VibeBuilders.ai Logo
VibeBuilders.ai

Joined

Explore resources related to joined to help implement AI solutions for your business.

Joined an AI Startup with Ex-ShipStation Team - Need Tips on Finding Early Users
reddit
LLM Vibe Score0
Human Vibe Score1
welcomereadThis week

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

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

Experienced Software Developer looking for startup to help. I will not promote
reddit
LLM Vibe Score0
Human Vibe Score1
DB010112This week

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

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

Experienced Software Developer looking for startup to help. I will not promote
reddit
LLM Vibe Score0
Human Vibe Score1
DB010112This week

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

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

10y of product development, 2 bankruptcies, and 1 Exit — what next? [Extended Story]
reddit
LLM Vibe Score0
Human Vibe Score1
Slight-Explanation29This week

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

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

Looking to streamline and update family business
reddit
LLM Vibe Score0
Human Vibe Score1
JohACNHThis week

Looking to streamline and update family business

Hey r/smallbusiness, I’ve been working at my family’s business for six years now—joined right after college—and I’ve realized that we’re long overdue for an overhaul. I handle advertising sales, and while the business itself is solid, the way we operate is extremely outdated. Without revealing too much, we print about 180 publications, and businesses pay to have their ads featured. As a sales rep, my job includes: Renewing current advertisers Finding new customers and making sales Collecting artwork for ads Gathering billing info Laying out the ad grid with all advertisers The Problem: Everything is still done with pen and paper. We use carbon copy paper to record business details, billing info, and ad costs. One copy goes to the graphic designers, the other to billing. The billing team manually enters everything into QuickBooks, prints invoices, stuffs envelopes, and mails them out. We recently got new software that lets us send invoices via email and text through QuickBooks, which is a step in the right direction, but it’s just a small fix to a much bigger problem. What I Want to Change: Move everything onto an app or website—no more paper. Digitally layout the ad grid instead of doing it manually. (For graphics team) Collect billing info online instead of writing it down. (Obviously to get paid faster and reduce wasted labor) Automate renewal emails instead of calling every single customer. (Save time) Find more efficient ways to generate leads for new business. (Work smarter not harder) Honestly, the company still runs like my grandma set it up in the '90s, and it’s overwhelming trying to figure out where to start. If anyone has been through something similar or has advice on modernizing a business, I’d love to hear your thoughts! Happy to provide more details if needed. I’ve explored some CRMs and AI tools, but I’m sure someone here has better insights or more experience with this than I do. There are other parts of the business that need improvement, but I believe this would be a big step in the right direction. Thanks in advance!

Learning Resources + Side Project Ideas
reddit
LLM Vibe Score0
Human Vibe Score1
Any-Reserve-4403This week

Learning Resources + Side Project Ideas

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

Month of August in AI
reddit
LLM Vibe Score0
Human Vibe Score1
Difficult-Race-1188This week

Month of August in AI

🔍 Inside this Issue: 🤖 Latest Breakthroughs: This month it’s all about Agents, LangChain RAG, and LLMs evaluation challenges.* 🌐 AI Monthly News: Discover how these stories are revolutionizing industries and impacting everyday life: EU AI Act, California’s Controversial SB1047 AI regulation act, Drama at OpenAI, and possible funding at OpenAI by Nvidia and Apple.* 📚 Editor’s Special: This covers the interesting talks, lectures, and articles we came across recently. Follow me on Twitter and LinkedIn at RealAIGuys and AIGuysEditor to get insight on new AI developments. Please don't forget to subscribe to our Newsletter: https://medium.com/aiguys/newsletter Latest Breakthroughs Are Agents just simple rules? Are Agents just enhanced reasoning? The answer is yes and no. Yes, in the sense that agents have simple rules and can sometimes enhance reasoning capabilities compared to a single prompt. But No in the sense that agents can have a much more diverse functionality like using specific tools, summarizing, or even following a particular style. In this blog, we look into how to set up these agents in a hierarchal manner just like running a small team of Authors, researchers, and supervisors. How To Build Hierarchical Multi-Agent Systems? TextGrad. It is a powerful framework performing automatic “differentiation” via text. It backpropagates textual feedback provided by LLMs to improve individual components of a compound AI system. In this framework, LLMs provide rich, general, natural language suggestions to optimize variables in computation graphs, ranging from code snippets to molecular structures. TextGrad showed effectiveness and generality across various applications, from question-answering and molecule optimization to radiotherapy treatment planning. TextGrad: Improving Prompting Using AutoGrad The addition of RAG to LLMs was an excellent idea. It helped the LLMs to become more specific and individualized. Adding new components to any system leads to more interactions and its own sets of problems. Adding RAG to LLMs leads to several problems such as how to retrieve the best content, what type of prompt to write, and many more. In this blog, we are going to combine the LangChain RAG with DSPy. We deep dive into how to evaluate the RAG pipeline quantitatively using RAGAs and how to create a system where instead of manually tweaking prompts, we let the system figure out the best prompt. How To Build LangChain RAG With DSPy? As the field of natural language processing (NLP) advances, the evaluation of large language models (LLMs) like GPT-4 becomes increasingly important and complex. Traditional metrics such as accuracy are often inadequate for assessing these models’ performance because they fail to capture the nuances of human language. In this article, we will explore why evaluating LLMs is challenging and discuss effective methods like BLEU and ROUGE for a more comprehensive evaluation. The Challenges of Evaluating Large Language Models AI Monthly News AI Act enters into force On 1 August 2024, the European Artificial Intelligence Act (AI Act) enters into force. The Act aims to foster responsible artificial intelligence development and deployment in the EU. The AI Act introduces a uniform framework across all EU countries, based on a forward-looking definition of AI and a risk-based approach: Minimal risk: most AI systems such as spam filters and AI-enabled video games face no obligation under the AI Act, but companies can voluntarily adopt additional codes of conduct. Specific transparency risk: systems like chatbots must clearly inform users that they are interacting with a machine, while certain AI-generated content must be labelled as such. High risk: high-risk AI systems such as AI-based medical software or AI systems used for recruitment must comply with strict requirements, including risk-mitigation systems, high-quality of data sets, clear user information, human oversight, etc. Unacceptable risk: for example, AI systems that allow “social scoring” by governments or companies are considered a clear threat to people’s fundamental rights and are therefore banned. EU announcement: Click here https://preview.redd.it/nwyzfzgm4cmd1.png?width=828&format=png&auto=webp&s=c873db37ca0dadd5b510bea70ac9f633b96aaea4 California AI bill SB-1047 sparks fierce debate, Senator likens it to ‘Jets vs. Sharks’ feud Key Aspects of SB-1047: Regulation Scope: Targets “frontier” AI models, defined by their immense computational training requirements (over 10²⁶ operations) or significant financial investment (>$100 million). Compliance Requirements: Developers must implement safety protocols, including the ability to immediately shut down, cybersecurity measures, and risk assessments, before model deployment. Whistleblower Protections: Encourages reporting of non-compliance or risks by offering protection against retaliation. Safety Incident Reporting: Mandates reporting AI safety incidents within 72 hours to a newly established Frontier Model Division. Certification: Developers need to certify compliance, potentially under penalty of perjury in earlier drafts, though amendments might have altered this. Pros: Safety First: Prioritizes the prevention of catastrophic harms by enforcing rigorous safety standards, potentially safeguarding against AI misuse or malfunction. Incentivizes Responsible Development: By setting high standards for AI model training, the company encourages developers to think critically about the implications of their creations. Public Trust: Enhances public confidence in AI by ensuring transparency and accountability in the development process. Cons: Innovation Stagnation: Critics argue it might stifle innovation, especially in open-source AI, due to the high costs and regulatory burdens of compliance. Ambiguity: Some definitions and requirements might be too specific or broad, leading to legal challenges or unintended consequences. Global Competitiveness: There’s concern that such regulations could push AI development outside California or the U.S., benefiting other nations without similar restrictions. Implementation Challenges: The practicalities of enforcing such regulations, especially the “positive safety determination,” could be complex and contentious. News Article: Click here Open Letter: Click here https://preview.redd.it/ib96d7nk4cmd1.png?width=828&format=png&auto=webp&s=0ed5913b5dae72e203c8592393e469d9130ed689 MORE OpenAI drama OpenAI co-founder John Schulman has left the company to join rival AI startup Anthropic, while OpenAI president and co-founder Greg Brockman is taking an extended leave until the end of the year. Schulman, who played a key role in creating the AI-powered chatbot platform ChatGPT and led OpenAI’s alignment science efforts, stated his move was driven by a desire to focus more on AI alignment and hands-on technical work. Peter Deng, a product manager who joined OpenAI last year, has also left the company. With these departures, only three of OpenAI’s original 11 founders remain: CEO Sam Altman, Brockman, and Wojciech Zaremba, lead of language and code generation. News Article: Click here https://preview.redd.it/0vdjc18j4cmd1.png?width=828&format=png&auto=webp&s=e9de604c26aed3e47b50df3bdf114ef61f967080 Apple and Nvidia may invest in OpenAI Apple, which is planning to integrate ChatGPT into iOS, is in talks to invest. Soon after, Bloomberg also reported that Apple is in talks but added that Nvidia “has discussed” joining the funding round as well. The round is reportedly being led by Thrive Capital and would value OpenAI at more than $100 billion. News Article: Click here https://preview.redd.it/ude6jguh4cmd1.png?width=828&format=png&auto=webp&s=3603cbca0dbb1be3e6d0efcf06c3a698428bbdd6 Editor’s Special The AI Bubble: Will It Burst, and What Comes After?: Click here Eric Schmidt Full Controversial Interview on AI Revolution (Former Google CEO): Click here AI isn’t gonna keep improving Click here General Intelligence: Define it, measure it, build it: Click here

[D] I tried the new Gemini API - it automatically stops when generating "OpenAI" or "GPT" lol
reddit
LLM Vibe Score0
Human Vibe Score0
AvvYaaThis week

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

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

[N] Last Week in AI News Digest 08/15-08/21: detecting hate speech, dogfight simulation, disaster-response, and more!
reddit
LLM Vibe Score0
Human Vibe Score-0.5
regalalgorithmThis week

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

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

[N] Last Week in AI News Digest 08/15-08/21: detecting hate speech, dogfight simulation, disaster-response, and more!
reddit
LLM Vibe Score0
Human Vibe Score-0.5
regalalgorithmThis week

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

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

How a Small Startup in Asia Secured a Contract with the US Department of Homeland Security
reddit
LLM Vibe Score0
Human Vibe Score1
Royal_Rest8409This 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.

I got fired due to automation — lessons learned. Two-month overview.
reddit
LLM Vibe Score0
Human Vibe Score1
WebsterPepsterThis week

I got fired due to automation — lessons learned. Two-month overview.

UPD: Guys, I'm not promoting myself as some of the redditors decided. That's why to deal with contradictions I'll do next things: make additional post with short review and description of the general tools and processes you could apply. help only those who have already written me. So I won't answer on new offers or DMs. As mentioned, damn robots have taken my job. PRE-HISTORY During Covid times, I found myself without my offline job, and since I was interested in marketing and SMM, I began searching for a job there. Completed free Google and Udemy courses and finally landed my first SMM manager position with a business owner. He had several projects so, finally, I started managing three Twitter accounts, two Facebook accs, two IGs, and one TikTok. I handled posting, content editing and responding routine, while freelancers usually took care of video creation for IG and TT. THE STORY ITSELF Things took a turn for the worse in April when my employer introduced ChatGPT and Midjourney, tools I was already using. The owner insisted on integrating them into the workflow, and my wages took a 20% hit. I thought I could roll with it, but it was just the beginning. By midsummer, the owner implemented second-layer AI tools like Visla, Pictory, and Woxo for video (bye freelancers, lol), as well as TweetHunter, Jasper, and Perplexity for content. Midjourney and Firefly joined for image generation. All together, my paycheck was slashed by 50%. Finally, at the end of October, my boss told me he automated stuff with Zapier, cutting costs that way. Additionally, he adopted MarketOwl, autoposting tool for Twitter, and SocialBee for Facebook. He stated that he didn’t need me, as by now he could manage the social media accounts himself. I feel so pissed then and even thought that there's no point in searching for similar jobs. HOW I SPENT TWO MONTHS Well, for the first two weeks, I did nothing but being miserable, drinking and staring at the wall. My gf said it's unbearable and threatened to leave if I not pull myself together. It was not the final push, but definitely made me rethink things. So I decided to learn more about the capabilities of these automation covers and eventually became an AI adviser for small businesses. It's ironic that now I sometimes earn money advising on how to optimize marketing, possibly contributing to other people's job loss. FINAL THOUGHTS I am fully aware of the instability of such a job and have invested my last savings in taking an online marketing course at Columbia to gain more marketing experience and got something more stable afterwards. Message for mods: I'm not promoting myself or anything mentioned here; just sharing the experience that someone might find helpful.

How a Small Startup in Asia Secured a Contract with the US Department of Homeland Security
reddit
LLM Vibe Score0
Human Vibe Score1
Royal_Rest8409This 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.

Made $940 in 3 days with the help of ChatGPT
reddit
LLM Vibe Score0
Human Vibe Score0
ninegagzThis week

Made $940 in 3 days with the help of ChatGPT

5 days ago I joined the HustleGPT challenge. Its purpose is to build products with the help of ChatGPT. I've made a goal of creating 1 digital product with chatGPT every day. On the 3rd day I've created an app for MacOS that lets you use ChatGPT inside any text field in any app. Basically, there is no need to open your browser, or go to openai website every time you want to use chatgpt. So, after building it and publishing on Gumroad, I've tweeted about it and went to sleep. You may be thinking that my tweet has gone viral and that's how I made all the sales. However, this is not the case. My tweet got only 1200 views. And these 1200 views generated me my first $140 of revenue! After that, I started actively posting my product on social media. I never gone viral but even with 1-2k views per post I've made sales. And I'm on my way to $1000 revenue from my side project. I didn't spend much time on it too. As I was writing this post, I've made 1 new sale! That's $19 revenue (profit from each is sale is $16). After some thinking, I got this idea: what if I let other entrepreneurs earn with my app? Basically, you can resell my app, redistribute it, and do whatever you want with it. Once you buy it, you can freely do whatever you want with it. What do you think? Here is a tool that I use to create content that drives most sales for me - link Also, if you want to build apps with ChatGPT - this guide will help you - Here is a link I'm open for any feedback and suggestions! Thanks

Meet The AI Entrepreneur Who Used LinkedIn To Raise $13.8 Million
youtube
LLM Vibe Score0.436
Human Vibe Score0.64
ForbesApr 19, 2024

Meet The AI Entrepreneur Who Used LinkedIn To Raise $13.8 Million

Benjamin Harvey, the CEO of AI Squared, says he’s added investors including former TIAA CEO Roger Ferguson. Harvey joined Forbes senior writer, Jabari Young, at the Nasdaq MarketSite to discuss the startup’s Series A raise. Read the full story on Forbes: https://www.forbes.com/sites/jabariyoung/2024/04/17/meet-the-ai-entrepreneur-who-used-linkedin-to-raise-138-million/?sh=60958bea5837 0:00 Introduction 2:16 Benjamin Gives Biggest Tip On Learning Profit Loss 5:00 Benjamin Harvey On The State Of AI 8:25 How Will AI Evolve And Change In The Future? 14:04 What Is It Like To Be CEO Of AI Squared? 17:04 How Benjamin's Upbringing And Love Of Cartoons Helps Put Ideas Together In Business 23:02 Benjamin On Getting Investors For AI Squared 25:56 Benjamin's Take On ChatGPT And How Its Used 29:48 Artificial Intelligence: Benjamin's Take On What's Next 34:49 A Good AI Platform vs. A Great One Subscribe to FORBES: https://www.youtube.com/user/Forbes?sub_confirmation=1 Fuel your success with Forbes. Gain unlimited access to premium journalism, including breaking news, groundbreaking in-depth reported stories, daily digests and more. Plus, members get a front-row seat at members-only events with leading thinkers and doers, access to premium video that can help you get ahead, an ad-light experience, early access to select products including NFT drops and more: https://account.forbes.com/membership/?utmsource=youtube&utmmedium=display&utmcampaign=growthnon-subpaidsubscribe_ytdescript Stay Connected Forbes newsletters: https://newsletters.editorial.forbes.com Forbes on Facebook: http://fb.com/forbes Forbes Video on Twitter: http://www.twitter.com/forbes Forbes Video on Instagram: http://instagram.com/forbes More From Forbes: http://forbes.com Forbes covers the intersection of entrepreneurship, wealth, technology, business and lifestyle with a focus on people and success.