His most recent online courses are: Microservices with this Udacity DevOps Nanodegree (Udacity, 2019) Command Line Automation in Python (DataCamp, 2019) AWS Certified Cloud Practitioner 2020-Real World & Pragmatic.

internet-tools-collection

Internet Tools Collection A collection of tools, website and AI for entrepreneurs, web designers, programmers and for everyone else. Content by category Artificial Intelligence Developers Design Entrepreneur Video Editing Stock videos Stock Photos Stock music Search Engine Optimization Blog Posts Resume Interviews No code website builder No code game builder Side Hustle Browser Extensions Other Students Artificial Intelligence Jasper - The Best AI Writing Assistant [](https://www.jasper.ai/) Create content 5x faster with artificial intelligence. Jasper is the highest quality AI copywriting tool with over 3,000 5-star reviews. Best for writing blog posts, social media content, and marketing copy. AutoDraw [](https://www.autodraw.com/) Fast drawing for everyone. AutoDraw pairs machine learning with drawings from talented artists to help you draw stuff fast. Rytr - Best AI Writer, Content Generator & Writing Assistant [](https://rytr.me/) Rytr is an AI writing assistant that helps you create high-quality content, in just a few seconds, at a fraction of the cost! Neevo - Neevo [](https://www.neevo.ai/) Kinetix Tech [](https://kinetix.tech/) Kinetix is a no-code 3D creation tool powered by Artificial Intelligence. The web-based platform leverages AI motion capture to convert a video into a 3D animation and lets you customize your avatars and environments. We make 3D animation accessible to every creator so they can create engaging stories. LALAL.AI: 100% AI-Powered Vocal and Instrumental Tracks Remover [](https://www.lalal.ai/) Split vocal and instrumental tracks quickly and accurately with LALAL.AI. Upload any audio file and receive high-quality extracted tracks in a few seconds. Copy.ai: Write better marketing copy and content with AI [](https://www.copy.ai/) Get great copy that sells. Copy.ai is an AI-powered copywriter that generates high-quality copy for your business. Get started for free, no credit card required! Marketing simplified! OpenAI [](https://openai.com/) OpenAI is an AI research and deployment company. Our mission is to ensure that artificial general intelligence benefits all of humanity. DALL·E 2 [](https://openai.com/dall-e-2/) DALL·E 2 is a new AI system that can create realistic images and art from a description in natural language. Steve.ai - World’s fastest way to create Videos [](https://www.steve.ai/) Steve.AI is an online Video making software that helps anyone to create Videos and animations in seconds. Octie.ai - Your A.I. ecommerce marketing assistant [](https://octie.ai/) Write emails, product descriptions, and more, with A.I. Created by Octane AI. hypnogram.xyz [](https://hypnogram.xyz/) Generate images from text descriptions using AI FakeYou. Deep Fake Text to Speech. [](https://fakeyou.com/) FakeYou is a text to speech wonderland where all of your dreams come true. Craiyon, formerly DALL-E mini [](https://www.craiyon.com/) Craiyon, formerly DALL-E mini, is an AI model that can draw images from any text prompt! Deck Rocks - Create Pictch Decks [](https://www.deck.rocks/) Writely | Using AI to Improve Your Writing [](https://www.writelyai.com/) Making the art of writing accessible to all Writesonic AI Writer - Best AI Writing Assistant [](https://writesonic.com/) Writesonic is an AI writer that's been trained on top-performing SEO content, high-performing ads, and converting sales copy to help you supercharge your writing and marketing efforts. Smart Copy - AI Copywriting Assistant | Unbounce [](https://unbounce.com/product/smart-copy/) Generate creative AI copy on-the-spot across your favourite tools Synthesia | #1 AI Video Generation Platform [](https://www.synthesia.io/) Create AI videos by simply typing in text. Easy to use, cheap and scalable. Make engaging videos with human presenters — directly from your browser. Free demo. NVIDIA Canvas: Turn Simple Brushstrokes into Realistic Images [](https://www.nvidia.com/en-us/studio/canvas/) Create backgrounds quickly, or speed up your concept exploration so you can spend more time visualizing ideas with the help of NVIDIA Canvas. Hotpot.ai - Hotpot.ai [](https://hotpot.ai/) Hotpot.ai makes graphic design and image editing easy. AI tools allow experts and non-designers to automate tedious tasks while attractive, easy-to-edit templates allow anyone to create device mockups, social media posts, marketing images, app icons, and other work graphics. Klaviyo: Marketing Automation Platform for Email & SMS [](https://www.klaviyo.com/) Klaviyo, an ecommerce marketing automation platform for email marketing and sms syncs your tech stack with your website store to scale your business. Search listening tool for market, customer & content research - AnswerThePublic [](https://answerthepublic.com/) Use our free tool to get instant, raw search insights, direct from the minds of your customers. Upgrade to a paid plan to monitor for new ways that people talk & ask questions about your brand, product or topic. Topic Mojo [](https://topicmojo.com/) Discover unique & newest queries around any topic and find what your customers are searching for. Pulling data from 50+ sources to enhance your topic research. AI Image Enlarger | Enlarge Image Without Losing Quality! [](https://imglarger.com/) AI Image Enlarger is a FREE online image enlarger that could upscale and enhance small images automatically. Make jpg/png pictures big without losing quality. Midjourney [](https://www.midjourney.com/app/) Kaedim - AI for turning 2D images to 3D models [](https://www.kaedim3d.com/webapp) AI for turning 2D images, sketches and photos to 3D models in seconds. Overdub: Ultra realistic text to speech voice cloning - Descript [](https://www.descript.com/overdub) Create a text to speech model of your voice. Try a live demo. Getting Started [](https://magenta.tensorflow.org/get-started) Resources to learn about Magenta Photosonic AI Art Generator | Create Unique Images with AI [](https://photosonic.writesonic.com/) Transform your imagination into stunning digital art with Photosonic - the AI art generator. With its creative suggestions, this Writesonic's AI image generator can help unleash your inner artist and share your creations with the world. Image Computer [](https://image.computer/) Most downloaded Instagram Captions App (+more creator tools) [](https://captionplus.app/) Join 3 Million+ Instagram Creators who use CaptionPlus to find Instagram Captions, Hashtags, Feed Planning, Reel Ideas, IG Story Design and more. Writecream - Best AI Writer & Content Generator - Writecream [](https://www.writecream.com/) Sentence Rewriter is a free tool to reword a sentence, paragraph and even entire essays in a short amount of time. Hypotenuse AI: AI Writing Assistant and Text Generator [](https://www.hypotenuse.ai/) Turn a few keywords into original, insightful articles, product descriptions and social media copy with AI copywriting—all in just minutes. Try it free today. Text to Speach Listnr: Generate realistic Text to Speech voiceovers in seconds [](https://www.listnr.tech/) AI Voiceover Generator with over 600+ voiceovers in 80+ languages, go from Text to Voice in seconds. Get started for Free! Free Text to Speech: Online, App, Software, Commercial license with Natural Sounding Voices. [](https://www.naturalreaders.com/) Free text to speech online app with natural voices, convert text to audio and mp3, for personal and commercial use Developers OverAPI.com | Collecting all the cheat sheets [](https://overapi.com/) OverAPI.com is a site collecting all the cheatsheets,all! Search Engine For Devs [](https://you.com/) Spline - Design tool for 3D web browser experiences [](https://spline.design/) Create web-based 3D browser experiences Image to HTML CSS converter. Convert image to HTML CSS with AI: Fronty [](https://fronty.com/) Fronty - Image to HTML CSS code converter. Convert image to HTML powered by AI. Sketchfab - The best 3D viewer on the web [](https://sketchfab.com/) With a community of over one million creators, we are the world’s largest platform to publish, share, and discover 3D content on web, mobile, AR, and VR. Railway [](https://railway.app/) Railway is an infrastructure platform where you can provision infrastructure, develop with that infrastructure locally, and then deploy to the cloud. JSON Crack - Crack your data into pieces [](https://jsoncrack.com/) Simple visualization tool for your JSON data. No forced structure, paste your JSON and view it instantly. Locofy.ai - ship your products 3-4x faster — with low code [](https://www.locofy.ai/) Turn your designs into production-ready frontend code for mobile apps and web. Ship products 3-4x faster with your existing design tools, tech stacks & workflows. Oh Shit, Git!?! [](https://ohshitgit.com/) Carbon | Create and share beautiful images of your source code [](https://carbon.now.sh/) Carbon is the easiest way to create and share beautiful images of your source code. GPRM : GitHub Profile ReadMe Maker [](https://gprm.itsvg.in/) Best Profile Generator, Create your perfect GitHub Profile ReadMe in the best possible way. Lots of features and tools included, all for free ! HubSpot | Software, Tools, and Resources to Help Your Business Grow Better [](https://www.hubspot.com/) HubSpot’s integrated CRM platform contains the marketing, sales, service, operations, and website-building software you need to grow your business. QuickRef.ME - Quick Reference Cheat Sheet [](https://quickref.me/) Share quick reference and cheat sheet for developers massCode | A free and open source code snippets manager for developers [](https://masscode.io/) Code snippets manager for developers, developed using web technologies. Snyk | Developer security | Develop fast. Stay secure. [](https://snyk.io/) Snyk helps software-driven businesses develop fast and stay secure. Continuously find and fix vulnerabilities for npm, Maven, NuGet, RubyGems, PyPI and more. Developer Roadmaps [](https://roadmap.sh/) Community driven roadmaps, articles, guides, quizzes, tips and resources for developers to learn from, identify their career paths, know what they don't know, find out the knowledge gaps, learn and improve. CSS Generators Get Waves – Create SVG waves for your next design [](https://getwaves.io/) A free SVG wave generator to make unique SVG waves for your next web design. Choose a curve, adjust complexity, randomize! Box Shadows [](https://box-shadow.dev/) Tridiv | CSS 3D Editor [](http://tridiv.com/) Tridiv is a web-based editor for creating 3D shapes in CSS Glassmorphism CSS Generator - Glass UI [](https://ui.glass/generator/) Generate CSS and HTML components using the glassmorphism design specifications based on the Glass UI library. Blobmaker - Make organic SVG shapes for your next design [](https://www.blobmaker.app/) Make organic SVG shapes for your next design. Modify the complexity, contrast, and color, to generate unique SVG blobs every time. Keyframes.app [](https://keyframes.app/) cssFilters.co - Custom and Instagram like photo filters for CSS [](https://www.cssfilters.co/) Visual playground for generating CSS for custom and Instagram like photo filters. Experiment with your own uploaded photo or select one from the Unsplash collection. CSS Animations Animista - CSS Animations on Demand [](https://animista.net/) Animista is a CSS animation library and a place where you can play with a collection of ready-made CSS animations and download only those you will use. Build Internal apps Superblocks | Save 100s of developer hours on internal tools [](https://www.superblocks.com/) Superblocks is the fast, easy and secure way for developers to build custom internal tools fast. Connect your databases & APIs. Drag and drop UI components. Extend with Python or Javascript. Deploy in 1-click. Secure and Monitor using your favorite tools Budibase | Build internal tools in minutes, the easy way [](https://budibase.com/) Budibase is a modern, open source low-code platform for building modern internal applications in minutes. Retool | Build internal tools, remarkably fast. [](https://retool.com/) Retool is the fast way to build internal tools. Drag-and-drop our building blocks and connect them to your databases and APIs to build your own tools, instantly. Connects with Postgres, REST APIs, GraphQL, Firebase, Google Sheets, and more. Built by developers, for developers. Trusted by startups and Fortune 500s. Sign up for free. GitHub Repositories GitHub - vasanthk/how-web-works: What happens behind the scenes when we type www.google.com in a browser? [](https://github.com/vasanthk/how-web-works) What happens behind the scenes when we type www.google.com in a browser? - GitHub - vasanthk/how-web-works: What happens behind the scenes when we type www.google.com in a browser? GitHub - kamranahmedse/developer-roadmap: Interactive roadmaps, guides and other educational content to help developers grow in their careers. [](https://github.com/kamranahmedse/developer-roadmap) Interactive roadmaps, guides and other educational content to help developers grow in their careers. - GitHub - kamranahmedse/developer-roadmap: Interactive roadmaps, guides and other educational content to help developers grow in their careers. GitHub - apptension/developer-handbook: An opinionated guide on how to become a professional Web/Mobile App Developer. [](https://github.com/apptension/developer-handbook) An opinionated guide on how to become a professional Web/Mobile App Developer. - GitHub - apptension/developer-handbook: An opinionated guide on how to become a professional Web/Mobile App Developer. ProfileMe.dev | Create an amazing GitHub profile in minutes [](https://www.profileme.dev/) ProfileMe.dev | Create an amazing GitHub profile in minutes GitHub - Kristories/awesome-guidelines: A curated list of high quality coding style conventions and standards. [](https://github.com/Kristories/awesome-guidelines) A curated list of high quality coding style conventions and standards. - GitHub - Kristories/awesome-guidelines: A curated list of high quality coding style conventions and standards. GitHub - tiimgreen/github-cheat-sheet: A list of cool features of Git and GitHub. [](https://github.com/tiimgreen/github-cheat-sheet) A list of cool features of Git and GitHub. Contribute to tiimgreen/github-cheat-sheet development by creating an account on GitHub. GitHub - andreasbm/web-skills: A visual overview of useful skills to learn as a web developer [](https://github.com/andreasbm/web-skills) A visual overview of useful skills to learn as a web developer - GitHub - andreasbm/web-skills: A visual overview of useful skills to learn as a web developer GitHub - Ebazhanov/linkedin-skill-assessments-quizzes: Full reference of LinkedIn answers 2022 for skill assessments (aws-lambda, rest-api, javascript, react, git, html, jquery, mongodb, java, Go, python, machine-learning, power-point) linkedin excel test lösungen, linkedin machine learning test LinkedIn test questions and answers [](https://github.com/Ebazhanov/linkedin-skill-assessments-quizzes) Full reference of LinkedIn answers 2022 for skill assessments (aws-lambda, rest-api, javascript, react, git, html, jquery, mongodb, java, Go, python, machine-learning, power-point) linkedin excel test lösungen, linkedin machine learning test LinkedIn test questions and answers - GitHub - Ebazhanov/linkedin-skill-assessments-quizzes: Full reference of LinkedIn answers 2022 for skill assessments (aws-lambda, rest-api, javascript, react, git, html, jquery, mongodb, java, Go, python, machine-learning, power-point) linkedin excel test lösungen, linkedin machine learning test LinkedIn test questions and answers Blockchain/Crypto Dashboards [](https://dune.com/) Blockchain ecosystem analytics by and for the community. Explore and share data from Ethereum, xDai, Polygon, Optimism, BSC and Solana for free. Introduction - The Anchor Book v0.24.0 [](https://book.anchor-lang.com/introduction/introduction.html) Crypto & Fiat Exchange Super App | Trade, Save & Spend | hi [](https://hi.com/) Buy, Trade, Send and Earn Crypto & Fiat. Deposit Bitcoin, ETH, USDT and other cryptos and start earning. Get the hi Debit Card and Multi-Currency IBAN Account. Moralis Web3 - Enterprise-Grade Web3 APIs [](https://moralis.io/) Bridge the development gap between Web2 and Web3 with Moralis’ powerful Web3 APIs. Mirror [](https://mirror.xyz/) Built on web3 for web3, Mirror’s robust publishing platform pushes the boundaries of writing online—whether it’s the next big white paper or a weekly community update. Makerdao [](https://blog.makerdao.com/) Sholi — software for Investors & Traders / Sholi MetriX [](https://sholi.io/) Sholi — software for Investors & Traders / Sholi MetriX Stock Trading Quiver Quantitative [](https://www.quiverquant.com/) Quiver Quantitative Chart Prime - The only tool you'll need for trading assets across all markets [](https://chartprime.com/) ChartPrime offers a toolkit that will take your trading game to the next level. Visit our site for a full rundown of features and helpful tutorials. Learning Hacker Rank [](https://www.hackerrank.com/) Coderbyte | Code Screening, Challenges, & Interview Prep [](https://coderbyte.com/) Improve your coding skills with our library of 300+ challenges and prepare for coding interviews with content from leading technology companies. Competitive Programming | Participate & Learn | CodeChef [](https://www.codechef.com/) Learn competitive programming with the help of CodeChef's coding competitions. Take part in these online coding contests to level up your skills Learn to Code - for Free | Codecademy [](https://www.codecademy.com/) Learn the technical skills to get the job you want. Join over 50 million people choosing Codecademy to start a new career (or advance in their current one). Free Code Camp [](https://www.freecodecamp.org/) Learn to Code — For Free Sololearn: Learn to Code [](https://www.sololearn.com/home) Join Now to learn the basics or advance your existing skills Mimo: The coding app you need to learn to code! Python, HTML, JavaScript [](https://getmimo.com/) Join more than 17 million learners worldwide. Learn to code for free. Learn Python, JavaScript, CSS, SQL, HTML, and more with our free code learning app. Free for developers [](https://free-for.dev/#/) Your Career in Web Development Starts Here | The Odin Project [](https://www.theodinproject.com/) The Odin Project empowers aspiring web developers to learn together for free Code Learning Games CheckiO - coding games and programming challenges for beginner and advanced [](https://checkio.org/) CheckiO - coding websites and programming games. Improve your coding skills by solving coding challenges and exercises online with your friends in a fun way. Exchanges experience with other users online through fun coding activities Coding for Kids | Game-Based Programming | CodeMonkey [](https://www.codemonkey.com/) CodeMonkey is a leading coding for kids program. Through its award-winning courses, millions of students learn how to code in real programming languages. Coding Games and Programming Challenges to Code Better [](https://www.codingame.com/) CodinGame is a challenge-based training platform for programmers where you can play with the hottest programming topics. Solve games, code AI bots, learn from your peers, have fun. Learn VIM while playing a game - VIM Adventures [](https://vim-adventures.com/) VIM Adventures is an online game based on VIM's keyboard shortcuts. It's the "Zelda meets text editing" game. So come have some fun and learn some VIM! CodeCombat - Coding games to learn Python and JavaScript [](https://codecombat.com/) Learn typed code through a programming game. Learn Python, JavaScript, and HTML as you solve puzzles and learn to make your own coding games and websites. Design Useberry - Codeless prototype analytics [](https://www.useberry.com/) User testing feedback & rich insights in minutes, not months! Figma: the collaborative interface design tool. [](https://www.figma.com/) Build better products as a team. Design, prototype, and gather feedback all in one place with Figma. Dribbble - Discover the World’s Top Designers & Creative Professionals [](https://dribbble.com/) Find Top Designers & Creative Professionals on Dribbble. We are where designers gain inspiration, feedback, community, and jobs. Your best resource to discover and connect with designers worldwide. Photopea | Online Photo Editor [](https://www.photopea.com/) Photopea Online Photo Editor lets you edit photos, apply effects, filters, add text, crop or resize pictures. Do Online Photo Editing in your browser for free! Toools.design – An archive of 1000+ Design Resources [](https://www.toools.design/) A growing archive of over a thousand design resources, weekly updated for the community. Discover highly useful design tools you never thought existed. All Online Tools in One Box | 10015 Tools [](https://10015.io/) All online tools you need in one box for free. Build anything online with “all-in-one toolbox”. All tools are easy-to-use, blazing fast & free. Phase - Digital Design Reinvented| Phase [](https://phase.com/) Design and prototype websites and apps visually and intuitively, in a new powerful product reworked for the digital age. Animated Backgrounds [](https://animatedbackgrounds.me/) A Collection of 30+ animated backgrounds for websites and blogs.With Animated Backgrounds, set a simple, elegant background animations on your websites and blogs. Trianglify.io · Low Poly Pattern Generator [](https://trianglify.io/) Trianglify.io is a tool for generating low poly triangle patterns that can be used as wallpapers and website assets. Cool Backgrounds [](https://coolbackgrounds.io/) Explore a beautifully curated selection of cool backgrounds that you can add to blogs, websites, or as desktop and phone wallpapers. SVG Repo - Free SVG Vectors and Icons [](https://www.svgrepo.com/) Free Vectors and Icons in SVG format. ✅ Download free mono or multi color vectors for commercial use. Search in 300.000+ Free SVG Vectors and Icons. Microcopy - Short copy text for your website. [](https://www.microcopy.me/) Search micro UX copy text: slogans, headlines, notifications, CTA, error messages, email, account preferences, and much more. 3D icons and icon paks - Free3Dicon [](https://free3dicon.com/) All 3D icons you need in one place. This is a collection of free, beautiful, trending 3D icons, that you can use in any project. Love 3D Icon [](https://free3dicons.com/) Downloads free 3D icons GIMP - GNU Image Manipulation Program [](https://www.gimp.org/) GIMP - The GNU Image Manipulation Program: The Free and Open Source Image Editor blender.org - Home of the Blender project - Free and Open 3D Creation Software [](https://www.blender.org/) The Freedom to Create 3D Design Software | 3D Modeling on the Web | SketchUp [](https://www.sketchup.com/) SketchUp is a premier 3D design software that truly makes 3D modeling for everyone, with a simple to learn yet robust toolset that empowers you to create whatever you can imagine. Free Logo Maker - Create a Logo in Seconds - Shopify [](https://www.shopify.com/tools/logo-maker) Free logo maker tool to generate custom design logos in seconds. This logo creator is built for entrepreneurs on the go with hundreds of templates, free vectors, fonts and icons to design your own logo. The easiest way to create business logos online. All your design tools in one place | Renderforest [](https://www.renderforest.com/) Time to get your brand noticed. Create professional videos, logos, mockups, websites, and graphics — all in one place. Get started now! Prompt Hero [](https://prompthero.com/) Type Scale - A Visual Calculator [](https://type-scale.com/) Preview and choose the right type scale for your project. Experiment with font size, scale and different webfonts. DreamFusion: Text-to-3D using 2D Diffusion [](https://dreamfusion3d.github.io/) DreamFusion: Text-to-3D using 2D Diffusion, 2022. The branding style guidelines documents archive [](https://brandingstyleguides.com/) Welcome to the brand design manual documents directory. Search over our worldwide style assets handpicked collection, access to PDF documents for inspiration. Super designer | Create beautiful designs with a few clicks [](https://superdesigner.co/) Create beautiful designs with a few clicks. Simple design tools to generate unique patterns, backgrounds, 3D shapes, colors & images for social media, websites and more Readymag—a design tool to create websites without coding [](https://readymag.com/) Meet the most elegant, simple and powerful web-tool for designing websites, presentations, portfolios and all kinds of digital publications. ffflux: Online SVG Fluid Gradient Background Generator | fffuel [](https://fffuel.co/ffflux/) SVG generator to make fluid gradient backgrounds that feel organic and motion-like. Perfect to add a feeling of motion and fluidity to your web designs. Generate unique SVG design assets | Haikei [](https://haikei.app/) A web-based design tool to generate unique SVG design assets for websites, social media, blog posts, desktop and mobile wallpapers, posters, and more! Our generators let you discover, customize, randomize, and export generative SVG design assets ready to use with your favorite design tools. UI/UX - Inspirational Free Website Builder Software | 10,000+ Free Templates [](https://nicepage.com/) Nicepage is your website builder software breaking limitations common for website builders with revolutionary freehand positioning. 7000+ Free Templates. Easy Drag-n-Drop. No coding. Mobile-friendly. Clean HTML. Super designer | Create beautiful designs with a few clicks [](https://superdesigner.co/) Create beautiful designs with a few clicks. Simple design tools to generate unique patterns, backgrounds, 3D shapes, colors & images for social media, websites and more Pika – Create beautiful mockups from screenshots [](https://pika.style/) Quickly create beautiful website and device mockup from screenshot. Pika lets you capture website screenshots form URL, add device and browser frames, customize background and more LiveTerm [](https://liveterm.vercel.app/) Minimal Gallery – Web design inspiration [](https://minimal.gallery/) For the love of beautiful, clean and functional websites. Awwwards - Website Awards - Best Web Design Trends [](https://www.awwwards.com/) Awwwards are the Website Awards that recognize and promote the talent and effort of the best developers, designers and web agencies in the world. Design Systems For Figma [](https://www.designsystemsforfigma.com/) A collection of Design Systems for Figma from all over the globe. Superside: Design At Scale For Ambitious Brands [](https://www.superside.com/) We are an always-on design company. Get a team of dedicated designers, speedy turnarounds, magical creative collaboration tech and the top 1% of global talent. UXArchive - Made by Waldo [](https://uxarchive.com/) UXArchive the world's largest library of mobile user flows. Be inspired to design the best user experiences. Search by Muzli [](https://search.muz.li/) Search, discover, test and create beautiful color palettes for your projects Siteinspire | Web Design Inspiration [](https://www.siteinspire.com/) SAVEE [](https://savee.it/) The best way to save and share inspiration. A little corner of the internet to find good landing page copywriting examples [](https://greatlandingpagecopy.com/) A little corner of the internet to find great landing page copywriting examples. The Best Landing Page Examples For Design Inspiration - SaaS Landing Page [](https://saaslandingpage.com/) SaaS Landing Page showcases the best landing page examples created by top-class SaaS companies. Get ideas and inspirations for your next design project. Websites Free templates Premium Bootstrap Themes and Templates: Download @ Creative Tim [](https://www.creative-tim.com/) UI Kits, Templates and Dashboards built on top of Bootstrap, Vue.js, React, Angular, Node.js and Laravel. Join over 2,014,387+ creatives to access all our products! Free Bootstrap Themes, Templates, Snippets, and Guides - Start Bootstrap [](https://startbootstrap.com/) Start Bootstrap develops free to download, open source Bootstrap 5 themes, templates, and snippets and creates guides and tutorials to help you learn more about designing and developing with Bootstrap. Free Website Templates [](https://freewebsitetemplates.com/) Get your free website templates here and use them on your website without needing to link back to us. One Page Love - One Page Website Inspiration and Templates [](https://onepagelove.com/) One Page Love is a One Page website design gallery showcasing the best Single Page websites, templates and resources. Free CSS | 3400 Free Website Templates, CSS Templates and Open Source Templates [](https://www.free-css.com/) Free CSS has 3400 free website templates, all templates are free CSS templates, open source templates or creative commons templates. Free Bootstrap Themes and Website Templates | BootstrapMade [](https://bootstrapmade.com/) At BootstrapMade, we create beautiful website templates and bootstrap themes using Bootstrap, the most popular HTML, CSS and JavaScript framework. Free and Premium Bootstrap Themes, Templates by Themesberg [](https://themesberg.com/) Free and Premium Bootstrap themes, templates, admin dashboards and UI kits used by over 38820 web developers and software companies HTML, Vue.js and React templates for startup landing pages - Cruip [](https://cruip.com/) Cruip is a gallery of premium and free HTML, Vue.js and React templates for startups and SaaS. Free Website Templates Download | WordPress Themes - W3Layouts [](https://w3layouts.com/) Want to download free website templates? W3Layouts WordPress themes and website templates are built with responsive web design techniques. Download now! Free HTML Landing Page Templates and UI Kits | UIdeck [](https://uideck.com/) Free HTML Landing Page Templates, Bootstrap Themes, React Templates, HTML Templates, Tailwind Templates, and UI Kits. Create Online Graphics Snappa - Quick & Easy Graphic Design Software [](https://snappa.com/) Snappa makes it easy to create any type of online graphic. Create & publish images for social media, blogs, ads, and more! Canva [](https://www.canva.com/) Polotno Studio - Make graphical designs [](https://studio.polotno.com) Free online design editor. Create images for social media, youtube previews, facebook covers Free Logo Maker: Design Custom Logos | Adobe Express [](https://www.adobe.com/express/create/logo) The Adobe Express logo maker is instant, intuitive, and intelligent. Use it to generate a wide range of possibilities for your own logo. Photo Editor: Fotor – Free Online Photo Editing & Image Editor [](https://www.fotor.com/) Fotor's online photo editor helps you edit photos with free online photo editing tools. Crop photos, resize images, and add effects/filters, text, and graphics in just a few clicks. Photoshop online has never been easier with Fotor's free online photo editor. VistaCreate – Free Graphic Design Software with 70,000+ Free Templates [](https://create.vista.com/) Looking for free graphic design software? Easily create professional designs with VistaCreate, a free design tool with powerful features and 50K+ ready-made templates Draw Freely | Inkscape [](https://inkscape.org/) Inkscape is professional quality vector graphics software which runs on Linux, Mac OS X and Windows desktop computers. Visual & Video Maker Trusted By 11 Million Users - Piktochart [](https://piktochart.com/) With Piktochart, you can create professional-looking infographics, flyers, posters, charts, videos, and more. No design experience needed. Start for free. The Web's Favorite Online Graphic Design Tool | Stencil [](https://getstencil.com/) Stencil is a fantastically easy-to-use online graphic design tool and image editor built for business owners, social media marketers, and bloggers. Pablo by Buffer - Design engaging images for your social media posts in under 30 seconds [](https://pablo.buffer.com/) Buffer makes it super easy to share any page you're reading. Keep your Buffer topped up and we automagically share them for you through the day. Free Online Graphic Design Software | Create stunning designs in seconds. [](https://desygner.com/) Easy drag and drop graphic design tool for anyone to use with 1000's of ready made templates. Create & print professional business cards, flyers, social posts and more. Color Pallet Color Palettes for Designers and Artists - Color Hunt [](https://colorhunt.co/) Discover the newest hand-picked color palettes of Color Hunt. Get color inspiration for your design and art projects. Coolors - The super fast color palettes generator! [](https://coolors.co/) Generate or browse beautiful color combinations for your designs. Get color palette inspiration from nature - colorpalettes.earth [](https://colorpalettes.earth/) Color palettes inspired by beautiful nature photos Color Palette Generator - Create Beautiful Color Schemes [](https://colors.muz.li/) Search, discover, test and create beautiful color palettes for your projects A Most Useful Color Picker | 0to255 [](https://0to255.com/) Find lighter and darker colors based on any color. Discover why over two million people have used 0to255 to choose colors for their website, logo, room interior, and print design projects. Colour Contrast Checker [](https://colourcontrast.cc/) Check the contrast between different colour combinations against WCAG standards Fonts Google Fonts [](https://fonts.google.com/) Making the web more beautiful, fast, and open through great typography Fonts In Use – Type at work in the real world. [](https://fontsinuse.com/) A searchable archive of typographic design, indexed by typeface, format, and topic. Wordmark - Helps you choose fonts! [](https://wordmark.it/) Wordmark helps you choose fonts by quickly displaying your text with your fonts. OH no Type Company [](https://ohnotype.co/) OH no Type Co. Retail and custom typefaces. Life’s a thrill, fonts are chill! Illustrations Illustrations | unDraw [](https://undraw.co/illustrations) The design project with open-source illustrations for any idea you can imagine and create. Create beautiful websites, products and applications with your color, for free. Design Junction [](https://designjunction.xyz/) Design Junction is a one-stop resource library for Designers and Creatives with curated list of best resources handpicked from around the web Humaaans: Mix-&-Match illustration library [](https://www.humaaans.com/) Mix-&-match illustrations of people with a design library for InVIsion Studio and Sketch. Stubborn - Free Illustrations Generator [](https://stubborn.fun/) Free illustrations generator for Figma and Sketch. Get the opportunity to design your characters using symbols and styles. Open Peeps, Hand-Drawn Illustration Library [](https://www.openpeeps.com/) Open Peeps is a hand-drawn illustration library to create scenes of people. You can use them in product illustration, marketing, comics, product states, user flows, personas, storyboarding, quinceañera invitations, or whatever you want! ⠀ Reshot | Free icons & illustrations [](https://www.reshot.com/) Design freely with instant downloads of curated SVG icons and vector illustrations. All free with commercial licensing. No attribution required. Blush: Illustrations for everyone [](https://blush.design/) Blush makes it easy to add free illustrations to your designs. Play with fully customizable graphics made by artists across the globe. Mockups Angle 4 - 5000+ Device Mockups for Figma, Sketch and XD [](https://angle.sh/) Vector mockups for iPhone, iPad, Android and Mac devices, including the new iPhone 13, Pro, Pro Max and Mini. Perfect for presenting your apps. Huge library of components, compositions, wallpapers and plugins made for Figma, Sketch and XD. Make Mockups, Logos, Videos and Designs in Seconds [](https://placeit.net/) Get unlimited downloads on all our 100K templates! You can make a logo, video, mockup, flyer, business card and social media image in seconds right from your browser. Free and premium tools for graphic designers | Lstore Graphics [](https://www.ls.graphics/) Free and premium mockups, UI/UX tools, scene creators for busy designers Logo Design & Brand Identity Platform for Entrepreneurs | Looka [](https://looka.com/) Logojoy is now Looka! Design a Logo, make a website, and create a Brand Identity you’ll love with the power of Artificial Intelligence. 100% free to use. Create stunning product mockups easily and online - Smartmockups [](https://smartmockups.com/) Smartmockups enables you to create stunning high-resolution mockups right inside your browser within one interface across multiple devices. Previewed - Free mockup generator for your app [](https://previewed.app/) Join Previewed to create stunning 3D image shots and animations for your app. Choose from hundreds of ready made mockups, or create your own. Free Design Software - Graphic Online Maker - Glorify [](https://www.glorify.com/) Create professional and high converting social media posts, ads, infographics, presentations, and more with Glorify, a free design software & graphic maker. Other BuiltWith Technology Lookup [](https://builtwith.com/) Web technology information profiler tool. Find out what a website is built with. Compress JPEG Images Online [](https://compressjpeg.com/) Compress JPEG images and photos for displaying on web pages, sharing on social networks or sending by email. PhotoRoom - Remove Background and Create Product Pictures [](https://www.photoroom.com/) Create product and portrait pictures using only your phone. Remove background, change background and showcase products. Magic Eraser - Remove unwanted things from images in seconds [](https://www.magiceraser.io/) Magic Eraser - Use AI to remove unwanted things from images in seconds. Upload an image, mark the bit you need removed, download the fixed up image. Compressor.io - optimize and compress JPEG photos and PNG images [](https://compressor.io/) Optimize and compress JPEG, PNG, SVG, GIF and WEBP images online. Compress, resize and rename your photos for free. Remove Video Background – Unscreen [](https://www.unscreen.com/) Remove the background of any video - 100% automatically, online & free! Goodbye Greenscreen. Hello Unscreen. Noun Project: Free Icons & Stock Photos for Everything [](https://thenounproject.com/) Noun Project features the most diverse collection of icons and stock photos ever. Download SVG and PNG. Browse over 5 million art-quality icons and photos. Design Principles [](https://principles.design/) An Open Source collection of Design Principles and methods Shapefest™ - A massive library of free 3D shapes [](https://www.shapefest.com/) A massive free library of beautifully rendered 3D shapes. 160,000+ high resolution PNG images in one cohesive library. Learning UX Degreeless.design - Everything I Learned in Design School [](https://degreeless.design/) This is a list of everything I've found useful in my journey of learning design, and an ongoing list of things I think you should read. For budding UX, UI, Interaction, or whatever other title designers. UX Tools | Practical UX skills and tools [](https://uxtools.co/) Lessons and resources from two full-time product designers. Built For Mars [](https://builtformars.com/) On a mission to help the world build better user experiences by demystifying UX. Thousands of hours of research packed into UX case studies. Case Study Club – Curated UX Case Study Gallery [](https://www.casestudy.club/) Case Study Club is the biggest curated gallery of the best UI/UX design case studies. Get inspired by industry-leading designers, openly sharing their UX process. The Guide to Design [](https://start.uxdesign.cc/) A self-guided class to help you get started in UX and answer key questions about craft, design, and career Uxcel - Where design careers are built [](https://app.uxcel.com/explore) Available on any device anywhere in the world, Uxcel is the best way to improve and learn UX design online in just 5 minutes per day. UI & UX Design Tips by Jim Raptis. [](https://www.uidesign.tips/) Learn UI & UX Design with practical byte-sized tips and in-depth articles from Jim Raptis. Entrepreneur Instant Username Search [](https://instantusername.com/#/) Instant Username Search checks out if your username is available on more than 100 social media sites. Results appear instantly as you type. Flourish | Data Visualization & Storytelling [](https://flourish.studio/) Beautiful, easy data visualization and storytelling PiPiADS - #1 TikTok Ads Spy Tool [](https://www.pipiads.com/) PiPiADS is the best tiktok ads spy tool .We provide tiktok advertising,advertising on tiktok,tiktok ads examples,tiktok ads library,tiktok ads best practices,so you can understand the tiktok ads cost and master the tiktok ads 2021 and tiktok ads manager. Minea - The best adspy for product search in ecommerce and dropshipping [](https://en.minea.com/) Minea is the ultimate e-commerce product search tool. Minea tracks all ads on all networks. Facebook Ads, influencer product placements, Snapspy, all networks are tracked. Stop paying adspy 149€ for one network and discover Minea. AdSpy [](https://adspy.com/) Google Trends [](https://trends.google.com/) ScoreApp: Advanced Quiz Funnel Marketing | Make a Quiz Today [](https://www.scoreapp.com/) ScoreApp makes quiz funnel marketing easy, so you can attract relevant warm leads, insightful data and increase your sales. Try for free today Mailmodo - Send Interactive Emails That Drive Conversions [](https://www.mailmodo.com/) Use Mailmodo to create and send interactive emails your customers love. Drive conversions and get better email ROI. Sign up for a free trial now. 185 Top E-Commerce Sites Ranked by User Experience Performance – Baymard Institute [](https://baymard.com/ux-benchmark) See the ranked UX performance of the 185 largest e-commerce sites in the US and Europe. The chart summarizes 50,000+ UX performance ratings. Metricool - Analyze, manage and measure your digital content [](https://metricool.com/) Social media scheduling, web analytics, link in bio and reporting. Metricool is free per live for one brand. START HERE Visualping: #1 Website change detection, monitoring and alerts [](https://visualping.io/) More than 1.5 millions users monitor changes in websites with Visualping, the No1 website change detection, website checker, webpage change monitoring and webpage change detection tool. Gumroad – Sell what you know and see what sticks [](https://gumroad.com/) Gumroad is a powerful, but simple, e-commerce platform. We make it easy to earn your first dollar online by selling digital products, memberships and more. Product Hunt – The best new products in tech. [](https://www.producthunt.com/) Product Hunt is a curation of the best new products, every day. Discover the latest mobile apps, websites, and technology products that everyone's talking about. 12ft Ladder [](https://12ft.io/) Show me a 10ft paywall, I’ll show you a 12ft ladder. namecheckr | Social and Domain Name Availability Search For Brand Professionals [](https://www.namecheckr.com/) Social and Domain Name Availability Search For Brand Professionals Excel AI Formula Generator - Excelformulabot.com [](https://excelformulabot.com/) Transform your text instructions into Excel formulas in seconds with the help of AI. Z-Library [](https://z-lib.org/) Global Print On Demand Platform | Gelato [](https://www.gelato.com/) Create and sell custom products online. With local production in 33 countries, easy integration, and 24/7 customer support, Gelato is an all-in-one platform. Freecycle: Front Door [](https://freecycle.org/) Free eBooks | Project Gutenberg [](https://www.gutenberg.org/) Project Gutenberg is a library of free eBooks. Convertio — File Converter [](https://convertio.co/) Convertio - Easy tool to convert files online. More than 309 different document, image, spreadsheet, ebook, archive, presentation, audio and video formats supported. Namechk [](https://namechk.com/) Crazy Egg Website — Optimization | Heatmaps, Recordings, Surveys & A/B Testing [](https://www.crazyegg.com/) Use Crazy Egg to see what's hot and what's not, and to know what your web visitors are doing with tools, such as heatmaps, recordings, surveys, A/B testing & more. Ifttt [](https://ifttt.com/) Also Asked [](https://alsoasked.com/) Business Name Generator - Easily create Brandable Business Names - Namelix [](https://namelix.com/) Namelix uses artificial intelligence to create a short, brandable business name. Search for domain availability, and instantly generate a logo for your new business Merch Informer [](https://merchinformer.com/) Headline Generator [](https://www.title-generator.com/) Title Generator: create 700 headlines with ONE CLICK: Content Ideas + Catchy Headlines + Ad Campaign E-mail Subject Lines + Emotional Titles. Simple - Efficient - One Click Make [](https://www.make.com/en) Create and add calculator widgets to your website | CALCONIC_ [](https://www.calconic.com/) Web calculator builder empowers you to choose from a pre-made templates or build your own calculator widgets from a scratch without any need of programming knowledge Boost Your Views And Subscribers On YouTube - vidIQ [](https://vidiq.com/) vidIQ helps you acquire the tools and knowledge needed to grow your audience faster on YouTube and beyond. Learn More Last Pass [](https://www.lastpass.com/) Starter Story: Learn How People Are Starting Successful Businesses [](https://www.starterstory.com/) Starter Story interviews successful entrepreneurs and shares the stories behind their businesses. In each interview, we ask how they got started, how they grew, and how they run their business today. How To Say No [](https://www.starterstory.com/how-to-say-no) Saying no is hard, but it's also essential for your sanity. Here are some templates for how to say no - so you can take back your life. Think with Google - Discover Marketing Research & Digital Trends [](https://www.thinkwithgoogle.com/) Uncover the latest marketing research and digital trends with data reports, guides, infographics, and articles from Think with Google. ClickUp™ | One app to replace them all [](https://clickup.com/) Our mission is to make the world more productive. To do this, we built one app to replace them all - Tasks, Docs, Goals, and Chat. The Manual [](https://manual.withcompound.com/) Wealth-planning resources for founders and startup employees Software for Amazon FBA Sellers & Walmart Sellers | Helium 10 [](https://www.helium10.com/) If you're looking for the best software for Amazon FBA & Walmart sellers on the market, check out Helium 10's capabilities online today! Buffer: All-you-need social media toolkit for small businesses [](https://buffer.com/) Use Buffer to manage your social media so that you have more time for your business. Join 160,000+ small businesses today. CPGD — The Consumer Packaged Goods Directory [](https://www.cpgd.xyz/) The Consumer Packaged Goods Directory is a platform to discover new brands and resources. We share weekly trends in our newsletter and partner with services to provide vetted, recommended platforms for our Directory brands. Jungle Scout [](https://www.junglescout.com/) BuzzSumo | The World's #1 Content Marketing Platform [](https://buzzsumo.com/) BuzzSumo powers the strategies of 500k+ marketers, with content marketing data on 8b articles, 42m websites, 300t engagements, 500k journalists & 492m questions. Login - Capital [](https://app.capital.xyz/) Raise, hold, spend, and send funds — all in one place. Marketing Pictory – Video Marketing Made Easy - Pictory.ai [](https://pictory.ai/) Pictory's powerful AI enables you to create and edit professional quality videos using text, no technical skills required or software to download. Tolstoy | Communicate with interactive videos [](https://www.gotolstoy.com/) Start having face-to-face conversations with your customers. Create Email Marketing Your Audience Will Love - MailerLite [](https://www.mailerlite.com/) Email marketing tools to grow your audience faster and drive revenue smarter. Get free access to premium features with a 30-day trial! Sign up now! Hypefury - Schedule & Automate Social Media Marketing [](https://hypefury.com/) Save time on social media while creating more value, and growing your audience faster. Schedule & automate your social media experience! Klaviyo: Marketing Automation Platform for Email & SMS [](https://www.klaviyo.com/) Klaviyo, an ecommerce marketing automation platform for email marketing and sms syncs your tech stack with your website store to scale your business. Online Email & Lead Scraper | Klean Leads [](https://www.kleanleads.com/) Klean Leads is an online email scraper & email address finder. Use it to book more appointments, get more replies, and close more sales. PhantomBuster [](https://phantombuster.com/) Call to Action Examples - 300+ CTA Phrases [](https://ctaexamples.com/) See the best CTA example in every situation covered by the library of 300+ CTA goals. Use the examples to create your own CTAs in minutes. Creative Center: one-stop creative solution for TikTok [](https://ads.tiktok.com/business/creativecenter/pc/en?from=001010) Come to get your next great idea for TikTok. Here you can find the best performing ads, viral videos, and trending hashtags across regions and verticals. Groove.cm GrooveFunnels, GrooveMail with CRM and Digital Marketing Automation Platform - Groove.cm with GrooveFunnels, GroovePages, GrooveKart [](https://groove.cm/) Groove is a website creator, page builder, sales funnel maker, membership site platform, email autoresponder, blog tool, shopping cart system, ecommerce store solution, affiliate manager, video marketing software and more apps to help build your online business. SurveyMonkey: The World’s Most Popular Free Online Survey Tool [](https://www.surveymonkey.com/) Use SurveyMonkey to drive your business forward by using our free online survey tool to capture the voices and opinions of the people who matter most to you. Video Maker | Create Videos Online | Promo.com [](https://promo.com/) Free customizable video maker to help boost your business. Video creator for ads, social media, product and explainer videos, and for anything else you need! beehiiv — The newsletter platform built for growth [](https://www.beehiiv.com/) Access the best tools available in email, helping your newsletter scale and monetize like never before. GetResponse | Professional Email Marketing for Everyone [](https://www.getresponse.com/) No matter your level of expertise, we have a solution for you. At GetResponse, it's email marketing done right. Start your free account today! Search Email Newsletter Archives : Email Tuna [](https://emailtuna.com/) Explore newsletters without subscribing. Get email design ideas, discount coupon codes and exclusive newsletters deals. Database of email newsletters archived from all over the internet. Other Tools Simplescraper — Scrape Websites and turn them into APIs [](https://simplescraper.io/) Web scraping made easy — a powerful and free Chrome extension for scraping websites in your browser, automated in the cloud, or via API. No code required. Exploding Topics - Discover the hottest new trends. [](https://explodingtopics.com/) See new market opportunities, trending topics, emerging technology, hot startups and more on Exploding Topics. Scribe | Visual step-by-step guides [](https://scribehow.com/) By capturing your process while you work, Scribe automatically generates a visual guide, ready to share with the click of a button. Get It Free – The internet's BEST place to find free stuff! [](https://getitfree.us/) The internet's BEST place to find free stuff! Inflact by Ingramer – Marketing toolkit for Instagram [](https://inflact.com/) Sell on Instagram, build your audience, curate content with the right set of tools. Free Online Form Builder & Form Creator | Jotform [](https://www.jotform.com/) We believe the right form makes all the difference. Go from busywork to less work with powerful forms that use conditional logic, accept payments, generate reports, and automate workflows. Manage Your Team’s Projects From Anywhere | Trello [](https://trello.com/en) Trello is the ultimate project management tool. Start up a board in seconds, automate tedious tasks, and collaborate anywhere, even on mobile. TikTok hashtag generator - tiktokhashtags.com [](https://tiktokhashtags.com/) Find out which are the best hashtags for your TikTok post. Create Infographics, Reports and Maps - Infogram [](https://infogram.com/) Infogram is an easy to use infographic and chart maker. Create and share beautiful infographics, online reports, and interactive maps. Make your own here. Confetto - Create Instagram content in minutes [](https://www.confet.to/) Confetto is an all-in-one social media marketing tool built for SMBs and Social Media Managers. Confetto helps you create high-quality content for your audience that maximizes your reach and engagement on social media. Design, copy-write, plan and schedule content all in one place. Find email addresses in seconds • Hunter (Email Hunter) [](https://hunter.io/) Hunter is the leading solution to find and verify professional email addresses. Start using Hunter and connect with the people that matter for your business. PlayPhrase.me: Site for cinema archaeologists. [](https://playphrase.me/) Travel and explore the world of cinema. Largest collection of video quotes from movies on the web. #1 Free SEO Tools → SEO Review Tools [](https://www.seoreviewtools.com/) SEO Review Tools: 42+ Free Online SEO Tools build with ❤! → Rank checker → Domain Authority Checker → Keyword Tool → Backlink Checker Podcastle: Seamless Podcast Recording & Editing [](https://podcastle.ai/) Podcastle is the simplest way to create professional-quality podcasts. Record, edit, transcribe, and export your content with the power of AI, in an intuitive web-based platform. Save Ads from TikTok & Facebook Ad Library - Foreplay [](https://www.foreplay.co/) The best way to save ads from TikTok Creative Center and Facebook Ad Library, Organize them into boards and share ad inspiration with your team. Supercharge your creative strategy. SiteRight - Automate Your Business [](https://www.siteright.co/) SiteRight combines the abilities of multiple online resources into a single dashboard allowing you to have full control over how you manage your business. Diffchecker - Compare text online to find the difference between two text files [](https://www.diffchecker.com/) Diffchecker will compare text to find the difference between two text files. Just paste your files and click Find Difference! Yout.com [](https://yout.com/) Yout.com allows you to record videos from YouTube, FaceBook, SoundCloud, VK and others too many formats with clipping. Intuitively easy to use, with Yout the Internet DVR, with a bit of extra. AI Content Generation | Competitor Analysis - Predis.ai [](https://predis.ai/) Predis helps brands and influencers communicate better on social media by providing AI-powered content strategy analysis, content and hashtag recommendations. Castr | #1 Live Video Streaming Solution With Video Hosting [](https://castr.io/) Castr is a live video streaming solution platform that delivers enterprise-grade live videos globally with CDN. Live event streaming, video hosting, pre-recorded live, multi stream – all in one place using Castr. Headliner - Promote your podcast, radio show or blog with video [](https://www.headliner.app/) Easily create videos to promote your podcast, radio show or blog. Share to Instagram, Facebook, Twitter, YouTube, Linkedin and anywhere video lives Create Presentations, Infographics, Design & Video | Visme [](https://www.visme.co/) Create professional presentations, interactive infographics, beautiful design and engaging videos, all in one place. Start using Visme today. Designrr - Create eBooks, Kindle books, Leadmagnets, Flipbooks and Blog posts from your content in 2 minutes [](https://designrr.io/) Upload any web page, MS Word, Video, Podcast or YouTube and it will create a stunning ebook and convert it to pdf, epub, Kindle or Flipbook. Quick and Easy to use. Full Training, 24x7 Support and Facebook Group Included. SwipeWell | Swipe File Software [](https://www.swipewell.app/) The only Chrome extension dedicated to helping you save, organize, and reference marketing examples (so you never feel stumped). Tango | Create how-to guides, in seconds [](https://www.tango.us/) Tango takes the pain out of documenting processes by automatically generating how-to guides while you work. Empower your team to do their best work. Ad Creative Bank [](https://www.theadcreativebank.com/) Get inspired by ads from across industries, learn new best practices, and start thinking creatively about your brand’s digital creative. Signature Hound • Free Email Signature and Template Generator [](https://signaturehound.com/) Our email signature generator is free and easy to use. Our customizable templates work with Gmail, Outlook, Office 365, Apple Mail and more. Organize All Of Your Marketing In One Place - CoSchedule [](https://coschedule.com/) Get more done in less time with the only work management software for marketers. B Ok - Books [](https://b-ok.xyz/categories) OmmWriter [](https://ommwriter.com/) Ommwriter Rebrandly | Custom URL Shortener, Branded Link Management, API [](https://www.rebrandly.com/) URL Shortener with custom domains. Shorten, brand and track URLs with the industry-leading link management platform. Free to try. API, Short URL, Custom Domains. Common Tools [](https://www.commontools.org/) Book Bolt [](https://bookbolt.io/) Zazzle [](https://www.zazzle.com/) InspiroBot [](https://inspirobot.me/) Download Free Cheat Sheets or Create Your Own! - Cheatography.com: Cheat Sheets For Every Occasion [](https://cheatography.com/) Find thousands of incredible, original programming cheat sheets, all free to download. No Code Chatbot Platform | Free Chatbot Platform | WotNot [](https://wotnot.io/) WotNot is the best no code chatbot platform to build AI bot easily without coding. Deploy bots and live chat on the Website, Messenger, WhatsApp, and more. SpyFu - Competitor Keyword Research Tools for Google Ads PPC & SEO [](https://www.spyfu.com/) Systeme.io - The only tool you need to launch your online business [](https://systeme.io/) Systeme.io has all the tools you need to grow your online business. Click here to create your FREE account! Productivity Temp Mail [](https://temp-mail.org/en/) The Visual Collaboration Platform for Every Team | Miro [](https://miro.com/) Scalable, secure, cross-device and enterprise-ready team collaboration whiteboard for distributed teams. Join 35M+ users from around the world. Grammarly: Free Online Writing Assistant [](https://www.grammarly.com/) Millions trust Grammarly’s free writing app to make their online writing clear and effective. Getting started is simple — download Grammarly’s extension today. Rize · Maximize Your Productivity [](https://rize.io/) Rize is a smart time tracker that improves your focus and helps you build better work habits. Motion | Manage calendars, meetings, projects & tasks in one app [](https://www.usemotion.com/) Automatically prioritize tasks, schedule meetings, and resolve calendar conflicts. Used by over 10k CEOs and professionals to improve focus, get more done, and streamline workday. Notion – One workspace. Every team. [](https://www.notion.so/) We’re more than a doc. Or a table. Customize Notion to work the way you do. Loom: Async Video Messaging for Work | Loom [](https://www.loom.com/) Record your screen, share your thoughts, and get things done faster with async video. Zapier | Automation that moves you forward [](https://zapier.com/) Workflow automation for everyone. Zapier automates your work across 5,000+ app integrations, so you can focus on what matters. Rows — The spreadsheet with superpowers [](https://rows.com/) Combine the power of a spreadsheet with built-in integrations from your business apps. Automate workflows and build tools that make work simpler. Free Online Form Builder | Tally [](https://tally.so/) Tally is the simplest way to create free forms & surveys. Create any type of form in seconds, without knowing how to code, and for free. Highbrow | Learn Something New Every Day. Join for Free! [](https://gohighbrow.com/) Highbrow helps you learn something new every day with 5-minute lessons delivered to your inbox every morning. Join over 400,000 lifelong learners today! Slick Write | Check your grammar. Proofread online. [](https://www.slickwrite.com/#!home) Slick Write is a powerful, FREE application that makes it easy to check your writing for grammar errors, potential stylistic mistakes, and other features of interest. Whether you're a blogger, novelist, SEO professional, or student writing an essay for school, Slick Write can help take your writing to the next level. Reverso [](https://www.reverso.net) Hemingway Editor [](https://hemingwayapp.com/) Web Apps by 123apps - Edit, Convert, Create [](https://123apps.com/) Splitbee – Your all-in-one analytics and conversion platform [](https://splitbee.io/) Track and optimize your online business with Splitbee. Analytics, Funnels, Automations, A/B Testing and more. PDF Tools Free PDF, Video, Image & Other Online Tools - TinyWow [](https://tinywow.com/) Smallpdf.com - A Free Solution to all your PDF Problems [](https://smallpdf.com/) Smallpdf - the platform that makes it super easy to convert and edit all your PDF files. Solving all your PDF problems in one place - and yes, free. Sejda helps with your PDF tasks [](https://www.sejda.com/) Sejda helps with your PDF tasks. Quick and simple online service, no installation required! Split, merge or convert PDF to images, alternate mix or split scans and many other. iLovePDF | Online PDF tools for PDF lovers [](https://www.ilovepdf.com/) iLovePDF is an online service to work with PDF files completely free and easy to use. Merge PDF, split PDF, compress PDF, office to PDF, PDF to JPG and more! Text rewrite QuillBot [](https://quillbot.com/) Pre Post SEO : Online SEO Tools [](https://www.prepostseo.com/) Free Online SEO Tools: plagiarism checker, grammar checker, image compressor, website seo checker, article rewriter, back link checker Wordtune | Your personal writing assistant & editor [](https://www.wordtune.com/) Wordtune is the ultimate AI writing tool that rewrites, rephrases, and rewords your writing! Trusted by over 1,000,000 users, Wordtune strengthens articles, academic papers, essays, emails and any other online content. Aliexpress alternatives CJdropshipping - Dropshipping from Worldwide to Worldwide! [](https://cjdropshipping.com/) China's reliable eCommerce dropshipping fulfillment supplier, helps small businesses ship worldwide, dropship and fulfillment services that are friendly to start-ups and small businesses, Shopify dropshipping. SaleHoo [](https://www.salehoo.com/) Alibaba.com: Manufacturers, Suppliers, Exporters & Importers from the world's largest online B2B marketplace [](https://www.alibaba.com/) Find quality Manufacturers, Suppliers, Exporters, Importers, Buyers, Wholesalers, Products and Trade Leads from our award-winning International Trade Site. Import & Export on alibaba.com Best Dropshipping Suppliers for US + EU Products | Spocket [](https://www.spocket.co/) Spocket allows you to easily start dropshipping top products from US and EU suppliers. Get started for free and see why Spocket consistently gets 5 stars. Best dropshipping supplier to the US [](https://www.usadrop.com/) THE ONLY AMERICAN-MADE FULFILLMENT CENTER IN CHINA. Our knowledge of the Worldwide dropshipping market and the Chinese Supply-Chain can't be beat! 阿里1688 [](https://www.1688.com/) 阿里巴巴（1688.com）是全球企业间（B2B）电子商务的著名品牌，为数千万网商提供海量商机信息和便捷安全的在线交易市场，也是商人们以商会友、真实互动的社区平台。目前1688.com已覆盖原材料、工业品、服装服饰、家居百货、小商品等12个行业大类，提供从原料--生产--加工--现货等一系列的供应产品和服务 Dropshipping Tools Oberlo | Where Self Made is Made [](https://www.oberlo.com/) Start selling online now with Shopify. All the videos, podcasts, ebooks, and dropshipping tools you'll need to build your online empire. Klaviyo: Marketing Automation Platform for Email & SMS [](https://www.klaviyo.com/) Klaviyo, an ecommerce marketing automation platform for email marketing and sms syncs your tech stack with your website store to scale your business. SMSBump | SMS Marketing E-Commerce App for Shopify [](https://smsbump.com/) SMSBump is an SMS marketing & automation app for Shopify. Segment customers, recover orders, send campaign text messages with a 35%+ click through rate. AfterShip: The #1 Shipment Tracking Platform [](https://www.aftership.com/) Order status lookup, branded tracking page, and multi-carrier tracking API for eCommerce. Supports USPS, FedEx, UPS, and 900+ carriers worldwide. #1 Dropshipping App | Zendrop [](https://zendrop.com/) Start and scale your own dropshipping business with Zendrop. Sell and easily fulfill your orders with the fastest shipping in the industry. Best Dropshipping Suppliers for US + EU Products | Spocket [](https://www.spocket.co/) Spocket allows you to easily start dropshipping top products from US and EU suppliers. Get started for free and see why Spocket consistently gets 5 stars. Video Editing Jitter • The simplest motion design tool on the web. [](https://jitter.video/) Animate your designs easily. Export your creations as videos or GIFs. All in your browser. DaVinci Resolve 18 | Blackmagic Design [](https://www.blackmagicdesign.com/products/davinciresolve) Professional video editing, color correction, visual effects and audio post production all in a single application. Free and paid versions for Mac, Windows and Linux. Online Video Editor | Video Creator | InVideo [](https://invideo.io/) InVideo's Online Video Editor Helps You Make Professional Videos From Premium Templates, Images, And Music. All your video needs in one place | Clipchamp [](https://clipchamp.com/) Fast-forward your creations with our video editing platform. Start with a video template or record your webcam or screen. Get the pro look with filters, transitions, text and more. Then, export in minutes and share in an instant. Descript | All-in-one audio/video editing, as easy as a doc. [](https://www.descript.com/) Record, transcribe, edit, mix, collaborate, and master your audio and video with Descript. Download for free →. Kapwing — Reach more people with your content [](https://www.kapwing.com/) Kapwing is a collaborative, online content creation platform that you can use to edit video and create content. Join over 10 million modern creators who trust Kapwing to create, edit, and grow their content on every channel. Panzoid [](https://panzoid.com/) Powerful, free online apps and community for creating beautiful custom content. Google Web Designer - Home [](https://webdesigner.withgoogle.com/) Kapwing — Reach more people with your content [](https://www.kapwing.com/) Kapwing is a collaborative, online content creation platform that you can use to edit video and create content. Join over 10 million modern creators who trust Kapwing to create, edit, and grow their content on every channel. ClipDrop [](https://clipdrop.co/) Create professional visuals without a photo studio CapCut [](https://www.capcut.com/) CapCut is an all-in-one online video editing software which makes creation, upload & share easier, with frame by frame track editor, cloud drive etc. VEED - Online Video Editor - Video Editing Made Simple [](https://www.veed.io/) Make stunning videos with a single click. Cut, trim, crop, add subtitles and more. Online, no account needed. Try it now, free. VEED Free Video Maker | Create & Edit Your Videos Easily - Animoto [](https://animoto.com/k/welcome) Create, edit, and share videos with our online video maker. Combine your photos, video clips, and music to make quality videos in minutes. Get started free! Runway - Online Video Editor | Everything you need to make content, fast. [](https://runwayml.com/) Discover advanced video editing capabilities to take your creations to the next level. CreatorKit - A.I. video creator for marketers [](https://creatorkit.com/) Create videos with just one click, using our A.I. video editor purpose built for marketers. Create scroll stopping videos, Instagram stories, Ads, Reels, and TikTok videos. Pixar in a Box | Computing | Khan Academy [](https://www.khanacademy.org/computing/pixar) 3D Video Motions Plask - AI Motion Capture and 3D Animation Tool [](https://plask.ai/) Plask is an all-in-one browser-based AI motion capture tool and animation editor that anybody can use, from motion designers to every day content creators. Captions Captions [](https://www.getcaptions.app/) Say hello to Captions, the only camera and editing app that automatically transcribes, captions and clips your talking videos for you. Stock videos Pexels [](https://www.pexels.com/) Pixabay [](https://pixabay.com/) Mixkit - Awesome free assets for your next video project [](https://mixkit.co/) Download Free Stock Video Footage, Stock Music & Premiere Pro Templates for your next video editing project. All assets can be downloaded for free! Free Stock Video Footage HD 4K Download Royalty-Free Clips [](https://www.videvo.net/) Download free stock video footage with over 300,000 video clips in 4K and HD. We also offer a wide selection of music and sound effect files with over 180,000 clips available. Click here to download royalty-free licensing videos, motion graphics, music and sound effects from Videvo today. Free Stock Video Footage HD Royalty-Free Videos Download [](https://mazwai.com/) Download free stock video footage with clips available in HD. Click here to download royalty-free licensing videos from Mazwai now. Royalty Free Stock Video Footage Clips | Vidsplay.com [](https://www.vidsplay.com/) Royalty Free Stock Video Footage Clips Free Stock Video Footage, Royalty Free Videos for Download [](https://coverr.co/) Download royalty free (for personal and commercial use), unique and beautiful video footage for your website or any project. No attribution required. Stock Photos Beautiful Free Images & Pictures | Unsplash [](https://unsplash.com/) Beautiful, free images and photos that you can download and use for any project. Better than any royalty free or stock photos. When we share, everyone wins - Creative Commons [](https://creativecommons.org/) Creative Commons licenses are 20! Honoring 20 years of open sharing using CC licenses, join us in 2022 to celebrate Better Sharing — advancing universal access to knowledge and culture, and fostering creativity, innovation, and collaboration. Help us reach our goal of raising $15 million for a future of Better Sharing. 20 Years of Better … Read More "When we share, everyone wins" Food Pictures • Foodiesfeed • Free Food Photos [](https://www.foodiesfeed.com/) Download 2000+ food pictures ⋆ The best free food photos for commercial use ⋆ CC0 license Free Stock Photos and Images for Websites & Commercial Use [](https://burst.shopify.com/) Browse thousands of beautiful copyright-free images. All our pictures are free to download for personal and commercial use, no attribution required. EyeEm | Authentic Stock Photography and Royalty-Free Images [](https://www.eyeem.com/) Explore high-quality, royalty-free stock photos for commercial use. License individual images or save money with our flexible subscription and image pack plans. picjumbo: Free Stock Photos [](https://picjumbo.com/) Free stock photos and images for your projects and websites.️ Beautiful 100% free high-resolution stock images with no watermark. Free Stock Photos, Images, and Vectors [](https://www.stockvault.net/) 139.738 free stock photos, textures, backgrounds and graphics for your next project. No attribution required. Free Stock Photos, PNGs, Templates & Mockups | rawpixel [](https://www.rawpixel.com/) Free images, PNGs, stickers, backgrounds, wallpapers, graphic templates and PSD mockups. All safe to use with commercial licenses. Free Commercial Stock Photos & Royalty Free Images | PikWizard [](https://pikwizard.com/) Free images, videos & free stock photos. Unlimited downloads ✓ Royalty-free Images ✓Copyright-free for commercial use ✓ No Attribution Required Design Bundles [](https://designbundles.net/) Stock music Royalty Free Music for video creators | Epidemic Sound [](https://www.epidemicsound.com/) Download premium Royalty free Music and SFX! Our free trial gives you access to over 35,000 tracks and 90,000 sound effects for video, streaming and more! Royalty-Free Music & SFX for Video Creators | Artlist [](https://artlist.io/) Explore the ultimate royalty-free music & sound effects catalogs for unlimited use in YouTube videos, social media & films created by inspiring indie artists worldwide. The go-to music licensing choice for all creators Royalty Free Audio Tracks - Envato Elements [](https://elements.envato.com/audio) Download Royalty Free Stock Audio Tracks for your next project from Envato Elements. Premium, High Quality handpicked Audio files ideal for any genre. License popular music for videos • Lickd [](https://lickd.co/) The only place you can license popular music for videos. Access 1M+ mainstream tracks, plus high-quality stock music for content creators NCS (NoCopyrightSounds) - free music for content creators [](https://ncs.io/) NCS is a Record Label dedicated to giving a platform to the next generation of Artists in electronic music, representing genres from house to dubstep via trap, drum & bass, electro pop and more. Search Engine Optimization Keyword Tool For Monthly Search Volume, CPC & Competition [](https://keywordseverywhere.com/) Keywords Everywhere is a browser add-on for Chrome & Firefox that shows search volume, CPC & competition on multiple websites. Semrush - Online Marketing Can Be Easy [](https://www.semrush.com/) Turn the algorithm into a friend. Make your business visible online with 55+ tools for SEO, PPC, content, social media, competitive research, and more. DuckDuckGo — Privacy, simplified. [](https://duckduckgo.com/) The Internet privacy company that empowers you to seamlessly take control of your personal information online, without any tradeoffs. SEO Software for 360° Analysis of Your Website [](https://seranking.com/) Leading SEO software for business owners, agencies, and SEO specialists. Track your rankings, monitor competitors, spot technical errors, and more. Skyrocket your organic traffic with Surfer [](https://surferseo.com/) Use Surfer to research, write, optimize, and audit! Everything you need to create a comprehensive content strategy that yields real results is right here. Ahrefs - SEO Tools & Resources To Grow Your Search Traffic [](https://ahrefs.com/) You don't have to be an SEO pro to rank higher and get more traffic. Join Ahrefs – we're a powerful but easy to learn SEO toolset with a passionate community. Neon Tools [](https://neontools.io/) Google Index Search [](https://lumpysoft.com/) Google Index Search SEO Backlink Checker & Link Building Toolset | Majestic.com [](https://majestic.com/) Develop backlink strategies with our Link Intelligence data, build the strongest SEO backlink campaigns to drive organic traffic and boost your rankings today. PageOptimizer Pro [](https://pageoptimizer.pro/) Plans Services SEO Consulting Learn SEO About Blog POP SEO Community Podcast Support POP On Page Workshops With Kyle Roof POP Chrome Extension Guide Tutorial Videos Frequently Asked Questions Best Practices Login Cancel Anytime Plans Services SEO Consulting Learn SEO About Blog POP SEO Community Podcast Support POP On Page… Keyword Chef - Keywords for Publishers [](https://keywordchef.com/) Rank Insanely Fast for Keywords Your Competition Can’t Find “Every long-tail keyword I find ends up ranking within a day” – Dane Eyerly, Owner at TextGoods.com Keyword Chef automatically finds and filters keywords for you. Real-time SERP analysis lets you find keywords nearly guaranteed to rank. Try for free → Let’s face it, most keyword tools ... Read more Notifier - Social Listening for Social Media and More! [](https://notifier.so/) Track keywords. Market your product for free. Drive the conversation. Easy. Free Trial. No obligation ever. Simple. Fast. Trusted by Top Companies. Free Keyword Research Tool from Wordtracker [](https://www.wordtracker.com/) The best FREE alternative to the Keyword Planner. Use Wordtracker to reveal 1000s of profitable longtail keywords with up to 10,000 results per search Blog Posts The 60 Hottest Front-end Tools of 2021 | CSS-Tricks - CSS-Tricks [](https://css-tricks.com/hottest-front-end-tools-in-2021/) A complete list of the most popular front-end tools in 2021, according to the Web Tools Weekly newsletter. See which resources made the list. Resume ResumeGlow - AI Powered Resume Builder [](https://resumeglow.com/) Get hired fast with a resume that grabs attention. Designed by a team of HR experts and typographers. Customizable templates with more than a million possible Create Your Job-winning Resume - (Free) Resume maker · Resume.io [](https://resume.io/) Free online resume maker, allows you to create a perfect Resume or Cover Letter in 5 minutes. See how easy it is to write a professional resume - apply for jobs today! Rezi - The Leading AI-Powered Free Resume Builder [](https://www.rezi.ai/) Rezi’s award-winning AI-powered resume builder is trusted by hundreds of thousands of job seekers. Create your perfect resume in minutes with Rezi. Create a Perfect Resume | Free Resume Builder | Resumaker.ai [](https://resumaker.ai/) Create your professional resume with this online resume maker. Choose a designer-made template and grab any employer attention in seconds. Trusted AI Resume Maker Helps You Get Hired Fast [](https://skillroads.com/) Reach a 96.4% success rate in the job hunt race with the best resume creator. Our innovative technologies and 24/7 support help you to become a perfect candidate for any job. Do not lose your chance to become the One. Kickresume | Best Online Resume & Cover Letter Builder [](https://www.kickresume.com/) Create your best resume yet. Online resume and cover letter builder used by 1,300,000 job seekers worldwide. Professional templates approved by recruiters. ResumeMaker.Online | Create a Professional Resume for Free [](https://www.resumemaker.online/) Save time with the easiest-to-use Resume Maker Online. Create an effective resume in just minutes and land your dream job. No Sign-up required, start now! Interviews Interview Warmup - Grow with Google [](https://grow.google/certificates/interview-warmup/) A quick way to prepare for your next interview. Practice key questions, get insights about your answers, and get more comfortable interviewing. No code website builder Carrd - Simple, free, fully responsive one-page sites for pretty much anything [](https://carrd.co/) A free platform for building simple, fully responsive one-page sites for pretty much anything. Webflow: Create a custom website | No-code website builder [](https://webflow.com/) Create professional, custom websites in a completely visual canvas with no code. Learn how to create a website by trying Webflow for free! Google Sites: Sign-in [](https://sites.google.com/) FlutterFlow - Build beautiful, modern apps incredibly fast! [](https://flutterflow.io/) FlutterFlow lets you build apps incredibly fast in your browser. Build fully functional apps with Firebase integration, API support, animations, and more. Export your code or even easier deploy directly to the app stores! Free Website Builder: Build a Free Website or Online Store | Weebly [](https://www.weebly.com/) Weebly’s free website builder makes it easy to create a website, blog, or online store. Find customizable templates, domains, and easy-to-use tools for any type of business website. Glide • No Code App Builder • Nocode Application Development [](https://www.glideapps.com/) Create the apps your business needs, without coding, waiting or overpaying. Get started for free and build an app today Adalo - Build Your Own No Code App [](https://www.adalo.com/) Adalo makes creating apps as easy as putting together a slide deck. Turn your idea into a real native app — no code needed! Siter.io - The collaborative web design tool, no-code website builder [](https://siter.io/) Siter.io is a visual website builder for designers. Prototype, design, and create responsive websites in the browser. Work together with your team in one place. Elementor: #1 Free WordPress Website Builder | Elementor.com [](https://elementor.com/) Elementor is the platform web creators choose to build professional WordPress websites, grow their skills, and build their business. Start for free today! No code app builder | Bravo Studio [](https://www.bravostudio.app/) Your no-code mobile app builder for iOS and Android. Create MVP’s, validate ideas and publish on App Store and Google Play Store. Home [](https://typedream.com/) The simplest way to build a website with no-code, as easy as writing on Notion. Try Typedream for free and upgrade for custom domains, collaborators, and unlimited pages. Free Website Builder | Create a Free Website | Wix.com [](https://www.wix.com/) Create a website with Wix’s robust website builder. With 900+ strategically designed templates and advanced SEO and marketing tools, build your brand online today. Free responsive Emails & Landing Pages drag-and-drop Editor | BEE [](https://beefree.io/) Free responsive emails and landing pages editor. With BEE drag-and-drop builders embedded in many software applications you can start designing now! Home [](https://typedream.com/) The simplest way to build a website with no-code, as easy as writing on Notion. Try Typedream for free and upgrade for custom domains, collaborators, and unlimited pages. Ownit Connected Checkout [](https://www.ownit.co/) Ownit Connected Checkout Bookmark.com | No-code Website Builder to Start Your Business [](https://www.bookmark.com/) Our AI powered platform ensures your business is future proof. Try Bookmark for free. The best way to build web apps without code | Bubble [](https://bubble.io/) Bubble introduces a new way to build software. It’s a no-code tool that lets you build SaaS platforms, marketplaces and CRMs without code. Bubble hosts all web apps on its cloud platform. Responsive Web Design | Website Creation | Editor X [](https://www.editorx.com/) Experience the future of website design with responsive layouts, CSS precision and smooth drag and drop. Create a Website for Free. Tilda Website Builder [](https://tilda.cc/) Create a website, online store, landing page with Tilda intuitive website builder. Build your site from hundreds of pre-designed templates and publish it today. No code required. No-code headless commerce and websites | Unstack Inc. [](https://www.unstack.com/) Deploy high performance eCommerce storefronts and websites without the engineering overhead using Unstack's no-code CMS Best Drag-and-Drop Website Builder | Jemi [](https://jemi.so/) The modern website builder for creatives, entrepreneurs, and dreamers. Build a beautiful link in bio site, portfolio, or landing page in minutes. No-code website builder that works like Notion [](https://popsy.co/) Create a beautiful no-code website in minutes. Popsy works just like Notion but is built from the ground up for building websites. Choose a free template. Edit content just like in Notion. Customize styles without code. Free Notion icons and illustrations. Unbounce - The Landing Page Builder & Platform [](https://unbounce.com/) Grow your relevance, leads, and sales with Unbounce. Use Unbounce to easily create and optimize landing pages for your small business and boost conversions with AI insights. Low-code Front-end Design & Development Platform | TeleportHQ [](https://teleporthq.io/) Front-end development platform, with a visual builder and headless content modelling capabilities. Static website creation, and UI development tools. Other tools used in no code website MemberSpace - Turn any part of your website into members-only with just a few clicks [](https://www.memberspace.com/) Create memberships on your website for anything you want like courses, video tutorials, member directories, and more while having 100% control over look & feel. Triggre | The number one true no-code platform to run your business [](https://www.triggre.com/) The best no-code platform to create highly advanced business applications in hours, without programming. Try it now for free! No code game builder Welcome to Buildbox [](https://signup.buildbox.com/) Welcome to Buildbox Flowlab Game Creator - Make games online [](https://flowlab.io/) Flowlab is an online game creator. Make your own games to share with friends. Make 2D Games With GameMaker | Free Video Game Maker [](https://gamemaker.io/) Make a game with GameMaker, the best free video game engine. Perfect for beginners and professionals. Learn to build your own 2D games with our simple tutorials. Side Hustle Side Hustle Stack [](https://sidehustlestack.co/) Side Hustle Stack is a resource for finding platform-based work, ranging from gig work and side hustles to platforms that help you start a small business that can grow. Fiverr [](https://www.fiverr.com/) Remotasks: Work From Home, Online Bootcamp Training [](https://www.remotasks.com/en) Make money doing tasks. Start earning today! Free bootcamp training offered online. Sign up for a free Remotasks account and work from home. Earn up to $200/month. Transcribe Speech to Text | Rev [](https://www.rev.com/) Transcribe Speech to Text with Rev. Reach your audience with clear and accurate captions, transcripts, and subtitles. AI Training Data and other Data Management Services [](https://www.clickworker.com/) AI training data, SEO texts, web research, tagging, surveys and more - Use the crowdsourcing principle with the power of >4.5M Clickworkers. Automate your Busy Work - Byron People-Powered Assistants [](https://www.hibyron.com/) Byron is an on demand US based virtual assistant platform that gives individuals and teams the ability to quickly outsource their non-essential tasks. Jobs Websites - Remote Latest Crypto Jobs, Web3 Jobs and Blockchain Jobs in the leading tech companies. [](https://cryptojobslist.com/) New Cryptocurrency Jobs, Web3 Jobs and Blockchain Jobs on CryptoJobsList — the leading site to find and post jobs. Connect with companies hiring in a few clicks and begin your next experience in the industry. Updated daily. Remote Jobs: Design, Marketing, Programming, Writing & More [](https://justremote.co/) Discover Remote Jobs from around the world. Give up the commute, work remotely and do what you love, daily, from anywhere. Find your perfect remote development, design, sales or marketing job today. Remote Ok [](https://remoteok.com/) Hire Freelancers & Remote Workers For Free [](https://talent.hubstaff.com/) Find and hire the highest quality freelancers from around the world - for free. Choose from thousands of developers, digital marketers, creatives and more. We Work Remotely: Remote jobs in design, programming, marketing and more [](https://weworkremotely.com/) Find the most qualified people in the most unexpected places: Hire remote! We Work Remotely is the best place to find and list remote jobs that aren't restricted by commutes or a particular geographic area. Browse thousands of remote work jobs today. Angel [](https://angel.co/) Remote Work: Jobs, Companies & Virtual Teams - Remote.co [](https://remote.co/) Remote.co is the definitive remote work job board for online job seekers and companies hiring. Start your remote job search here! FlexJobs: Best Remote Jobs, Work from Home Jobs, Online Jobs & More [](https://www.flexjobs.com/) The #1 job search site for hand-screened flexible and remote jobs (work from home jobs) since 2007. Plus get resume, coaching and career help. Join today! Remote jobs remotefront.io [](https://remotefront.io/) All remote jobs at remotefront.io Daily Virtual Events Helping You Grow Professionally [](https://powertofly.com/) PowerToFly is where you receive expert career advice, free video training, coaching and exclusive access to jobs and events at top companies. Best Remote and Work from Home Jobs - Virtual Vocations [](https://www.virtualvocations.com/) Best work from home jobs and remote jobs in over 50 categories for professionals, digital nomads, telecommuting workers and entry level jobseekers. Education, healthcare, medical, customer support and tech job openings. Remote Jobs | Working Nomads [](https://www.workingnomads.com/jobs) Remote jobs for digital working nomads. Start your telecommuting career and work remotely from home or places around the world. Job Search, Companies Hiring Near Me, and Advice | The Muse [](https://www.themuse.com/) Find jobs at the best companies hiring near you and get free career advice. Startupers [](https://www.startupers.com/) NoDesk - Where Everyone Works Remote [](https://nodesk.co/) Browse and apply to the best new remote jobs at leading remote companies and startups for free. Join hundreds of companies that use NoDesk to build their remote teams. Browser Extensions Blackbox - Select. Copy. Paste & Search - Magazinul web Chrome [](https://chrome.google.com/webstore/detail/blackbox-select-copy-past/mcgbeeipkmelnpldkobichboakdfaeon) Fastest Way to Copy Text from Videos & Images Octotree - GitHub code tree - Magazinul web Chrome [](https://chrome.google.com/webstore/detail/octotree-github-code-tree/bkhaagjahfmjljalopjnoealnfndnagc) GitHub on steroids WhatFont - Chrome Web Store [](https://chrome.google.com/webstore/detail/whatfont/jabopobgcpjmedljpbcaablpmlmfcogm?hl=en) The easiest way to identify fonts on web pages. Window Resizer - Chrome Web Store [](https://chrome.google.com/webstore/detail/window-resizer/kkelicaakdanhinjdeammmilcgefonfh?hl=en) Resize the browser window to emulate various screen resolutions. Amino: CSS Editor - Magazinul web Chrome [](https://chrome.google.com/webstore/detail/amino-css-editor/pbcpfbcibpcbfbmddogfhcijfpboeaaf) Live CSS Editor. Write custom CSS for any website and see your changes in real time. Checkbot: SEO, Web Speed & Security Tester 🚀 - Chrome Web Store [](https://chrome.google.com/webstore/detail/checkbot-seo-web-speed-se/dagohlmlhagincbfilmkadjgmdnkjinl?hl=en) Test SEO/speed/security of 100s of pages in a click! Check broken links, HTML/JavaScript/CSS, URL redirects, duplicate titles... Honey: Automatic Coupons & Rewards - Magazinul web Chrome [](https://chrome.google.com/webstore/detail/honey-automatic-coupons-r/bmnlcjabgnpnenekpadlanbbkooimhnj) Save money and earn rewards when you shop online. Tango: screenshots, training, & documentation - Magazinul web Chrome [](https://chrome.google.com/webstore/detail/tango-screenshots-trainin/lggdbpblkekjjbobadliahffoaobaknh) Automatically create beautiful step-by-step guides with screenshots, in seconds. No code browser automation | axiom.ai [](https://axiom.ai/) Build browser bots quickly, without code. Automate website actions and repetitive tasks using just your browser, on any website or web app. No Code Browser extensions builder Bildr - Visual Web Development in your Browser [](https://www.bildr.com/) Visually build SaaS products, Chrome extensions, and web3 dApps Other Repurposing content for social media the easy way » Repurpose.io [](https://repurpose.io/) Repurposing content for social media made easy. Automatically repurpose YouTube, TikTok, Lives, Podcasts, and Zoom calls. Try it for FREE. Smart Serials: Your serial numbers database [](https://smartserials.com/) This is your main source of free serial numbers, unlock keys in a clean environment safe to browse by all ages. Old versions of Windows, Mac and Linux Software, Apps & Abandonware Games - Download at OldVersion.com [](http://www.oldversion.com/) Online Room Planner - Design Your Room [](http://www.planyourroom.com/) Planyourroom.com is a wonderful website to redesign each room in your house by picking out perfect furniture options to fit your unique space. BoredHumans.com - Fun AI Programs You Can Use Online [](https://boredhumans.com/) Fun AI programs you can use online. AI games, fake people, computer generated art, machine learning demos, and more. BNProject | Home [](https://buynothingproject.org/) Open Source Alternatives to Proprietary Software [](https://www.opensourcealternative.to/) Discover 400+ popular open source alternatives to proprietary SaaS. URL Shortener - Short URLs & Custom Free Link Shortener | Bitly [](https://bitly.com/) Bitly’s Connections Platform is more than a free URL shortener, with robust link management software, advanced QR Code features, and a Link-in-bio solution. TinEye Reverse Image Search [](https://tineye.com/) Good Books | Books recommended by successful people [](https://www.goodbooks.io/) Looking for the best books to read in 2022? Discover the best book recommendations from the world's most successful, influential and interesting people. Directory - Website Recommendations [](https://tokapps.com/directory/) 0 TRIED & TESTED WEBSITES LISTED Insanely Useful Websites A combination of useful websites for businesses, freelancers, DIYers, and individuals in a centralised area.All websites have been tried and tested. Filter Websites Audio Business Tools Copywriting Design Entertainment Graphics Guides Health Marketing PC Resources Savings SEO Software Travel Video Apply filter Watch Anime Online, Free Anime Streaming Online on Zoro.to Anime Website [](https://zoro.to/) Zoro is a Free anime streaming website which you can watch English Subbed and Dubbed Anime online with No Account and Daily update. WATCH NOW! Animated Drawings [](https://sketch.metademolab.com/) Bring children's drawings to life, by animating characters to move around! Alternativeto [](https://alternativeto.net/) Chatroulette [](https://chatroulette.com/) Random meetings around the world Tiktok Downloader - Download Video tiktok Without Watermark - SnapTik [](https://snaptik.app/en) TikTok Video Downloader - SnapTik.App is one of the best free Download video Tiktok No Watermark tool available online. You can download TikTok video from any device you have. Imgflip - Create and Share Awesome Images [](https://imgflip.com/) Flip through memes, gifs, and other funny images. Make your own images with our Meme Generator or Animated GIF Maker. Fake Text Message | Make Fake Text Conversation [](https://ifaketextmessage.com/) Fake Text Message is a tool to create a Fake Text Conversation and a Fake iMessage. ✂Templatemaker ︎ [](https://www.templatemaker.nl/en/) Omni Calculator [](https://www.omnicalculator.com/) Omni Calculator solves 2960 problems anywhere from finance and business to health. It’s so fast and easy you won’t want to do the math again! Watch Movies Online Free | Watch Series HD Free [](https://hdtoday.tv/) Free Access to the Biggest library of HD Movies and HD Series online - NO ADS - No Account Required - Fast Free Streaming Students Answers - The Most Trusted Place for Answering Life's Questions [](https://www.answers.com/) Answers is the place to go to get the answers you need and to ask the questions you want Wolfram|Alpha: Computational Intelligence [](https://www.wolframalpha.com/) Compute answers using Wolfram's breakthrough technology & knowledgebase, relied on by millions of students & professionals. For math, science, nutrition, history, geography, engineering, mathematics, linguistics, sports, finance, music… Online Math Tools - Simple, free and easy to use math utilities [](https://onlinemathtools.com/) World's simplest collection of useful mathematics utilities. Generate number sequences, draw fractals, do quick matrix and numerical calculations and more! edX | Free Online Courses by Harvard, MIT, & more | edX [](https://www.edx.org/) Access 2000 free online courses from 140 leading institutions worldwide. Gain new skills and earn a certificate of completion. Join today. Sci-Hub [](https://sci-hub.hkvisa.net/) Sci-Hub,mg.scihub.ltd,sci-hub.tw,The project is supported by user donations. Imagine the world with free access to knowledge for everyone ‐ a world without any paywalls. DigitalDefynd - Find the Best + Free Courses Online [](https://digitaldefynd.com/) 4 Million+ Learners | 96,000+ Courses | 45,000+ Free Courses | 1200+ Free Certificates Learn Anything [](https://learn-anything.xyz/) Search Interactive Mind Maps to learn anything HubSpot Academy - Homepage [](https://academy.hubspot.com/) HubSpot Academy is the worldwide leader in inbound marketing, sales, and customer service/support training.

#github #internet-tools-collection

YT_Emerging_Technologies_Introduction_to_AI

YT_Emerging_Technologies_Introduction_to_AI

YouTube Channel: Emerging Technologies Playlist: Introduction to AI Instructor: Zeeshan-ul-hassan Usmani Dear Students, I have uploaded all relevant material here for your quick access and learning. I hope you will find it beneficiary Yours Truly, Zeeshan =========================================== Video title: Resources Books to Order: Artificial Intelligence by Zeeshan Usmani - https://gufhtugu.com/artificial-intelligence Artificial Intelligence by Baqir Naqvi - https://gufhtugu.com/masnoi-zahanat/ Recommended Books • Gödel, Escher, Bach : An Eternal Golden Braid by Douglas R. Hofstadter A classic, poetic, philosophical defense of AI. • Machines Who Think by Pamela McCorduck. A good review of early AI history. • Robot: Mere Machine to Transcendent Mind by Hans P. Moravec Somewhat hyped book by a CMU robotics researcher. • Flesh and Machines: How Robots Will Change Us by Rodney Allen Brooks Reasonably decent book by MIT's leading robotics researcher. • Wired for War by Peter Warren Singer Reviews growing use of robots and unmanned vehicles in warfare. • Behind Deep Blue: Building the Computer That Defeated the World Chess Champion by Feng-Hsiung Hsu Autobiographical book on the development of a history making game-playing system. Interesting personal story of the hard engineering work that went into the system, with a few interesting facts on the technical aspects. • The Age of Spiritual Machines : When Computers Exceed Human Intelligence by Ray Kurzweil A recent view by an AI entrepreneur that has content if you ignore all the hype and overly-optimistic trust that Moore's law will magically solve all of the major problems. • Hal's Legacy : 2001's Computer As Dream and Reality An interesting collection of edited articles written to celebrate the fictional birthday of a famous intelligent computer who's true birthday must unfortunately be delayed, pending AI's inevitable progress. • The Sciences of the Artificial by Herbert Simon AI as science by one of its founders. • Models of My Life by Herbert Simon. An autobiography of one of AI's founders who's intellectual contributions also include fundamental contributions to economics (for which he won the Nobel prize), cognitive psychology, and computer science (such as co-inventing the linked list in the 1950's). • Alan Turing: The Enigma by Alan Hodges. A biography of one of the founders of CS and originator of the Turing test. Also a testimony to the tragic implications of homophobia. • The Emperor's New Mind : Concerning Computers, Minds, and the Laws of Physics and Shadows of the Mind : A Search for the Missing Science of Consciousness and The Large, the Small and the Human Mind by Roger Penrose A completely bogus argument against AI by a hopelessly Platonic mathematician. The last book contains an appended article by Stephen Hawking (a colleague of Penrose's) who of course doesn't buy his bogus argument. • The Mind's New Science : A History of the Cognitive Revolution by Howard Gardner A nice history of the development of cognitive science. • How the Mind Works , The Language Instinct , and Words and Rules : The Ingredients of Language by Steven Pinker Fun reading on lots of interesting issues in modern Cognitive Science and Linguistics if you don't take his exaggerated beliefs in nativism and evolutionary psychology too seriously. • Bots : The Origin of New Species by Andrew Leonard A light, somewhat hyped book on on Internet agents, chatterbots, etc. with a few funny stories. • Mathematics: The Loss of Certainty by Morris Kline A very nice book on the failed enterprise of using logic to build a firm foundation for infallible mathematics and the role of Gödel's Incompleteness Theorem in the philosophy of mathematics. • Incompleteness: The Proof and Paradox of Kurt Gödel by Rebecca Goldstein An interesting biography of Kurt Gödel. Too bad he was such a Platonist that, unlike Turing, he did not understand the true implications of his own theorems (interesting author connection: Goldstein is Pinker's wife). Links: • AAAI AI Topics Basic info on AI from the American Association for Artificial Intelligence: http://www.aaai.org/AITopics/html/welcome.html • Loebner Prize for limited Turing test: http://www.loebner.net/Prizef/loebner-prize.html • IBM's Deep Blue Page: http://www.research.ibm.com/deepblue/ • Robocup: Robotic Soccer Competition: http://www.robocup.org/ • NY Times Article on Proof of the Robbins Theorem: http://www.nytimes.com/library/cyber/week/1210math.html • NY Times article on Bayes Nets at Microsoft Research: http://www.nytimes.com/library/tech/00/07/biztech/articles/17lab.html =========================================== Video title: Numbers Infinity Video Link - •https://www.youtube.com/watch?v=hlXHwMgS06c https://www.cbs.com/shows/numb3rs/ http://numb3rs.wolfram.com/ =========================================== Video title: 20 Hours Rule and Assisgnemnt Assignment - https://www.urdufake2020.cicling.org/ =========================================== Video title: Assignments – P1 Mostly Human - https://money.cnn.com/mostly-human =========================================== Video title: Assignments – P2 Assignment – 2 - https://replika.ai/ Assignment – 3 – Teachable Machines https://teachablemachine.withgoogle.com/ Assignment – 4 – Tensor Flow Playground https://playground.tensorflow.org Assignment – 5 – GPT-3 Paper (175B Parameters) https://debuild.co/ Assignment – 6 - Image GPT-3 https://openai.com/blog/image-gpt/ =========================================== Video title: Create your own Deep Fake 1.https://colab.research.google.com/drive/1mGg_fmvhTpvkPkclw2yKkhALVzmawfvT?usp=sharing 2.https://drive.google.com/drive/folders/1wW1bxRV2S7Ce8gc3VDTzMQABE3-WCc_Y?usp=sharing •go into you gdrive > find cloned folder and ensure that this folder must have: vox-adv-cpk.pth.tar & vox-cpk.pth.tar failes •Aliaksandr Siarohin : https://github.com/AliaksandrSiarohin/first-order-model

#github #yt_emerging_technologies_introduction_to_ai

#github #awesome-conversation-ai-bot

0.383

0.0056

XiaomingX•Jan 13, 2025

awesome-conversation-ai-bot

优秀的对话式AI资源精选的对话式AI资源列表，帮助你快速入门并创建出色的聊天机器人或数字助手。目录书籍和论文客户端对话式用户体验自然语言理解平台书籍和论文设计聊天机器人 - 指导如何设计和构建高效对话体验及有趣的聊天机器人，帮助用户更高效地完成任务。设计语音用户界面 - 本书涵盖了语音用户界面（VUI）设计的基本原理，适用于移动应用、玩具或家用助理设备。客户端 LINE - 连接聊天机器人到LINE，并使用其设计工具快速原型化。 Messenger - 为Facebook页面添加聊天机器人。 Slack - 将聊天机器人部署到Slack，帮助用户在工作环境中获得帮助。 Telegram - 使用Telegram Bot API方便地连接聊天机器人到Telegram。 WhatsApp - 使用WhatsApp商业平台API，将聊天机器人连接到客户。对话式用户体验 Conversation Design Institute - 提供对话设计的课程和认证。 Voiceflow - 一个对话设计工具，用于设计、原型和发布语音和聊天助手。自然语言理解 Awesome NLP - 一个关于自然语言处理的资源集合。 The NLP Index - NLP索引，包含3000多个代码库、相关论文和GitHub资源。平台 Amazon Lex - AWS提供的语音和文本对话接口服务。 Dialogflow - Google提供的自然语言虚拟代理平台。 Rasa - 创建虚拟助手的平台，提供开源和企业版本。

#github #ai-learning-roadmap

0.442

0.035708035270567436

gopala-kr•Nov 30, 2024

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

coursera-practical-data-science-specialization