Feeling

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

reddit

0

1

vishwa1238•This week

Feeling stuck—built a startup, got rejected from YC & IVI, met smarter people, and now I don’t know what to do. ( i will not promote ) I will not promote

I will not promote I don’t even know where to start, but I just feel completely stuck right now. I’m 20 years oldI don’t even know where to start, but I just feel completely stuck right now. I’m 20 years old, have been grinding non-stop for months, and it feels like I have nothing to show for it. I built an AI agent that automates workflows for businesses. I can build tech, but I can’t sell. That’s been my biggest realization recently—I thought building would be enough, but it’s not. I need customers, I need a co-founder, I need to figure out the business side… and I have no idea how. I applied to YC, IVI at ISB, and EF, met a lot of insanely smart people—some were impressed with me and my work, but they were wiser, more experienced, and honestly, just better at all of this than I am. It made me realize how much I don’t know. I got rejected from YC & IVI. 💔 YC didn’t even give much feedback—just a standard rejection. 💔 IVI told me: “You're too young, you need more experience, and you should work with a team before trying to start something.” That hit me hard. I had already been struggling to find a co-founder, and this just made me wonder if I even belong in this space yet. The Frustrating Part? I KNOW my tool Has a Unique Edge. I’m not just another AI automation tool—I know my tool has a strong USP that competitors lack. It has the potential to be an AI employee for businesses, not just another workflow tool. But I still haven’t built the “perfect product” I originally envisioned. And that’s what’s eating at me. I see what it COULD be, but I haven’t made it happen yet. At the same time, the competition in the AI agent space is exploding. YC-backed companies are working on AI agent startups. OpenAI is making huge progress with Operator. Competitors are moving fast, while I feel stuck. I’ve delayed development because I’m unsure whether to double down, pivot, or just move on entirely. Where I’m Stuck Right Now 🔹 Do I keep pushing and try to crack sales somehow? 🔹 Do I join a startup as a founding engineer to get experience, make connections, and learn sales before trying again? 🔹 Do I move to Bangalore, meet founders, and figure out what’s next? 🔹 Do I pivot to something nicher instead of competing in the AI agent race? If so, how do I even find a niche worth pursuing? 🔹 Do I even belong in startups? Or am I just forcing something that’s not working? I feel stuck in a weird middle zone where I’m not a beginner, but I’m also not successful. I’ve done enough to see what’s possible, but not enough to make it real. Every rejection makes me question if I’m even on the right path. I don’t know if I’m posting this for advice or just to get it out of my system. Maybe both. Has anyone else felt like this before? If you’ve been in this situation—how did you figure out whether to keep going or move on? TL;DR: I’m 20, built an AI agent for automating workflows, got rejected from YC & IVI, met insanely smart and experienced people, realized I can build tech but can’t sell, struggling to find a co-founder, AI agent competition is growing, delaying development, confused about the future—don’t know whether to double down, pivot, or move on. The frustrating part? I\ know I have a unique edge that others lack, but I still haven’t built the perfect product I originally envisioned.* edit: removed the tool's name

#reddit#feeling#stuck—built

reddit

0

1

vishwa1238•This week

Feeling stuck—built a startup, got rejected from YC & IVI, met smarter people, and now I don’t know what to do. ( i will not promote ) I will not promote

I will not promote I don’t even know where to start, but I just feel completely stuck right now. I’m 20 years oldI don’t even know where to start, but I just feel completely stuck right now. I’m 20 years old, have been grinding non-stop for months, and it feels like I have nothing to show for it. I built an AI agent that automates workflows for businesses. I can build tech, but I can’t sell. That’s been my biggest realization recently—I thought building would be enough, but it’s not. I need customers, I need a co-founder, I need to figure out the business side… and I have no idea how. I applied to YC, IVI at ISB, and EF, met a lot of insanely smart people—some were impressed with me and my work, but they were wiser, more experienced, and honestly, just better at all of this than I am. It made me realize how much I don’t know. I got rejected from YC & IVI. 💔 YC didn’t even give much feedback—just a standard rejection. 💔 IVI told me: “You're too young, you need more experience, and you should work with a team before trying to start something.” That hit me hard. I had already been struggling to find a co-founder, and this just made me wonder if I even belong in this space yet. The Frustrating Part? I KNOW my tool Has a Unique Edge. I’m not just another AI automation tool—I know my tool has a strong USP that competitors lack. It has the potential to be an AI employee for businesses, not just another workflow tool. But I still haven’t built the “perfect product” I originally envisioned. And that’s what’s eating at me. I see what it COULD be, but I haven’t made it happen yet. At the same time, the competition in the AI agent space is exploding. YC-backed companies are working on AI agent startups. OpenAI is making huge progress with Operator. Competitors are moving fast, while I feel stuck. I’ve delayed development because I’m unsure whether to double down, pivot, or just move on entirely. Where I’m Stuck Right Now 🔹 Do I keep pushing and try to crack sales somehow? 🔹 Do I join a startup as a founding engineer to get experience, make connections, and learn sales before trying again? 🔹 Do I move to Bangalore, meet founders, and figure out what’s next? 🔹 Do I pivot to something nicher instead of competing in the AI agent race? If so, how do I even find a niche worth pursuing? 🔹 Do I even belong in startups? Or am I just forcing something that’s not working? I feel stuck in a weird middle zone where I’m not a beginner, but I’m also not successful. I’ve done enough to see what’s possible, but not enough to make it real. Every rejection makes me question if I’m even on the right path. I don’t know if I’m posting this for advice or just to get it out of my system. Maybe both. Has anyone else felt like this before? If you’ve been in this situation—how did you figure out whether to keep going or move on? TL;DR: I’m 20, built an AI agent for automating workflows, got rejected from YC & IVI, met insanely smart and experienced people, realized I can build tech but can’t sell, struggling to find a co-founder, AI agent competition is growing, delaying development, confused about the future—don’t know whether to double down, pivot, or move on. The frustrating part? I\ know I have a unique edge that others lack, but I still haven’t built the perfect product I originally envisioned.* edit: removed the tool's name

#reddit#feeling#stuck—built

reddit

0

1

Consistent_Access844•This week

Finally Launched My First App Without Any Coding Experience

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

#reddit#finally#launched

reddit

0

1

DB010112•This 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.

#reddit#experienced#software

reddit

0

1

Royal_Rest8409•This week

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

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

#reddit#founder#built

reddit

0

0

Fine4FenderFriend•This week

Mentally burnt out

My startup is not working and this is the year I probably need to shut down. I have struggled and tried to make this work for 5 years now but I am down to one person and hired consultants. I have a feeling of utter failure and no significant achievements. The minor alerts I have put out to potential future job prospects look bleak too. I am seen as too broad having been a Founder and not deep. I have an Engineering background but played the Go to Market/CEO role at my startup. Part of my mistake was not getting deep into the Engineering (outsourcing it). I have a rare combination of knowledge in Gen AI, Autonomous Vehicles and Strategy. However, there seem to be no takers - the market is too nascent and my skills have become too broad - a founder skillset rather than deep. What do I do now? I am mentally burnt out to make $$ out of this startup but the job market is not helping either.

#reddit#mentally#burnt

reddit

0

1

GPT-Rex•This week

Is my idea + progress good enough to raise pre-seed round? CRM for construction niches. Non-tech founder.

Is my startup idea and progress good enough to raise a pre-seed round? It’s a CRM with meaningful AI integrations for specific type of B2B construction companies. I only want to continue at my current pace if it’s realistic to start raising within the next 2 weeks. At first, I thought it was fine because simple companies still get on Y-comb such as hammr and Relate CRM , but now I’m not sure. Would love to get the community’s thoughts on this. I’ve been working on this for about a week. ​ Key Highlights (You can skip to longer section below) Product is CRM for B2B construction companies. The previous tech company I worked at used an in-house built CRM for their workflow, and I’m creating that solution and applying it to B2B construction companies that have similar workflows. No competitors I’ve found. I’m uniquely positioned to spearhead: B2B SaaS/tech sales + expertise in construction I’m a non-tech sales founder with experience in UI/UX. Will bring on CTO co-founder once I start raising as that would entice better talent Progress + Traction $400 MRR in pre-sales, can get to \~$800-1000 EOM Validated through customer interviews Created some Figma frames, product overview, user journeys, business plan Made a simple but meaningful AI tool that will be available to those that sign up for waitlist. Did this with GitHub + ChatGPT Landing page website going up this week followed by PPC campaign, email marketing, and outreach. My GF works in enterprise sales and she’ll help me generate more leads. ​ Long Version Background B2B SaaS/Tech sales. I worked at enterprise company as an Account Executive where I worked with funded startups and their development, UI/UX, and Product management teams. I have a general knowledge in all these - my best being UI/UX design as I can work with Figma well Domain expertise: my family has had a construction company since I was young. I have a large network because of this. Problem At my previous company, we had a custom in-house built CRM for our workflow. It worked okay, despite being maintained by multiple engineers costing hundreds of thousands a year. I’m creating a CRM that solves that, and applying it to construction industries that can make use of it. I have a great network here which makes it easy for me get sales quickly. Vision Building this CRM for construction niche will allow us to generate MRR fast. We will be first movers in bringing meaningful AI tools to construction, which is generating significant interest. This gives us the opportunity to build the foundational technology that can be adapted to a wider audience such as my previous company and others - think researchers, consultants, etc. Traction + Current Progress (1 week) Validated idea through user interviews and pre-sales. Currently have $400 MRR in pre-sales. I expect $800-1000 in a month if I continue at my pace. This is from doing typical B2B sales. I’ve set up a CRM for this. Created product overview, user journeys, wireframes and some Figma frames, business plan Created a simple but meaningful AI tool for the niche which will be available to those that sign up for the waitlist. Created with GitHub + ChatGPT Completing landing page website this week. Will start PPC ads (I’m experienced in this) after that to generate sign-ups. I’ll also start email marketing from lists I’ve scraped. Team Solo-founder, will bring on CTO co-founder once I start raising funds. I have promising candidates, but feel that I need to raise funds to really entice a good co-founder. I’m uniquely positioned to head this product; B2B sales having worked with many CRMs + construction expertise and network. That said, I’ve never actually done anything that* impressive besides being an AE at a known enterprise techy company (but not FAANG level). ​ I want to acknowledge that my progress might sound more impressive than it is - it's still just a CRM after all, and I'm non-technical. Should I keep going? Advice? I also have a great offer to lead sales at a profitable startup, but I could always do both if it was worth it. I’m feeling really uncertain for some reason :/ maybe it’s just burnout.

#reddit#idea#progress

reddit

0

1

Both_Ask4432•This week

Marketing strategy for early-stage startup

Hi! I'm a first-time founder and now we with my co-founder are working on launching our solution. We are working on a b2c service that visualizes what people feel based on their notes. Our potential users are women 18-29 who are interested in feeling better. I'm non-technical so marketing is in my responsibilities. Now I am trying to create something like a marketing strategy for this early-stage launch, and I would like to know your opinions about it, maybe I missed something that could work for us. In my plan, we start by announcing in personal social networks, like LI, Ig and meeting new people on offline events. We also would try to have some paid or unpaid announcements in groups on Fb about health, well-being, new apps, AI (we use AI in our service), women entrepreneurs supportive communities. We were thinking about Tinder Ads, but I didn't have any reviews of it. We also plan to work with influencers on Ig and YT, maybe TikTok. And also would like to try Google Ads, IG ads, YT ads. ​ Have you tried something of it? How it was? Maybe I missed something that worked for you in similar cases?

#reddit#marketing#strategy

reddit

0

1

Consistent_Access844•This week

Finally Launched My First App Without Any Coding Experience

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

#reddit#finally#launched

reddit

0

1

DB010112•This 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.

#reddit#experienced#software

reddit

0

0

Prior-Inflation8755•This week

People are overthinking with digital products.

All you really need is a checkout link to start. I failed a lot of times. Literally I could build the whole landing page, admin panel, ai automation to handle moderation and content. After spending months in vacuum building more, more, more features. Launching and getting 0 customers in the end. You are literally just getting depressed. You know that feeling, right ? Me too. We missed one important step before building anything - ASKING. We need to ask more clients, users, and do our research based on Google Keywords, forums and subreddits. You probably won't do it. It is your choice. You have all rights to do it. Let me give one piece of advice, instead of building more features and spendings months on your MVP. Set a deadline in 2-4 weeks. Build it, launch it, and go live as soon as possible. You need to get a real feedback and face a reality. Most of the companies that you see, started with simple Excel file, Google Doc, or even paper with pen. Do you know why ? Because they didn't have anything in the beginning. No money, no customers, NOTHING. Remember that.

#reddit#people#overthinking

reddit

0

1

Royal_Rest8409•This week

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

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

#reddit#founder#built

reddit

0

0

Consistent_Yak6765•This week

After building an AI Co-founder to solve my startup struggles, I realized we might be onto something bigger. What problems would you want YOUR AI Co-founder to solve?

A few days ago, I shared my entrepreneurial journey and the endless loop of startup struggles I was facing. The response from the community was overwhelming, and it validated something I had stumbled upon while trying to solve my own problems. In just a matter of days, we've built out the core modules I initially used for myself, deep market research capabilities, automated outreach systems, and competitor analysis. It's surreal to see something born out of personal frustration turning into a tool that others might actually find valuable. But here's where it gets interesting (and where I need your help). While we're actively onboarding users for our alpha test, I can't shake the feeling that we're just scratching the surface. We've built what helped me, but what would help YOU? When you're lying awake at 3 AM, stressed about your startup, what tasks do you wish you could delegate to an AI co-founder who actually understands context and can take meaningful action? Of course, it's not a replacement for an actual AI cofounder, but using our prior entrepreneurial experience and conversations with other folks, we understand that OUTREACH and SALES might actually be a big problem statement we can go deeper on as it naturally helps with the following: Idea Validation - Testing your assumptions with real customers before building Pricing strategy - Understanding what the market is willing to pay Product strategy - Getting feedback on features and roadmap Actually revenue - Converting conversations into real paying customers I'm not asking you to imagine some sci-fi scenario, we've already built modules that can: Generate comprehensive 20+ page market analysis reports with actionable insights Handle customer outreach Monitor competitors and target accounts, tracking changes in their strategy Take supervised actions based on the insights gathered (Manual effort is required currently) But what else should it do? What would make you trust an AI co-founder with parts of your business? Or do you think this whole concept is fundamentally flawed? I'm committed to building this the right way, not just another AI tool or an LLM Wrapper, but an agentic system that can understand your unique challenges and work towards overcoming them. Whether you think this is revolutionary or ridiculous, I want to hear your honest thoughts. But more importantly, I want to hear your unfiltered feedback in the comments. What would make this truly valuable for YOU? Edit 1: The AI cofounder will take no equity in your startup.

#reddit#after#building

reddit

0

1

BetAltruistic6556•This week

I started a Tech Startup, and I feel totally STUCK.

I made "Visual Love," a Computer Vision/AI-driven matchmaking platform. The idea is that although appearance is one of the biggest factors for starting a relationship, current matchmaking services and dating apps do not have the capability to search for people based on appearance. On Visual Love, you can find your ideal match simply by uploading a picture of your "ideal type." Also, you can connect with someone who thinks of you as their ideal type, simply by uploading your own picture. Or, there might be a perfect (mutually ideal) match. I made this CV/AI algorithm to scan faces, retrieve facial features, and make it possible to find the closest match among millions of others in a second. On average, regular dating app users swipe 8000 times over 8 months until they find their love. On Visual Love, users can find one in a million just in a second. You can try the tech demo on the website if you want to (find the link through my LinkedIn at the bottom of the post; I have to follow the "I will not promote" rule.) I thought this app would have the best chance in Asia, as people care a lot more about appearance in Asia (especially Korea and Japan). Also, my nationality is Korean, and I speak both Korean and Japanese as fluently as I speak English. So I came to Korea, and pitched to a number of VC/AC firms in Korea and Japan, and two of them were typically intersted in making investment. However, they both required me to provide market validation: how much it would cost per user acquisition, how much each user would pay on average, and etc, even after I provided them with a 3-years financial projection including market research based on other dating apps. ​ Everything might be going just as expected, or even better than anticipated, but I'm feeling very stuck now. I am not a business expert, and I don't have much idea on how to proceed from here. The problem is, it wouldn't quite work as expected when there are not many users. If I start with a small group of users, it's not any better than any other dating app. Matching users within a small group doesn't quite reflect the values of Visual Love. So I figured a way around: making a game version of Visual Love targeting 100k to 500k users to work as an initial distribution channel. This version will include finding look-alike celebrities, and solving look-alike face puzzles, and etc. But now, the problem is, I cannot continue this project by myself. I have no social/financial support, and I'm running low on cash. Also, although I'm from Korea, I lived in many different countries. I did my undergraduate in New York (Columbia University) and all my friends are in the US. I don't feel very included here. I can't stop feeling frustrated and distressed :( I'm sure Visual Love can reshape the future of the matchmaking market. But, only if I can continue this project by getting the fund I require. I'm open to any advice, and if you're interested in providing any help or working with me, please contact me through LinkedIn. https://www.linkedin.com/in/don-lee-3853b1264/

#reddit#started#tech

reddit

0

0

Consistent_Yak6765•This week

After building an AI Co-founder to solve my startup struggles, I realized we might be onto something bigger. What problems would you want YOUR AI Co-founder to solve?

A few days ago, I shared my entrepreneurial journey and the endless loop of startup struggles I was facing. The response from the community was overwhelming, and it validated something I had stumbled upon while trying to solve my own problems. In just a matter of days, we've built out the core modules I initially used for myself, deep market research capabilities, automated outreach systems, and competitor analysis. It's surreal to see something born out of personal frustration turning into a tool that others might actually find valuable. But here's where it gets interesting (and where I need your help). While we're actively onboarding users for our alpha test, I can't shake the feeling that we're just scratching the surface. We've built what helped me, but what would help YOU? When you're lying awake at 3 AM, stressed about your startup, what tasks do you wish you could delegate to an AI co-founder who actually understands context and can take meaningful action? Of course, it's not a replacement for an actual AI cofounder, but using our prior entrepreneurial experience and conversations with other folks, we understand that OUTREACH and SALES might actually be a big problem statement we can go deeper on as it naturally helps with the following: Idea Validation - Testing your assumptions with real customers before building Pricing strategy - Understanding what the market is willing to pay Product strategy - Getting feedback on features and roadmap Actually revenue - Converting conversations into real paying customers I'm not asking you to imagine some sci-fi scenario, we've already built modules that can: Generate comprehensive 20+ page market analysis reports with actionable insights Handle customer outreach Monitor competitors and target accounts, tracking changes in their strategy Take supervised actions based on the insights gathered (Manual effort is required currently) But what else should it do? What would make you trust an AI co-founder with parts of your business? Or do you think this whole concept is fundamentally flawed? I'm committed to building this the right way, not just another AI tool or an LLM Wrapper, but an agentic system that can understand your unique challenges and work towards overcoming them. Whether you think this is revolutionary or ridiculous, I want to hear your honest thoughts. But more importantly, I want to hear your unfiltered feedback in the comments. What would make this truly valuable for YOU? Edit 1: The AI cofounder will take no equity in your startup.

#reddit#after#building

reddit

0

0.778

No-Understanding5609•This week

The Birth of My First (and Hilariously Flawed) Voice Agent: A Tale of No-Code Chaos

Okay Reddit, buckle up. I'm about to tell you the saga of how I birthed my very first voice agent, a chaotic and frankly, slightly embarrassing journey involving Retell.ai, Make.com, and Zapier. Looking back, it's equal parts hilarious and traumatizing. The Naive Dream: Back then (it feels like ages ago!), I was convinced I could easily whip up a voice agent that would take restaurant orders over the phone. Elegant, efficient, and completely automated! I envisioned a world where my clients' restaurant never missed a beat, all thanks to my coding prowess... or rather, my no-code prowess. How wrong I was. The Gauntlet Begins: Retell.ai's Murky Depths Retell.ai was the starting point, the "voice" of my operation. Getting the phone number hooked up felt like a small victory, quickly overshadowed by the realization that their documentation was... well, let's just say it wasn't written for complete novices. I spent what felt like an eternity staring at API keys, convinced I'd entered them correctly, only to be greeted by cryptic error messages. The sheer frustration I felt wrestling with that initial setup is something I'll never forget. Make.com: From Pretty Picture to Painful Puzzle Then came Make.com, the orchestra conductor of my workflow. It looked so beautiful, so user-friendly! Drag and drop, visual modules... what could go wrong? Oh, so much could go wrong. Trying to decipher the JSON data stream from Retell was like trying to understand a foreign language I only knew a few words of. Mapping that data to a Google Sheet? A complete and utter disaster. I remember spending hours just trying to get the correct fields to populate, each failed attempt fueling my growing despair. Zapier: Briefly Considered, Quickly Dismissed I flirted with the idea of using Zapier instead, seduced by its simplicity. But its limitations became glaringly obvious when I tried to build the complex, multi-step process I needed. Make.com was the only real option, which meant diving headfirst into a whole new world of modules, triggers, and data transformations. The Infernal Testing Loop: The absolute WORST part of the entire process was the testing. Picture this: Calling the agent, rambling through a mock order, waiting for the workflow to execute, only to discover (yet another) error. Then, tweaking the scenario, pushing "save," and repeating the entire agonizing process. Each test call felt like a mini-marathon, a grueling race against time and my own dwindling patience. The AI's... Quirks: And then there was the AI itself. It was... let's just say it had a personality of its own. Sometimes, it perfectly understood my order. Other times, it decided I wanted to order 500 pizzas with extra anchovies. Debugging the AI's interpretation felt like negotiating with a stubborn toddler. Lessons Hard-Learned (And Forever Etched in My Memory): Start absurdly small: I tried to build a fully functional system right away. A HUGE mistake. If I could go back, I would have focused on just extracting one piece of information (like, say, just the quantity) and gotten that rock solid before adding anything else. JSON is your friend (or should be): Back then, JSON felt like alien code. Now, I have a slightly better grasp on it. Trust me, learn JSON. It will save you so much pain. Test like your sanity depends on it: Because it does. After every. Single. Change. Test the entire flow. It's tedious, but it's the only way to catch errors before they snowball into a catastrophe. Don't suffer in silence: I tried to be a lone wolf, figuring everything out myself. Big mistake. Retell.ai's forums and Make.com's documentation are goldmines. Use them! Embrace the struggle: This is the most important lesson. Building a voice agent, especially your first one, is hard. It's frustrating. It will test your limits. But don't give up. The feeling of finally making it work (even partially) is worth it. The Bot That (Barely) Lived: In the end, I did create a voice agent that could take orders and log them into a spreadsheet. It wasn't pretty. It was buggy. It occasionally ordered things that didn't make any sense. But it was mine. And it was the first step on a long and winding road. Looking back, I laugh (and cringe) at my naivety. But I also appreciate the lessons I learned and the sheer grit it took to bring my little AI Frankenstein to life. Anyone else have a similar "first bot" story? Let's hear them! Misery (and laughter) loves company. #RetellAI #Makecom #Zapier #FirstBot #NoCodeFail #VoiceAgentStruggles #StoryTime

#reddit#birth#first

reddit

0

1

HouJB•This week

Seeking Advice on Online Lead Generation and Tools for a New Service-Based Brokerage

I recently launched an online, B2B, service-based brokerage that's heavily reliant on web-based marketing for lead generation. As a bootstrapped business owner, I'm feeling a bit overwhelmed trying to determine the most effective strategies for driving online leads—whether through Google Ads, SEO, or other methods. In addition, I'm looking for the best software and tools to help organize and manage leads, or even assist in the lead generation process. I've been exploring AI-powered tools like AI Call Agents and others, but I’m unsure of what would be most effective for a growing business like mine. If anyone has experience with tools or strategies that have worked well early in your business journey, I’d love to hear your insights!

#reddit#seeking#advice

reddit

0

1

sarveshpandey89•This week

Seeking Feedback on My Business Idea – SaaS + Lead Generation for Small Businesses

Edit: TL;DR I’m Sarvesh, a digital marketer with 10 years of experience in paid ads. After losing my job last year, I started freelancing and discovered how much small businesses struggle with getting reviews (Google, Yelp, TrustPilot, etc.). My Business Idea – SaaS + Paid Ads Free Plan: Businesses can track & reply to reviews across 40+ platforms in one dashboard. Paid Plan ($99/month): Automates review collection, AI-powered responses, social media posting, and spam detection. Custom Plan: Paid ads to generate leads, offered only to businesses on my paid plan for 3+ months. Goal: SaaS platform attracts users → Some upgrade to paid plan → Best clients get lead-generation help → More leads → More reviews → More organic customers → A profitable business cycle. Need Feedback: Does this idea have potential? How can I get my first beta users? Any features I should add/remove? Would love your thoughts—thanks for reading! 😊 TL: Hi everyone, I’m Sarvesh, and I’m in the process of starting my own business. Since my target audience is small businesses, I’d love to get some input, advice, or critiques from this community. A Little About Me I’ve spent the last 10 years working in paid advertising, helping medium and large businesses generate leads through Facebook and Google Ads. I also have experience running e-commerce campaigns. You can check out my background on LinkedIn: LinkedIn Profile Last year, my second daughter was born, and around the same time, my company shut down all its offices (India & UK), leaving me without a job. I decided to take a break and spend time with my wife and newborn, something I regretted not doing with my first child. By November, I started job hunting again, but in the meantime, I got some freelance work through Reddit, helping small businesses with ads for the first time. For context, in my previous jobs, I managed ad campaigns with daily budgets of £4K–£8K. Working with small businesses was a new challenge, but to my surprise, I was able to generate solid leads for beauty salons, hair salons, and nail salons, helping them grow. What stood out to me was how much impact my work had—unlike my corporate job, where I was just another person in the system, here I felt truly valued. That feeling led me to explore starting my own business. The Problem I Noticed While working with small businesses, I realized that online reviews (Google, Yelp, Trustpilot, etc.) are critical for them, yet many struggle to get them. Customers often don’t leave reviews, and employees are either too shy or don’t prioritize asking for them. This gave me an idea—to build a system that helps businesses get more genuine Google reviews from customers. I developed the system but struggled to find businesses willing to test it, even for free. My target audience is U.S. small businesses, but since I’m based in India, cold emails and Reddit outreach didn’t get much traction. My Business Idea – SaaS + Custom Plans I’m now thinking of pivoting my business model into a SaaS platform with optional paid upgrades. Here’s how it would work: Free Plan (Review Tracking & Management) Businesses can track their reviews across 40+ platforms (Google, Yelp, Facebook, Trustpilot, TripAdvisor, etc.) in one dashboard. They can reply to reviews manually from a single place instead of switching between platforms. This will be completely free forever. Paid Plan ($99/month, Plus SMS/Email Costs) For businesses that struggle to get reviews, they can upgrade to a paid plan that includes: Automated Review Requests – Automatically send review requests via SMS & email. Website Widget – Showcase 4- and 5-star reviews dynamically. Social Media Automation – Automatically post positive reviews on Facebook/Instagram. AI-Powered Responses – AI can reply to reviews automatically. Spam Detection – The system will notify businesses of suspicious reviews (but won’t take direct action). Custom Plan (Lead Generation via Paid Ads) I will personally manage paid ad campaigns to generate leads. Pricing depends on the niche, budget, and contract duration. Money-Back Guarantee – If I don’t deliver results, I refund the month’s fee. Small businesses can’t afford wasted ad spend, and I want to ensure I provide real value. Limited spots per month to maintain quality and avoid burnout. How Everything Ties Together The SaaS platform serves as a lead generation tool for my custom plans: Businesses use the free plan to track their reviews. Some upgrade to the paid plan to automate and improve reviews. A select few, after 3 months on the paid plan, can join my custom plan for paid ads to generate more leads. More leads → More reviews → Better Google Maps ranking → More organic customers → A more profitable business. Would Love Your Feedback! What do you think about this approach? Do you see potential for this business to take off? Any features I should add or remove? Any suggestions on how I can get my first beta users to test the SaaS platform? What about pricing? Do you think $99 is good pricing? I know this is a long post, but I really appreciate anyone taking the time to read and share their thoughts. Thanks in advance!

#reddit#seeking#feedback

reddit

0

0.857

ricky0603•This week

What I learn from my $200 MRR App I built 4 months ago?

4 month ago, I am just a 10-years experienced product manager without any software development experience. I have an $3K/month job, but I am so tired, I don’t like my life, don’t like my boss, don’t like my daily work, that make me feeling I already died however I am still living. I yearn for freedom and want to live each day the way I want to. So I quit my job, and become a Indie developer to build my own business, my own app, even my own life. I am so grateful for this time and experience, now my app reach $200 MRR, still very little compared to my previous salary, but I never regret. I have learned lots of things from this time and experience, more than I had in last 10 years. Here is the time-line of my App: \- Sep 2023: Launch first version to iOS App store \- Oct 2023: Release in-app-purchase features and have first subscriber, the revenue in October is $154 \- Nov 2023: Change from subscription to pay per use, and I did lots of marketing jobs in November, however, the revenue reduced to only $40. \- Dec 2023: Change back to subscription, and stop some invalid marketing jobs, only keep the ones that actually work. I almost did nothing in December, and the revenue come to $243. During this process, I have learned lots of things, there are some of them that I think could help you as well. Web or App My App is an iOS app that only can running on Apple’s device such like iPhone/iPad or Mac with Apple silicon. Many people ask me why my product is an iOS app not a website, because they don’t have any Apple device. It's true that promoting an app is much harder than promoting a website. However I am now very glad I made an App and not a website! If I make a website, I don't think it's possible to make $100 in the first month. My App is about keyword research, to help people find some ideas from search keyword, because every keyword people searched in Google are representing a real need of them, also can be used in SEO field. However there are a lot of website tools about keyword research, some of them are famous like Ahrefs, SEMrush… I have no intention of competing with them. Actually I don’t have any chance. While in app store, there are little apps about keyword research, each of them have terrible data and user experience, that means if my app has better data and experience that could be my chance. In fact, the App store brings me 20 organic installs a day that Google would never have been able to bring me if I had a website, at least for the first few months. Furthermore, Apple nearly did everything for developer, I don’t need to care about user login, payment and so on, Apple did everything, I just need to call their API, that save lots of time, if I build a website, I need to implement login and payment by myself, that would add some extra work. Not to mention I'd need to buy servers and domains, that would cost me a lot of money. Although Apple will take 30% of the revenue, I can live with that in the early stages because the most important thing for me is to get the product to market as soon as possible. Actually thought Apple’s SMB program, the take rate is 15% now. So Web or App is not important in the early stage, time is important, if people need my product, it's easy to make a website one. More Users or More Valuable Users In November, I notice some users would like use my app, and they were meet paywall, but they never subscribe. I provided 7 day free trail, but it seem that they don’t like it. So I decide to change subscription to pay per use. Because as a user, I don’t like subscription as well, pay per use seem like more friendly. So I change from subscription to pay per use. People can afford $9.99 to subscribe monthly for unlimited use or pay $1.99 for each data they want(First purchase is $0.99 then $1.99). I was expecting more user to pay, but it was the complete opposite! Some users who would have paid a higher subscription fee are switching to a lower priced single payment. Users are encountering paywalls more often, and each time they need to make a decision about whether or not to pay, which increases the probability that they will abandon payment. This resulted in a 75% decrease in revenue in November. In fact, the mostly of my revenue comes from a handful of long-cycle subscribers, such as annual subscription. \\Few bring in most of the revenue,\\ that is the most important thing I learned. You don't need a lot of customers, you just need more valuable ones. That's why it's only right to design a mechanism to filter out high-value customers and focus on them, all the things you want do is just let more people into the filter, and from that point of view, subscription with free trial period is the best way, even if most people don't like it. The rule of 20/80 will always be there. The most important thing is always focus on the 20 percent things and people. Effort does not always guarantee rewards. Unless one engages in deep thinking, or most efforts are invalid. I have been working very hard to promote my product for a period of time. It’s about in November. I did a lot of job, such as write script to send message to my potential clients on Fiverr, post and write comments on others post on Reddit, find related questions and answer them on Quora, post and comments on Twitte, etc. During that period, I was exhausted every day, but the outcome did not meet my expectations. There is only little growth on App installation, even less revenue than before. That make me frustrated. I finally realized that If I need to put in a tremendous amount of effort just to make a little progress, there is must something wrong. So I stop 80% of promote work I have ever did, only keep app store search ad, which will bring a installation with less than $0.5 cost. Then I dive into long time and deeply thinking, I spent more time on reading books, investigate other product with great MRR, watch interviews with people who are already living the kind of life I aspire to live, for example, u/levelsio. These things have given me great inspiration, and my life has become easier. It seems that the life I anticipated when I resigned is getting closer. I also have a clearer understanding of my app. Meanwhile, MRR has been growing. This experience let me learn that effort does not always guarantee results. Many times, our efforts are just wishful thinking, they are invalid, do the right thing after deeply thinking is more important. What Next? My goal is reach $3K MRR, as same as my job payment, I will never stop to building things, and I will keep my currently lifestyle. I still don't know how to get more people to use my app, but levelsio's interviews give me some inspiration that I can verified something by manually instead of build a software. I plan to launch a trend analysis product based on the keyword data provided by my current app. I have always wanted to combine AI to build such a product, but I didn't know how to do it. Now I intend to manually complete it first and start software development once there are paying users. If you are interested to my App, you could try it.

#reddit#learn#$200

reddit

0

1

CivilLifeguard189•This week

Teaching an AI to Play Mario: A Learning Journey

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

#reddit#teaching#play

reddit

0

1

Suspicious_Dig_3849•This week

Advice Needed

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

#reddit#advice#needed

reddit

0

1

Any-Reserve-4403•This 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\

#reddit#learning#resources

reddit

0

1

Prudent_Ad_3114•This week

I'm Building an "AiExecutiveSuperAgent_Systems_Interface" between humanity and the Ai world, as well as each other... Let's Talk?

Ok... So look... This one is pretty crazy... I'm building an Ai Interface that knows me better than I know myself - Check, lots of people have this, either in reality with employees and family members, or with ai intelligence. But it doesn't just know Me... It knows how to talk with Me. It understands my language, because I've trained it to. I've also trained it to translate that to all my clients and HumanAgents, soon to become RobotAgents... The RESULT: I can literally just spend 1-18 hours talking to it, and things get DONE. Most of that time, I just say EXECUTE, or ENGAGE, or DRAFT, or DISPATCH. I feel like a secret agent communicating in codes with his agency 😂 Not great for the paranoiac in me, but it's easy to get that part under control, ya'll. It's like having a team of 10,000 people, all available 24/7, all perfectly synchronised to each other's communication styles, preferences and ultimately: WHAT DO YOU NEED ME TO DO. At the end of the it all, having run my single COMMAND through a thousand of those people, a Document is prepared that outlines the next 3 stages of the plan, along with instructions to the whole team for how to ENACT it. Sounds rather grand and wonderful... Even when I simply use it to help me come up with a filing system for my creative work... \\\\\\\\\\\\\\\\\\\\\\ Here's my current VISION, why I'm doing this AND why I'm doing it publicly despite it being top secret. VISION To create an army of User-Owned and Operated "AiSuperAgencies" which gather intelligence on the user, securely file and analyse it, and then construct a sub-army of agents and tools that work together to produce the desired output, for any Function in the Personal and Professional Lives of EVERYONE, EVERYWHERE, in 3-5 Years. To start, I'm building it for me and the 5-10 cleaners who've made it to Level 1 in my access system. They were sick of toxic employers, tyrannical agencies and greedy customers. They gathered around us (many came in, many went out, few stayed, took about a year for our core team of 3 Level 2 Cleaners. My goal has always been to never employ anyone. Just me, my Partner and the Cleaners. All Shared Owners in the system for delivering the right cleaner to the right house in our town, at the right time and without any dramas or arguments... I have a personal talent for resolving disputes, which has made working for and buying from my business a mostly enjoyable and upbeat experience, with a touch of mystery and a feeling that you're part of something big! It is a business that ran on Me. I put in my time, every day, building automated tool after automated tool. Hiring a contractor to do a job, scratching my head when it didn't add enough value to pay for itself, then just doing it myself again. I wanted to solve that problem. I'm trusting that the few who hear about it who actually see the potential, will just come join us, no dramas, just cool people partnering up! And those that don't, won't. No one could steal it, because it's Mine, and I'll just change the keys anyway loser! Enjoy digging through my past, you lunatic! I'm out here living Now. Anyways... It's lonely around here. I have a cleaning business that I run from my laptop, which means I can live anywhere, but I still had this big problem of time... NOT ENOUGH Oh Wait. It's Here.

#reddit#building#"aiexecutivesuperagent_systems_interface"

reddit

0

1

Prudent_Ad_3114•This week

I'm Building an "AiExecutiveSuperAgent_Systems_Interface" between humanity and the Ai world, as well as each other... Let's Talk?

Ok... So look... This one is pretty crazy... I'm building an Ai Interface that knows me better than I know myself - Check, lots of people have this, either in reality with employees and family members, or with ai intelligence. But it doesn't just know Me... It knows how to talk with Me. It understands my language, because I've trained it to. I've also trained it to translate that to all my clients and HumanAgents, soon to become RobotAgents... The RESULT: I can literally just spend 1-18 hours talking to it, and things get DONE. Most of that time, I just say EXECUTE, or ENGAGE, or DRAFT, or DISPATCH. I feel like a secret agent communicating in codes with his agency 😂 Not great for the paranoiac in me, but it's easy to get that part under control, ya'll. It's like having a team of 10,000 people, all available 24/7, all perfectly synchronised to each other's communication styles, preferences and ultimately: WHAT DO YOU NEED ME TO DO. At the end of the it all, having run my single COMMAND through a thousand of those people, a Document is prepared that outlines the next 3 stages of the plan, along with instructions to the whole team for how to ENACT it. Sounds rather grand and wonderful... Even when I simply use it to help me come up with a filing system for my creative work... \\\\\\\\\\\\\\\\\\\\\\ Here's my current VISION, why I'm doing this AND why I'm doing it publicly despite it being top secret. VISION To create an army of User-Owned and Operated "AiSuperAgencies" which gather intelligence on the user, securely file and analyse it, and then construct a sub-army of agents and tools that work together to produce the desired output, for any Function in the Personal and Professional Lives of EVERYONE, EVERYWHERE, in 3-5 Years. To start, I'm building it for me and the 5-10 cleaners who've made it to Level 1 in my access system. They were sick of toxic employers, tyrannical agencies and greedy customers. They gathered around us (many came in, many went out, few stayed, took about a year for our core team of 3 Level 2 Cleaners. My goal has always been to never employ anyone. Just me, my Partner and the Cleaners. All Shared Owners in the system for delivering the right cleaner to the right house in our town, at the right time and without any dramas or arguments... I have a personal talent for resolving disputes, which has made working for and buying from my business a mostly enjoyable and upbeat experience, with a touch of mystery and a feeling that you're part of something big! It is a business that ran on Me. I put in my time, every day, building automated tool after automated tool. Hiring a contractor to do a job, scratching my head when it didn't add enough value to pay for itself, then just doing it myself again. I wanted to solve that problem. I'm trusting that the few who hear about it who actually see the potential, will just come join us, no dramas, just cool people partnering up! And those that don't, won't. No one could steal it, because it's Mine, and I'll just change the keys anyway loser! Enjoy digging through my past, you lunatic! I'm out here living Now. Anyways... It's lonely around here. I have a cleaning business that I run from my laptop, which means I can live anywhere, but I still had this big problem of time... NOT ENOUGH Oh Wait. It's Here.

#reddit#building#"aiexecutivesuperagent_systems_interface"

reddit

0

1

MonkDi•This week

My Marketing App made $10,000 in 2024. Here is how I target to make $100,000 in 2025:

You totally get me, I think. It’s a bizarre feeling when you build something, and people appreciate it and are even ready to pay! Pleasant though) In early 2024 my mate and I created a marketing tool that generates ads, content and strategy blocks with a click – Aiter.io. Users can just insert a URL, hit the button and everything is ready. TBH, I built this tool because I’m too lazy to chat with ChatGPT) https://preview.redd.it/ew2kud7ceyde1.png?width=1140&format=png&auto=webp&s=f3fe5b67075858cea3d52278e8063113efa3b97e In 2024 we made $10,000, here is what worked for us: AI directories. Still is the best channel of traffic and clients for us. We listed on TAAFT and other directories scrape TAAFT, so, eventually, we became listed on all major ones. I wrote a Reddit post earlier that explained this process in detail. Email marketing. Gosh, I thought it was dead – I have never been so wrong! We set up automatic emails that share marketing insights and they have a \~25% open rate + consistently convert people. It works great. Product marketing. Having a free version really helps with word-of-mouth and leads, which can be converted via email. Also, we consistently worked on product improvement. I’d say, that our free updates give people a feeling that the devs care about their stuff that’s why they are more confident investing in it. Google Ads. TBH, we had a shitty landing page all the time because were busy with the product. So, Google Ads didn’t work well for us. But we’ve launched the 2.0 version which has a better landing page, and will try it again. Influencers. Worked well for us, but we didn’t pay a dime for this. They just found our tool on directories and created videos about Aiter, so it was a sporadic marketing channel for us. We hope to change it in 2025. We see that our product works and attracts the audience, so we want to deliver and get more in 2025. Here is the plan: Product: add ad banners and video generation. So far, we generate only text data and it’s not so valuable in the time of ChatGPT and Claude. But to generate a high-quality ad banner is still challenging, so we put this on our roadmap. Another feature – one-click market analysis to get marketing insights. Become a TOP50 tool on TAAFT. We’ve become a top tool in our category (content generation) but will need to promote our profile on the profile far more aggressively to get into TOP50 Email marketing. We are fools because we almost didn’t have product emails that explain how it works. Will fix it. Also, we are considering participating more in paid newsletters, like collaborating with Substack influencers. Youtube marketing. Search for low-tail marketing keywords on YouTube and create videos on them, placing my product in them. Blog. Our new platform is Webflow which gives a lot of flexibility in terms of blogging. So, we will repeat the YouTube strategy with blogging. Paid marketing. With an updated landing page, we hope that paid campaigns will work better. We plan to launch campaigns that target different jobs to be done and customer objections to find the right message. Product Management. For 2025, our two key product metrics are retention and product activation rate. For this, we plan to simplify onboarding and make it simpler as well as conduct a lot of in-depth interviews to understand how we can retain users better. Funding. All of this exciting stuff requires money, so we are in the process of securing funding (fingers crossed). Having an indie project is exciting and invigorating. With all these activities, I hope we will achieve the goal of $100,000 in 2025. And what are your goals and marketing steps for 2025? Or maybe you could share some exciting marketing ideas I overlooked?

#reddit#marketing#made

reddit

0

1

jottrled•This week

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

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

#reddit#went#solopreneur

reddit

0

0.857

ricky0603•This week

What I learn from my $200 MRR App I built 4 months ago

4 month ago, I am just a 10-years experienced product manager without any software development experience. I have an $3K/month job, but I am so tired, I don’t like my life, don’t like my boss, don’t like my daily work, that make me feeling I already died however I am still living. I yearn for freedom and want to live each day the way I want to. So I quit my job, and become a Indie developer to build my own business, my own app, even my own life. I am so grateful for this time and experience, now my app reach $200 MRR, still very little compared to my previous salary, but I never regret. I have learned lots of things from this time and experience, more than I had in last 10 years. Here is the time-line of my App: ​ Sep 2023: Launch first version to iOS App store Oct 2023: Release in-app-purchase features and have first subscriber, the revenue in October is $154 Nov 2023: Change from subscription to pay per use, and I did lots of marketing jobs in November, however, the revenue reduced to only $40. Dec 2023: Change back to subscription, and stop some invalid marketing jobs, only keep the ones that actually work. I almost did nothing in December, and the revenue come to $243. During this process, I have learned lots of things, there are some of them that I think could help you as well. Web or App My App is an iOS app that only can running on Apple’s device such like iPhone/iPad or Mac with Apple silicon. Many people ask me why my product is an iOS app not a website, because they don’t have any Apple device. It's true that promoting an app is much harder than promoting a website. However I am now very glad I made an App and not a website! If I make a website, I don't think it's possible to make $100 in the first month. My App is about keyword research, to help people find some ideas from search keyword, because every keyword people searched in Google are representing a real need of them, also can be used in SEO field. However there are a lot of website tools about keyword research, some of them are famous like Ahrefs, SEMrush… I have no intention of competing with them. Actually I don’t have any chance. While in app store, there are little apps about keyword research, each of them have terrible data and user experience, that means if my app has better data and experience that could be my chance. In fact, the App store brings me 20 organic installs a day that Google would never have been able to bring me if I had a website, at least for the first few months. Furthermore, Apple nearly did everything for developer, I don’t need to care about user login, payment and so on, Apple did everything, I just need to call their API, that save lots of time, if I build a website, I need to implement login and payment by myself, that would add some extra work. Not to mention I'd need to buy servers and domains, that would cost me a lot of money. Although Apple will take 30% of the revenue, I can live with that in the early stages because the most important thing for me is to get the product to market as soon as possible. Actually thought Apple’s SMB program, the take rate is 15% now. So Web or App is not important in the early stage, time is important, if people need my product, it's easy to make a website one. More Users or More Valuable Users In November, I notice some users would like use my app, and they were meet paywall, but they never subscribe. I provided 7 day free trail, but it seem that they don’t like it. So I decide to change subscription to pay per use. Because as a user, I don’t like subscription as well, pay per use seem like more friendly. So I change from subscription to pay per use. People can afford $9.99 to subscribe monthly for unlimited use or pay $1.99 for each data they want(First purchase is $0.99 then $1.99). I was expecting more user to pay, but it was the complete opposite! Some users who would have paid a higher subscription fee are switching to a lower priced single payment. Users are encountering paywalls more often, and each time they need to make a decision about whether or not to pay, which increases the probability that they will abandon payment. This resulted in a 75% decrease in revenue in November. In fact, the mostly of my revenue comes from a handful of long-cycle subscribers, such as annual subscription. Few bring in most of the revenue, that is the most important thing I learned. You don't need a lot of customers, you just need more valuable ones. That's why it's only right to design a mechanism to filter out high-value customers and focus on them, all the things you want do is just let more people into the filter, and from that point of view, subscription with free trial period is the best way, even if most people don't like it. The rule of 20/80 will always be there. The most important thing is always focus on the 20 percent things and people. Effort does not always guarantee rewards. Unless one engages in deep thinking, or most efforts are invalid. I have been working very hard to promote my product for a period of time. It’s about in November. I did a lot of job, such as write script to send message to my potential clients on Fiverr, post and write comments on others post on Reddit, find related questions and answer them on Quora, post and comments on Twitte, etc. During that period, I was exhausted every day, but the outcome did not meet my expectations. There is only little growth on App installation, even less revenue than before. That make me frustrated. I finally realized that If I need to put in a tremendous amount of effort just to make a little progress, there is must something wrong. So I stop 80% of promote work I have ever did, only keep app store search ad, which will bring a installation with less than $0.5 cost. Then I dive into long time and deeply thinking, I spent more time on reading books, investigate other product with great MRR, watch interviews with people who are already living the kind of life I aspire to live, for example, u/levelsio. These things have given me great inspiration, and my life has become easier. It seems that the life I anticipated when I resigned is getting closer. I also have a clearer understanding of my app. Meanwhile, MRR has been growing. This experience let me learn that effort does not always guarantee results. Many times, our efforts are just wishful thinking, they are invalid, do the right thing after deeply thinking is more important. What Next? My goal is reach $3K MRR, as same as my job payment, I will never stop to building things, and I will keep my currently lifestyle. I still don't know how to get more people to use my app, but levelsio's interviews give me some inspiration that I can verified something by manually instead of build a software. I plan to launch a trend analysis product based on the keyword data provided by my current app. I have always wanted to combine AI to build such a product, but I didn't know how to do it. Now I intend to manually complete it first and start software development once there are paying users. If you are interested to my App, you could try it. Gotrends

#reddit#learn#$200

reddit

0

1

iamx9000again•This week

[D] Overwhelmed by fast advances in recent weeks

I was watching the GTC keynote and became entirely overwhelmed by the amount of progress achieved from last year. I'm wondering how everyone else feels. ​ Firstly, the entire ChatGPT, GPT-3/GPT-4 chaos has been going on for a few weeks, with everyone scrambling left and right to integrate chatbots into their apps, products, websites. Twitter is flooded with new product ideas, how to speed up the process from idea to product, countless promp engineering blogs, tips, tricks, paid courses. ​ Not only was ChatGPT disruptive, but a few days later, Microsoft and Google also released their models and integrated them into their search engines. Microsoft also integrated its LLM into its Office suite. It all happenned overnight. I understand that they've started integrating them along the way, but still, it seems like it hapenned way too fast. This tweet encompases the past few weeks perfectly https://twitter.com/AlphaSignalAI/status/1638235815137386508 , on a random Tuesday countless products are released that seem revolutionary. ​ In addition to the language models, there are also the generative art models that have been slowly rising in mainstream recognition. Now Midjourney AI is known by a lot of people who are not even remotely connected to the AI space. ​ For the past few weeks, reading Twitter, I've felt completely overwhelmed, as if the entire AI space is moving beyond at lightning speed, whilst around me we're just slowly training models, adding some data, and not seeing much improvement, being stuck on coming up with "new ideas, that set us apart". ​ Watching the GTC keynote from NVIDIA I was again, completely overwhelmed by how much is being developed throughout all the different domains. The ASML EUV (microchip making system) was incredible, I have no idea how it does lithography and to me it still seems like magic. The Grace CPU with 2 dies (although I think Apple was the first to do it?) and 100 GB RAM, all in a small form factor. There were a lot more different hardware servers that I just blanked out at some point. The omniverse sim engine looks incredible, almost real life (I wonder how much of a domain shift there is between real and sim considering how real the sim looks). Beyond it being cool and usable to train on synthetic data, the car manufacturers use it to optimize their pipelines. This change in perspective, of using these tools for other goals than those they were designed for I find the most interesting. ​ The hardware part may be old news, as I don't really follow it, however the software part is just as incredible. NVIDIA AI foundations (language, image, biology models), just packaging everything together like a sandwich. Getty, Shutterstock and Adobe will use the generative models to create images. Again, already these huge juggernauts are already integrated. ​ I can't believe the point where we're at. We can use AI to write code, create art, create audiobooks using Britney Spear's voice, create an interactive chatbot to converse with books, create 3D real-time avatars, generate new proteins (?i'm lost on this one), create an anime and countless other scenarios. Sure, they're not perfect, but the fact that we can do all that in the first place is amazing. ​ As Huang said in his keynote, companies want to develop "disruptive products and business models". I feel like this is what I've seen lately. Everyone wants to be the one that does something first, just throwing anything and everything at the wall and seeing what sticks. ​ In conclusion, I'm feeling like the world is moving so fast around me whilst I'm standing still. I want to not read anything anymore and just wait until everything dies down abit, just so I can get my bearings. However, I think this is unfeasible. I fear we'll keep going in a frenzy until we just burn ourselves at some point. ​ How are you all fairing? How do you feel about this frenzy in the AI space? What are you the most excited about?

#reddit#overwhelmed#fast

reddit

0

0

AvvYaa•This 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. ​

#reddit#tried#gemini

reddit

0

0.667

milaworld•This week

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

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

#reddit#stability#ai’s

reddit

0

0.667

milaworld•This week

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

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

#reddit#stability#ai’s

reddit

0

1

LightGreenSquash•This week

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

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

#reddit#"grokking"#deep

reddit

0

1

Educational_News_371•This week

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

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

#reddit#[d]stuck#hell:

reddit

0

0.667

milaworld•This week

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

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

#reddit#stability#ai’s

reddit

0

0

Moist_Stuff4509•This week

[P] A Call to AI Devs and Entrepreneurs

Hey, I am thinking about potentially creating a global yet small community of AI devs and entrepreneurs. I know that a lot of communities already exist, but this one would be specific for AI entrepreneurs and devs to build together. I don’t want it to be big, since I want it to be active. That is the way to keep it interesting and avoid the noise. We could use slack for example, to make it a bit more work related than just for soft engagements. We could tag everyone with the skills that they have and interest, to make it easy for people to connect and start building stuff. Tags could be tech, growth, product, fundraising, business, etc. The goal would be to actually launch new products in the AI space. I am a serial entrepreneur myself with an exit with one of the biggest providers in our vertical a few years ago. I am finishing a PhD in AI and have been working in the AI field in the industry for many years now. I think this is a unique moment in time. The market will change substantially as AI brings new capabilities to the game, but my perspective is that the business models for AI are yet to be built. The bottom line is that as with any platform shift, we will see the creation of the Googles of the future during this time. I think that we have much more probability of success if we work together to try to conquer the market step by step. My feeling is that the grind will be much harder on this wave than any other for a variety of reasons, from the macroeconomic environment to the very fast pace of how things are moving. I know that communities exist already, I am in a program with an accelerator myself, but I would scope this new community in a different way. It would be the place to meet and to build together. Everyone sharing the same pains, being in the scout for the new tech that just launched, helping to push out new deals, connect with VCs, all those things. Let me know if this would interest you.

#reddit#call#devs

reddit

0

1

iamx9000again•This week

[D] Overwhelmed by fast advances in recent weeks

I was watching the GTC keynote and became entirely overwhelmed by the amount of progress achieved from last year. I'm wondering how everyone else feels. ​ Firstly, the entire ChatGPT, GPT-3/GPT-4 chaos has been going on for a few weeks, with everyone scrambling left and right to integrate chatbots into their apps, products, websites. Twitter is flooded with new product ideas, how to speed up the process from idea to product, countless promp engineering blogs, tips, tricks, paid courses. ​ Not only was ChatGPT disruptive, but a few days later, Microsoft and Google also released their models and integrated them into their search engines. Microsoft also integrated its LLM into its Office suite. It all happenned overnight. I understand that they've started integrating them along the way, but still, it seems like it hapenned way too fast. This tweet encompases the past few weeks perfectly https://twitter.com/AlphaSignalAI/status/1638235815137386508 , on a random Tuesday countless products are released that seem revolutionary. ​ In addition to the language models, there are also the generative art models that have been slowly rising in mainstream recognition. Now Midjourney AI is known by a lot of people who are not even remotely connected to the AI space. ​ For the past few weeks, reading Twitter, I've felt completely overwhelmed, as if the entire AI space is moving beyond at lightning speed, whilst around me we're just slowly training models, adding some data, and not seeing much improvement, being stuck on coming up with "new ideas, that set us apart". ​ Watching the GTC keynote from NVIDIA I was again, completely overwhelmed by how much is being developed throughout all the different domains. The ASML EUV (microchip making system) was incredible, I have no idea how it does lithography and to me it still seems like magic. The Grace CPU with 2 dies (although I think Apple was the first to do it?) and 100 GB RAM, all in a small form factor. There were a lot more different hardware servers that I just blanked out at some point. The omniverse sim engine looks incredible, almost real life (I wonder how much of a domain shift there is between real and sim considering how real the sim looks). Beyond it being cool and usable to train on synthetic data, the car manufacturers use it to optimize their pipelines. This change in perspective, of using these tools for other goals than those they were designed for I find the most interesting. ​ The hardware part may be old news, as I don't really follow it, however the software part is just as incredible. NVIDIA AI foundations (language, image, biology models), just packaging everything together like a sandwich. Getty, Shutterstock and Adobe will use the generative models to create images. Again, already these huge juggernauts are already integrated. ​ I can't believe the point where we're at. We can use AI to write code, create art, create audiobooks using Britney Spear's voice, create an interactive chatbot to converse with books, create 3D real-time avatars, generate new proteins (?i'm lost on this one), create an anime and countless other scenarios. Sure, they're not perfect, but the fact that we can do all that in the first place is amazing. ​ As Huang said in his keynote, companies want to develop "disruptive products and business models". I feel like this is what I've seen lately. Everyone wants to be the one that does something first, just throwing anything and everything at the wall and seeing what sticks. ​ In conclusion, I'm feeling like the world is moving so fast around me whilst I'm standing still. I want to not read anything anymore and just wait until everything dies down abit, just so I can get my bearings. However, I think this is unfeasible. I fear we'll keep going in a frenzy until we just burn ourselves at some point. ​ How are you all fairing? How do you feel about this frenzy in the AI space? What are you the most excited about?

#reddit#overwhelmed#fast

reddit

0

0.667

milaworld•This week

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

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

#reddit#stability#ai’s

reddit

0

1

vnjxk•This week

I built a no-code solution for UI-driven AI applications, But I'm lost on the business side - How to market and transform it into a viable business?

Hey everyone! sorry for the "no-code solution for UI-driven AI applications" (counted 3 buzzwords), couldn't find a way to describe it so I asked claude I'm in a bit of a pickle and could use some wisdom from this awesome community. A few months back, I developed a tool that I'm pretty excited about, but I hit a wall and shelved it. Now I'm feeling the itch to dive back in, but I'm struggling with the business side of things. Here's the gist: It's a drag-and-drop UI builder You can define buttons to execute logic and AI behind the scenes (using no-code) It uses the UI built for both input and output The good news: The site is functional and looks pretty slick (except the produced UI from the builder). Most features are implemented, though I still need to polish up the UI blocks and add more workflow nodes. The not-so-good news: I have zero users and no clear monetization strategy. The tool is so versatile that I'm having trouble figuring out how to even approach marketing it effectively. So, I turn to you guys in hopes of finding a direction: Any ideas on potential monetization strategies for a tool like this? How would you approach marketing such a multi-purpose product? Has anyone been in a similar situation? How did you move forward? generally I'd love to hear your thoughts, experiences, or even wild ideas! Thanks in advance for any insights you can share. The site is withui.com you can test it out

#reddit#built#no-code

reddit

0

1

hopefully_useful•This week

We made $325k in 2023 from AI products, starting from 0, with no-code, no funding and no audience

I met my co-founder in late 2022 after an introduction from a mutual friend to talk about how to find contract Product Management roles. I was sporadically contracting at start-up at the time and he had just come out of another start-up that was wiped out by the pandemic. We hit it off, talking about ideas, sharing what other indie-hackers were doing, and given GPT-3’s prominence at the time, we started throwing around ideas about things we could build with it, if nothing else, just to learn. I should caveat, neither of us were AI experts when starting out, everything we learned has been through Twitter and blogs, my background is as an accountant, and his a consultant. Here’s how it went since then: &#x200B; Nov 2022 (+$50) \- We built a simple tool in around a week using GPT-3 fine-tuning and a no-code tool (Bubble) that helped UK university students write their personal statements for their applications \- We set some Google Ads going and managed to make a few sales (\~$50) in the first week \- OpenAI were still approving applications at the time and said this went against their “ethics” so we had to take it down &#x200B; Dec 2022 (+$200) \- We couldn’t stop coming up with ideas related to AI fine-tuning, but realised it was almost impossible to decide which to pursue \- We needed a deadline to force us so we signed up for the Ben’s Bites hackathon in late December \- In a week, we built and launched a no-code fine-tuning platform, allowing people to create fine-tuned models by dragging and dropping an Excel file onto it \- We launched it on Product Hunt, having no idea how to price it, and somehow managed to get \~2,000 visitors on the site and make 2 sales at $99 &#x200B; Jan 2023 (+$3,000) \- We doubled down on the fine-tuning idea and managed to get up to \~$300 MRR, plus a bunch of one-time sales and a few paid calls to help people get the most out of their models \- We quickly realised that people didn’t want to curate models themselves, they just wanted to dump data and get magic out \- That was when we saw people building “Talk with x book/podcast” on Twitter as side projects and realised that was the missing piece, we needed to turn it into a tool \- We started working on the new product in late January &#x200B; Feb 2023 (+$9,000) \- We started pre-selling access to an MVP for the new product, which allowed people to “chat with their data/content”, we got $5,000 in pre-sales, more than we made from the previous product in total \- By mid-February, after 3 weeks of building we were able to launch and immediately managed to get traction, getting to $1k MRR in < 1 week, building on the hype of ChatGPT and AI (we were very lucky here) &#x200B; Mar - Jul 2023 (+$98,000) \- We worked all the waking hours to keep up with customer demand, bugs, OpenAI issues \- We built integrations for a bunch of services like Slack, Teams, Wordpress etc, added tons of new functionality and continue talking to customers every day \- We managed to grow to $17k MRR (just about enough to cover our living expenses and costs in London) through building in public on Twitter, newsletters and AI directories (and a million other little things) \- We sold our fine-tuning platform for \~$20k and our university project for \~$3k on Acquire &#x200B; Aug 2023 (+$100,000) \- We did some custom development work based on our own product for a customer that proved pretty lucrative &#x200B; Sep - Oct 2023 (+$62,000) \- After 8 months of building constantly, we started digging more seriously into our usage and saw subscriptions plateauing \- We talked to and analysed all our paying users to identify the main use cases and found 75% were for SaaS customer support \- We took the leap to completely rebuild a version of our product around this use case, our biggest to date (especially given most features with no-code took us <1 day) &#x200B; Nov - Dec 2023 (+$53,000) \- We picked up some small custom development work that utilised our own tech \- We’re sitting at around $22k MRR now with a few bigger clients signed up and coming soon \- After 2 months of building and talking to users, we managed to finish our “v2” of our product, focussed squarely on SaaS customer support and launched it today. &#x200B; We have no idea what the response will be to this new version, but we’re pretty happy with it, but couldn’t have planned anything that happened to us in 2023 so who knows what will come of 2024, we just know that we are going to be learning a ton more. &#x200B; Overall, it is probably the most I have had to think in my life - other jobs you can zone out from time to time or rely on someone else if you aren’t feeling it - not when you are doing this, case and point, I am writing this with a banging head-cold right now, but wanted to get this done. A few more things we have learned along the way - context switching is unreal, as is keeping up with, learning and reacting to AI. There isn’t a moment of the day I am not thinking about what we do next. But while in some way we now have hundreds of bosses (our customers) I still haven’t felt this free and can’t imagine ever going back to work for someone else. Next year we’re really hoping to figure out some repeatable distribution channels and personally, I want to get a lot better at creating content/writing, this is a first step! Hope this helps someone else reading this to just try starting something and see what happens.

#reddit#made#$325k

reddit

0

0.895

matthewbarby•This week

The delicate balance of building an online community business

Hey /r/Entrepreneur 👋 Just under two years ago I launched an online community business called Traffic Think Tank with two other co-founders, Nick Eubanks and Ian Howells. As a Traffic Think Tank customer you (currently) pay $119 a month to get access to our online community, which is run through Slack. The community is focused on helping you learn various aspects of marketing, with a particular focus on search engine optimization (SEO). Alongside access to the Slack community, we publish new educational video content from outside experts every week that all customers have access to. At the time of writing, Traffic Think Tank has around 650 members spanning across 17 of the 24 different global time zones. I was on a business trip over in Sydney recently, and during my time there I met up with some of our Australia-based community members. During dinner I was asked by several of them how the idea for Traffic Think Tank came about and what steps we took to validate that the idea was worth pursuing.  This is what I told them… How it all began It all started with a personal need. Nick, an already successful entrepreneur and owner of a marketing agency, had tested out an early version Traffic Think Tank in early 2017. He offered real-time consulting for around ten customers that he ran from Slack. He would publish some educational videos and offer his advice on projects that the members were running. The initial test went well, but it was tough to maintain on his own and he had to charge a fairly high price to make it worth his time. That’s when he spoke to me and Ian about turning this idea into something much bigger. Both Ian and I offered something slightly different to Nick. We’ve both spent time in senior positions at marketing agencies, but currently hold senior director positions in 2,000+ public employee companies (HubSpot and LendingTree). Alongside this, as a trio we could really ramp up the quality and quantity of content within the community, spread out the administrative workload and just generally have more resources to throw at getting this thing off the ground. Admittedly, Nick was much more optimistic about the potential of Traffic Think Tank – something I’m very thankful for now – whereas Ian and I were in the camp of “you’re out of your mind if you think hundreds of people are going to pay us to be a part of a Slack channel”. To validate the idea at scale, we decided that we’d get an initial MVP of the community up and running with a goal of reaching 100 paying customers in the first six months. If we achieved that, we’d validated that it was a viable business and we would continue to pursue it. If not, we’d kill it. We spent the next month building out the initial tech stack that enabled us to accept payments, do basic user management to the Slack channel, and get a one-page website up and running with information on what Traffic Think Tank was all about.  After this was ready, we doubled down on getting some initial content created for members – I mean, we couldn’t have people just land in an empty Slack channel, could we? We created around ten initial videos, 20 or so articles and then some long threads full of useful information within the Slack channel so that members would have some content to pour into right from the beginning.  Then, it was time to go live. The first 100 customers Fortunately, both Nick and I had built a somewhat substantial following in the SEO space over the previous 5-10 years, so we at least had a large email list to tap into (a total of around 40,000 people). We queued up some launch emails, set an initial price of $99 per month and pressed send. [\[LINK\] The launch email I sent to my subscribers announcing Traffic Think Tank](https://mailchi.mp/matthewbarby/future-of-marketing-1128181) What we didn’t expect was to sell all of the initial 100 membership spots in the first 72 hours. “Shit. What do we do now? Are we ready for this many people? Are we providing them with enough value? What if something breaks in our tech stack? What if they don’t like the content? What if everyone hates Slack?” All of these were thoughts running through my head. This brings me to the first great decision we made: we closed down new membership intake for 3 months so that we could focus completely on adding value to the first cohort of users. The right thing at the right time SEO is somewhat of a dark art to many people that are trying to learn about it for the first time. There’s hundreds of thousands (possibly millions) of articles and videos online that talk about how to do SEO.  Some of it’s good advice; a lot of it is very bad advice.  Add to this that the barrier to entry of claiming to be an “expert” in SEO is practically non-existent and you have a recipe for disaster. This is why, for a long time, individuals involved in SEO have flocked in their masses to online communities for information and to bounce ideas off of others in the space. Forums like SEObook, Black Hat World, WickedFire, Inbound.org, /r/BigSEO, and many more have, at one time, been called home by many SEOs.  In recent times, these communities have either been closed down or just simply haven’t adapted to the changing needs of the community – one of those needs being real-time feedback on real-world problems.  The other big need that we all spotted and personally had was the ability to openly share the things that are working – and the things that aren’t – in SEO within a private forum. Not everyone wanted to share their secret sauce with the world. One of the main reasons we chose Slack as the platform to run our community on was the fact that it solved these two core needs. It gave the ability to communicate in real-time across multiple devices, and all of the information shared within it was outside of the public domain. The other problem that plagued a lot of these early communities was spam. Most of them were web-based forums that were free to access. That meant they became a breeding ground for people trying to either sell their services or promote their own content – neither of which is conducive to building a thriving community. This was our main motivation for charging a monthly fee to access Traffic Think Tank. We spent a lot of time thinking through pricing. It needed to be enough money that people would be motivated to really make use of their membership and act in a way that’s beneficial to the community, but not too much money that it became cost prohibitive to the people that would benefit from it the most. Considering that most of our members would typically spend between $200-800 per month on SEO software, $99 initially felt like the perfect balance. Growing pains The first three months of running the community went by without any major hiccups. Members were incredibly patient with us, gave us great feedback and were incredibly helpful and accommodating to other members. Messages were being posted every day, with Nick, Ian and myself seeding most of the engagement at this stage.  With everything going smoothly, we decided that it was time to open the doors to another intake of new members. At this point we’d accumulated a backlog of people on our waiting list, so we knew that simply opening our doors would result in another large intake. Adding more members to a community has a direct impact on the value that each member receives. For Traffic Think Tank in particular, the value for members comes from three areas: The ability to have your questions answered by me, Nick and Ian, as well as other members of the community. The access to a large library of exclusive content. The ability to build connections with the wider community. In the early stages of membership growth, there was a big emphasis on the first of those three points. We didn’t have an enormous content library, nor did we have a particularly large community of members, so a lot of the value came from getting a lot of one-to-one time with the community founders. [\[IMAGE\] Screenshot of engagement within the Traffic Think Tank Slack community](https://cdn.shortpixel.ai/client/qglossy,retimg,w_1322/https://www.matthewbarby.com/wp-content/uploads/2019/08/Community-Engagement-in-Traffic-Think-Tank.png) The good thing about having 100 members was that it was just about feasible to give each and every member some one-to-one time within the month, which really helped us to deliver those moments of delight that the community needed early on. Two-and-a-half months after we launched Traffic Think Tank, we opened the doors to another 250 people, taking our total number of members to 350. This is where we experienced our first growing pains.  Our original members had become used to being able to drop us direct messages and expect an almost instant response, but this wasn’t feasible anymore. There were too many people, and we needed to create a shift in behavior. We needed more value to come from the community engaging with one another or we’d never be able to scale beyond this level. We started to really pay attention to engagement metrics; how many people were logging in every day, and of those, how many were actually posting messages within public channels.  We asked members that were logging in a lot but weren’t posting (the “lurkers”) why that was the case. We also asked the members that engaged in the community the most what motivated them to post regularly. We learned a lot from doing this. We found that the large majority of highly-engaged members had much more experience in SEO, whereas most of the “lurkers” were beginners. This meant that most of the information being shared in the community was very advanced, with a lot of feedback from the beginners in the group being that they “didn’t want to ask a stupid question”.  As managers of the community, we needed to facilitate conversations that catered to all of our members, not just those at a certain level of skill. To tackle this problem, we created a number of new channels that had a much deeper focus on beginner topics so novice members had a safe place to ask questions without judgment.  We also started running live video Q&As each month where we’d answer questions submitted by the community. This gave our members one-on-one time with me, Nick and Ian, but spread the value of these conversations across the whole community rather than them being hidden within private messages. As a result of these changes, we found that the more experienced members in the community were really enjoying sharing their knowledge with those with less experience. The number of replies within each question thread was really starting to increase, and the community started to shift away from just being a bunch of threads created by me, Nick and Ian to a thriving forum of diverse topics compiled by a diverse set of individuals. This is what we’d always wanted. A true community. It was starting to happen. [\[IMAGE\] Chart showing community engagement vs individual member value](https://cdn.shortpixel.ai/client/qglossy,retimg,w_1602/https://www.matthewbarby.com/wp-content/uploads/2019/08/Community-Engagement-Balance-Graph.jpg) At the same time, we started to realize that we’ll eventually reach a tipping point where there’ll be too much content for us to manage and our members to engage with. When we reach this point, the community will be tough to follow and the quality of any given post will go down. Not only that, but the community will become increasingly difficult to moderate. We’re not there yet, but we recognize that this will come, and we’ll have to adjust our model again. Advocating advocacy As we started to feel more comfortable about the value that members were receiving, we made the decision to indefinitely open for new members. At the same time, we increased the price of membership (from $99 a month to $119) in a bid to strike the right balance between profitability as a business and to slow down the rate at which we were reaching the tipping point of community size. We also made the decision to repay all of our early adopters by grandfathering them in to the original pricing – and committing to always do this in the future. Despite the price increase, we saw a continued flow of new members come into the community. The craziest part about this was that we were doing practically no marketing activities to encourage new members– this was all coming from word of mouth. Our members were getting enough value from the community that they were recommending it to their friends, colleagues and business partners.  The scale at which this was happening really took us by surprise and it told us one thing very clearly: delivering more value to members resulted in more value being delivered to the business. This is a wonderful dynamic to have because it perfectly aligns the incentives on both sides. We’d said from the start that we wouldn’t sacrifice value to members for more revenue – this is something that all three of us felt very strongly about. First and foremost, we wanted to create a community that delivered value to its members and was run in a way that aligned with our values as people. If we could find a way to stimulate brand advocacy, while also tightening the bonds between all of our individual community members, we’d be boosting both customer retention and customer acquisition in the same motion. This became our next big focus. [\[TWEET\] Adam, one of our members wore his Traffic Think Tank t-shirt in the Sahara desert](https://twitter.com/AdamGSteele/status/1130892481099382784) We started with some simple things: We shipped out Traffic Think Tank branded T-shirts to all new members. We’d call out each of the individuals that would submit questions to our live Q&A sessions and thank them live on air. We set up a new channel that was dedicated to sharing a quick introduction to who you are, what you do and where you’re based for all new members. We’d created a jobs channel and a marketplace for selling, buying and trading services with other members. Our monthly “blind dates” calls were started where you’d be randomly grouped with 3-4 other community members so that you could hop on a call to get to know each other better. The Traffic Think Tank In Real Life (IRL)* channel was born, which enabled members to facilitate in-person meetups with each other. In particular, we saw that as members started to meet in person or via calls the community itself was feeling more and more like a family. It became much closer knit and some members started to build up a really positive reputation for being particularly helpful to other members, or for having really strong knowledge in a specific area. [\[TWEET\] Dinner with some of the Traffic Think Tank members in Brighton, UK](https://twitter.com/matthewbarby/status/1117175584080134149) Nick, Ian and I would go out of our way to try and meet with members in real life wherever we could. I was taken aback by how appreciative people were for us doing this, and it also served as an invaluable way to gain honest feedback from members. There was another trend that we’d observed that we didn’t really expect to happen. More and more members were doing business with each another. We’ve had people find new jobs through the community, sell businesses to other members, launch joint ventures together and bring members in as consultants to their business. This has probably been the most rewarding thing to watch, and it was clear that the deeper relationships that our members were forming were resulting in an increased level of trust to work with each other. We wanted to harness this and take it to a new level. This brought us to arguably the best decision we’ve made so far running Traffic Think Tank… we were going to run a big live event for our members. I have no idea what I’m doing It’s the first week of January 2019 and we’re less than three weeks away from Traffic Think Tank LIVE, our first ever in-person event hosting 150 people, most of which are Traffic Think Tank members. It's like an ongoing nightmare I can’t wake up from. That was Nick’s response in our private admin channel to myself and Ian when I asked if they were finding the run-up to the event as stressful as I was. I think that all three of us were riding on such a high from how the community was growing that we felt like we could do anything. Running an event? How hard can it be? Well, turns out it’s really hard. We had seven different speakers flying over from around the world to speak at the event, there was a pre- and after event party, and we’d planned a charity dinner where we would take ten attendees (picked at random via a raffle) out for a fancy meal. Oh, and Nick, Ian and I were hosting a live Q&A session on stage. It wasn’t until precisely 48 hours before the event that we’d realized we didn’t have any microphones, nor had a large amount of the swag we’d ordered arrived. Plus, a giant storm had hit Philly causing a TON of flight cancellations. Perfect. Just perfect. This was honestly the tip of the iceberg. We hadn’t thought about who was going to run the registration desk, who would be taking photos during the event and who would actually field questions from the audience while all three of us sat on stage for our live Q&A panel. Turns out that the answer to all of those questions were my wife, Laura, and Nick’s wife, Kelley. Thankfully, they were on hand to save our asses. The weeks running up to the event were honestly some of the most stressful of my life. We sold around 50% of our ticket allocation within the final two weeks before the event. All of the event organizers told us this would happen, but did we believe them? Hell no!  Imagine having two weeks until the big day and as it stood half of the room would be completely empty. I was ready to fly most of my extended family over just to make it look remotely busy. [\[IMAGE\] One of our speakers, Ryan Stewart, presenting at Traffic Think Tank LIVE](https://cdn.shortpixel.ai/client/qglossy,retimg,w_1920/https://www.matthewbarby.com/wp-content/uploads/2019/08/Traffic-Think-Tank-LIVE-Ryan-Presenting.jpg) Thankfully, if all came together. We managed to acquire some microphones, the swag arrived on the morning of the event, all of our speakers were able to make it on time and the weather just about held up so that our entire allocation of ticket holders was able to make it to the event. We pooled together and I’m proud to say that the event was a huge success. While we made a substantial financial loss on the event itself, January saw a huge spike in new members, which more than recouped our losses. Not only that, but we got to hang out with a load of our members all day while they said really nice things about the thing we’d built. It was both exhausting and incredibly rewarding. Bring on Traffic Think Tank LIVE 2020! (This time we’re hiring an event manager...)   The road ahead Fast forward to today (August 2019) and Traffic Think Tank has over 650 members. The biggest challenges that we’re tackling right now include making sure the most interesting conversations and best content surfaces to the top of the community, making Slack more searchable (this is ultimately one of its flaws as a platform) and giving members a quicker way to find the exclusive content that we create. You’ll notice there’s a pretty clear theme here. In the past 30 days, 4,566 messages were posted in public channels inside Traffic Think Tank. If you add on any messages posted inside private direct messages, this number rises to 21,612. That’s a lot of messages. To solve these challenges and enable further scale in the future, we’ve invested a bunch of cash and our time into building out a full learning management system (LMS) that all members will get access to alongside the Slack community. The LMS will be a web-based portal that houses all of the video content we produce. It will also  provide an account admin section where users can update or change their billing information (they have to email us to do this right now, which isn’t ideal), a list of membership perks and discounts with our partners, and a list of links to some of the best threads within Slack – when clicked, these will drop you directly into Slack. [\[IMAGE\] Designs for the new learning management system (LMS)](https://cdn.shortpixel.ai/client/qglossy,retimg,w_2378/https://www.matthewbarby.com/wp-content/uploads/2019/08/Traffic-Think-Tank-LMS.png) It’s not been easy, but we’re 95% of the way through this and I’m certain that it will have a hugely positive impact on the experience for our members. Alongside this we hired a community manager, Liz, who supports with any questions that our members have, coordinates with external experts to arrange webinars for the community, helps with new member onboarding, and has tightened up some of our processes around billing and general accounts admin. This was a great decision. Finally, we’ve started planning next year’s live event, which we plan to more than double in size to 350 attendees, and we decided to pick a slightly warmer location in Miami this time out. Stay tuned for me to have a complete meltdown 3 weeks from the event. Final thoughts When I look back on the journey we’ve had so far building Traffic Think Tank, there’s one very important piece to this puzzle that’s made all of this work that I’ve failed to mention so far: co-founder alignment. Building a community is a balancing act that relies heavily on those in charge being completely aligned. Nick, Ian and I completely trust each other and more importantly, are philosophically aligned on how we want to run and grow the community. If we didn’t have this, the friction between us could tear apart the entire community. Picking the right people to work with is important in any company, but when your business is literally about bringing people together, there’s no margin for error here.  While I’m sure there will be many more challenges ahead, knowing that we all trust each other to make decisions that fall in line with each of our core values makes these challenges dramatically easier to overcome. Finally, I’d like to thank all of our members for making the community what it is today – it’d be nothing without you and I promise that we’ll never take that for granted. &#x200B; I originally posted this on my blog here. Welcoming all of your thoughts, comments, questions and I'll do my best to answer them :)

#reddit#delicate#balance

reddit

0

1

Royal_Rest8409•This week

How a founder built a B2B AI startup to serve with 65+ global brands (including Fortune500 companies)

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

#reddit#founder#built

reddit

0

1

chtrbx_ai•This week

🚀 Noob Seeking Go To Market experts! What are the most effective strategies to launch an AI Saas in the market and gain early traction with potential clients?

Question: What are some ways you have successfully gone to market for an AI Saas product? Any great (not good, but great) resources? Background: I have little sense of what is the most effective use of my time as I am feeling spread too thin. Creating a startup is not dissimilar to my job (identify problems, design tech based solutions, and roll out to 40,000 employees); however… I’ve never worked on a project where people a) pay for these solutions b) choices in what solutions they go with.

#reddit#noob#seeking

reddit

0

1

hopefully_useful•This week

We made $325k in 2023 from AI products, starting from 0, with no-code, no funding and no audience

I met my co-founder in late 2022 after an introduction from a mutual friend to talk about how to find contract Product Management roles. I was sporadically contracting at start-up at the time and he had just come out of another start-up that was wiped out by the pandemic. We hit it off, talking about ideas, sharing what other indie-hackers were doing, and given GPT-3’s prominence at the time, we started throwing around ideas about things we could build with it, if nothing else, just to learn. I should caveat, neither of us were AI experts when starting out, everything we learned has been through Twitter and blogs, my background is as an accountant, and his a consultant. Here’s how it went since then: &#x200B; Nov 2022 (+$50) \- We built a simple tool in around a week using GPT-3 fine-tuning and a no-code tool (Bubble) that helped UK university students write their personal statements for their applications \- We set some Google Ads going and managed to make a few sales (\~$50) in the first week \- OpenAI were still approving applications at the time and said this went against their “ethics” so we had to take it down &#x200B; Dec 2022 (+$200) \- We couldn’t stop coming up with ideas related to AI fine-tuning, but realised it was almost impossible to decide which to pursue \- We needed a deadline to force us so we signed up for the Ben’s Bites hackathon in late December \- In a week, we built and launched a no-code fine-tuning platform, allowing people to create fine-tuned models by dragging and dropping an Excel file onto it \- We launched it on Product Hunt, having no idea how to price it, and somehow managed to get \~2,000 visitors on the site and make 2 sales at $99 &#x200B; Jan 2023 (+$3,000) \- We doubled down on the fine-tuning idea and managed to get up to \~$300 MRR, plus a bunch of one-time sales and a few paid calls to help people get the most out of their models \- We quickly realised that people didn’t want to curate models themselves, they just wanted to dump data and get magic out \- That was when we saw people building “Talk with x book/podcast” on Twitter as side projects and realised that was the missing piece, we needed to turn it into a tool \- We started working on the new product in late January &#x200B; Feb 2023 (+$9,000) \- We started pre-selling access to an MVP for the new product, which allowed people to “chat with their data/content”, we got $5,000 in pre-sales, more than we made from the previous product in total \- By mid-February, after 3 weeks of building we were able to launch and immediately managed to get traction, getting to $1k MRR in < 1 week, building on the hype of ChatGPT and AI (we were very lucky here) &#x200B; Mar - Jul 2023 (+$98,000) \- We worked all the waking hours to keep up with customer demand, bugs, OpenAI issues \- We built integrations for a bunch of services like Slack, Teams, Wordpress etc, added tons of new functionality and continue talking to customers every day \- We managed to grow to $17k MRR (just about enough to cover our living expenses and costs in London) through building in public on Twitter, newsletters and AI directories (and a million other little things) \- We sold our fine-tuning platform for \~$20k and our university project for \~$3k on Acquire &#x200B; Aug 2023 (+$100,000) \- We did some custom development work based on our own product for a customer that proved pretty lucrative &#x200B; Sep - Oct 2023 (+$62,000) \- After 8 months of building constantly, we started digging more seriously into our usage and saw subscriptions plateauing \- We talked to and analysed all our paying users to identify the main use cases and found 75% were for SaaS customer support \- We took the leap to completely rebuild a version of our product around this use case, our biggest to date (especially given most features with no-code took us <1 day) &#x200B; Nov - Dec 2023 (+$53,000) \- We picked up some small custom development work that utilised our own tech \- We’re sitting at around $22k MRR now with a few bigger clients signed up and coming soon \- After 2 months of building and talking to users, we managed to finish our “v2” of our product, focussed squarely on SaaS customer support and launched it today. &#x200B; We have no idea what the response will be to this new version, but we’re pretty happy with it, but couldn’t have planned anything that happened to us in 2023 so who knows what will come of 2024, we just know that we are going to be learning a ton more. &#x200B; Overall, it is probably the most I have had to think in my life - other jobs you can zone out from time to time or rely on someone else if you aren’t feeling it - not when you are doing this, case and point, I am writing this with a banging head-cold right now, but wanted to get this done. A few more things we have learned along the way - context switching is unreal, as is keeping up with, learning and reacting to AI. There isn’t a moment of the day I am not thinking about what we do next. But while in some way we now have hundreds of bosses (our customers) I still haven’t felt this free and can’t imagine ever going back to work for someone else. Next year we’re really hoping to figure out some repeatable distribution channels and personally, I want to get a lot better at creating content/writing, this is a first step! Hope this helps someone else reading this to just try starting something and see what happens.

#reddit#made#$325k

reddit

0

1

mr_t_forhire•This week

Started a content marketing agency 6 years ago - $0 to $5,974,324 (2023 update)

Hey friends, My name is Tyler and for the past 6 years, I’ve been documenting my experience building a content marketing agency called Optimist. Year 1 - 0 to $500k ARR Year 2 - $500k to $1MM ARR Year 3 - $1MM ARR to $1.5MM(ish) ARR Year 4 - $3,333,686 Revenue Year 5 - $4,539,659 Revenue How Optimist Works First, an overview/recap of the Optimist business model: We operate as a “collective” of full time/professional freelancers Everyone aside from me is a contractor Entirely remote/distributed team Each freelancer earns $65-85/hour Clients pay us a flat monthly fee for full-service content marketing (research, strategy, writing, editing, design/photography, reporting and analytics, targeted linkbuilding, and more) We recently introduced hourly engagements for clients who fit our model but have some existing in-house support Packages range in price from $10-20k/mo We offer profit share to everyone on our core team as a way to give everyone ownership in the company In 2022, we posted $1,434,665 in revenue. It was our highest revenue year to date and brings our lifetime total to $5,974,324. Here’s our monthly revenue from January 2017 to December of 2022. But, like every year, it was a mix of ups and downs. Here’s my dispatch for 2023. — Running a business is like spilling a drink. It starts as a small and simple thing. But, if you don’t clean it up, the spill will spread and grow — taking up more space, seeping into every crack. There’s always something you could be doing. Marketing you could be working on. Pitches you could be making. Networking you could be doing. Client work you could help with. It can be all-consuming. And it will be — if you don’t clean up the spill. I realized this year that I had no containment for the spill that I created. Running an agency was spilling over into nearly every moment of my life. When I wasn’t working, I was thinking about work. When I wasn’t thinking about work, I was dreaming about it. Over the years, I’ve shared about a lot of my personal feelings and experience as an entrepreneur. And I also discussed my reckoning with the limitations of running the business we’ve built. My acceptance that it was an airplane but not a rocket. And my plan to try to compartmentalize the agency to make room in my life for other things — new business ideas, new revenue streams, and maybe some non-income-producing activity. 🤷 What I found in 2022 was that the business wasn’t quite ready for me to make that move. It was still sucking up too much of my time and attention. There were still too many gaps to fill and I was the one who was often filling them. So what do you do? Ultimately you have two choices on the table anytime you run a business and it’s not going the way you want it: Walk away Turn the ship — slowly For a huge number of reasons (personal, professional, financial, etc), walking away from Optimist was not really even an option or the right move for me. But it did feel like things needed to change. I needed to keep turning the ship to get it to the place where it fit into my life — instead of my life fitting around the business. This means 2022 was a year of transition for the agency. (Again?) Refocusing on Profit Some money is better than no money. Right? Oddly, this was one of the questions I found myself asking in 2022. Over the years, we’ve been fortunate to have many clients who have stuck with us a long time. In some cases, we’ve had clients work with us for 2, 3, or even 4 years. (That’s over half of our existence!) But, things have gotten more expensive — we’ve all felt it. We’ve had to increase pay to remain competitive for top talent. Software costs have gone up. It’s eaten into our margin. Because of our increasing costs and evolving scope, many of our best, most loyal clients were our least profitable. In fact, many were barely profitable — if at all. We’ve tried to combat that by increasing rates on new, incoming clients to reflect our new costs and try to make up for shrinking margin on long-term clients. But we didn’t have a good strategy in place for updating pricing for current clients. And it bit us in the ass. Subsidizing lower-profit, long-term clients with new, higher-margin clients ultimately didn’t work out. Our margins continued to dwindle and some months we were barely breaking even while posting six-figures of monthly revenue. 2022 was our highest revenue year but one of our least profitable. It only left one option. We had to raise rates on some of our long-term clients. But, of course, raising rates on a great, long-term client can be delicate. You’ve built a relationship with these people over the years and you’re setting yourself up for an ultimatum — are you more valuable to the client or is the client more valuable to you? Who will blink first? We offered all of these clients the opportunity to move to updated pricing. Unfortunately, some of them weren’t on board. Again, we had 2 options: Keep them at a low/no profit rate Let them churn It seems intuitive that having a low-profit client is better than having no client. But we’ve learned an important lesson many times over the years. Our business doesn’t scale infinitely and we can only handle so many clients at a time. That means that low-profit clients are actually costing us money in some cases. Say our average client generates $2,500 per month in profit — $30,000 per year. If one of our clients is only generating $500/mo in profit, working with them means missing out on bringing on a more profitable client (assuming our team is currently at capacity). Instead of $30,000/year, we’re only making $6,000. Keeping that client costs us $24,000. That’s called opportunity cost. So it’s clear: We had to let these clients churn. We decided to churn about 25% of our existing clients. On paper, the math made sense. And we had a pretty consistent flow of new opportunities coming our way. At the time, it felt like a no-brainer decision. And I felt confident that we could quickly replace these low-profit clients with higher-margin ones. I was wrong. Eating Shit Right after we initiated proactively churning some of our clients, other clients — ones we planned to keep — gave us notice that they were planning to end the engagement. Ouch. Fuck. We went from a 25% planned drop in revenue to a nearly 40% cliff staring us right in the face. Then things got even worse. Around Q3 of this year, talk of recession and layoffs really started to intensify. We work primarily with tech companies and startups. And these were the areas most heavily impacted by the economic news. Venture funding was drying up. Our leads started to slow down. This put us in a tough position. Looking back now, I think it’s clear that I made the wrong decision. We went about this process in the wrong way. The reality sinks in when you consider the imbalance between losing a client and gaining a client. It takes 30 days for someone to fire us. It’s a light switch. But it could take 1-3 months to qualify, close, and onboard a new client. We have lots of upfront work, research, and planning that goes into the process. We have to learn a new brand voice, tone, and style. It’s a marathon. So, for every client we “trade”, there’s a lapse in revenue and work. This means that, in retrospect, I would probably have made this transition using some kind of staggered schedule rather than a cut-and-dry approach. We could have gradually off-boarded clients when we had more definitive work to replace them. I was too confident. But that’s a lesson I had to learn the hard way. Rebuilding & Resetting Most of the voluntary and involuntary churn happened toward the end of 2022. So we’re still dealing with the fall out. Right now, it feels like a period of rebuilding. We didn’t quite lose 50% of our revenue, but we definitely saw a big hit heading into 2023. To be transparent: It sucks. It feels like a gigantic mistake that I made which set us back significantly from our previous high point. I acted rashly and it cost us a lot of money — at least on the surface. But I remind myself of the situation we were in previously. Nearly twice the revenue but struggling to maintain profitability. Would it have been better to try to slowly fix that situation and battle through months of loss or barely-break-even profits? Or was ripping off the bandaid the right move after all? I’m an optimist. (Heh, heh) Plus, I know that spiraling over past decisions won’t change them or help me move forward. So I’m choosing to look at this as an opportunity — to rebuild, reset, and refocus the company. I get to take all of the tough lessons I’ve learned over the last 6 years and apply them to build the company in a way that better aligns with our new and current goals. It’s not quite a fresh, clean start, but by parting ways with some of our oldest clients, we’ve eliminated some of the “debt” that’s accumulated over the years. We get a chance to fully realize the new positioning that we rolled out last year. Many of those long-term clients who churned had a scope of work or engagement structure that didn’t fit with our new positioning and focus. So, by losing them, we’re able to completely close up shop on the SOWs that no longer align with the future version of Optimist. Our smaller roster of clients is a better fit for that future. My job is to protect that positioning by ensuring that while we’re rebuilding our new roster of clients we don’t get desperate. We maintain the qualifications we set out for future clients and only take on work that fits. How’s that for seeing the upside? Some other upside from the situation is that we got an opportunity to ask for candid feedback from clients who were leaving. We asked for insight about their decision, what factors they considered, how they perceived us, and the value of our work. Some of the reasons clients left were obvious and possibly unavoidable. Things like budget cuts, insourcing, and uncertainty about the economy all played at least some part of these decisions. But, reading between the lines, where was one key insight that really struck me. It’s one of those, “oh, yeah — duh — I already knew that,” things that can be difficult to learn and easy to forget…. We’re in the Relationship Business (Plan Accordingly) For all of our focus on things like rankings, keywords, content, conversions, and a buffet of relevant metrics, it can be easy to lose the forest for the trees. Yes, the work itself matters. Yes, the outcomes — the metrics — matter. But sometimes the relationship matters more. When you’re running an agency, you can live or die by someone just liking you. Admittedly, this feels totally unfair. It opens up all kinds of dilemmas, frustration, opportunity for bias and prejudice, and other general messiness. But it’s the real world. If a client doesn’t enjoy working with us — even if for purely personal reasons — they could easily have the power to end of engagement, regardless of how well we did our actual job. We found some evidence of this in the offboarding conversations we had with clients. In some cases, we had clients who we had driven triple- and quadruple-digital growth. Our work was clearly moving the needle and generating positive ROI and we had the data to prove it. But they decided to “take things in another direction” regardless. And when we asked about why they made the decision, it was clear that it was more about the working relationship than anything we could have improved about the service itself. The inverse is also often true. Our best clients have lasting relationships with our team. The work is important — and they want results. But even if things aren’t quite going according to plan, they’re patient and quick to forgive. Those relationships feel solid — unshakeable. Many of these folks move onto new roles or new companies and quickly look for an opportunity to work with us again. On both sides, relationships are often more important than the work itself. We’ve already established that we’re not building a business that will scale in a massive way. Optimist will always be a small, boutique service firm. We don’t need 100 new leads per month We need a small, steady roster of clients who are a great fit for the work we do and the value we create. We want them to stick around. We want to be their long-term partner. I’m not built for churn-and-burn agency life. And neither is the business. When I look at things through this lens, I realize how much I can cut from our overall business strategy. We don’t need an ultra-sophisticated, multi-channel marketing strategy. We just need strong relationships — enough of them to make our business work. There are a few key things we can take away from this as a matter of business strategy: Put most of our effort into building and strengthening relationships with our existing clients Be intentional about establishing a strong relationship with new clients as part of onboarding Focus on relationships as the main driver of future business development Embracing Reality: Theory vs Practice Okay, so with the big learnings out the way, I want to pivot into another key lesson from 2022. It’s the importance of understanding theory vs practice — specifically when it comes to thinking about time, work, and life. It all started when I was considering how to best structure my days and weeks around running Optimist, my other ventures, and my life goals outside of work. Over the years, I’ve dabbled in many different ways to block time and find focus — to compartmentalize all of the things that are spinning and need my attention. As I mapped this out, I realized that I often tried to spread myself too thin throughout the week. Not just that I was trying to do too much but that I was spreading that work into too many small chunks rather than carving out time for focus. In theory, 5 hours is 5 hours. If you have 5 hours of work to get done, you just fit into your schedule whenever you have an open time slot. In reality, a single 5-hour block of work is 10x more productive and satisfying than 10, 30-minute blocks of work spread out across the week. In part, this is because of context switching. Turning your focus from one thing to another thing takes time. Achieving flow and focus takes time. And the more you jump from one project to another, the more time you “lose” to switching. This is insightful for me both in the context of work and planning my day, but also thinking about my life outside of Optimist. One of my personal goals is to put a finite limit on my work time and give myself more freedom. I can structure that in many different ways. Is it better to work 5 days a week but log off 1 hour early each day? Or should I try to fit more hours into each workday so I can take a full day off? Of course, it’s the latter. Both because of the cost of context switching and spreading work into more, smaller chunks — but also because of the remainder that I end up with when I’m done working. A single extra hour in my day probably means nothing. Maybe I can binge-watch one more episode of a new show or do a few extra chores around the house. But it doesn’t significantly improve my life or help me find greater balance. Most things I want to do outside of work can’t fit into a single extra hour. A full day off from work unlocks many more options. I can take the day to go hiking or biking. I can spend the day with my wife, planning or playing a game. Or I can push it up against the weekend and take a 3-day trip. It gives me more of the freedom and balance that I ultimately want. So this has become a guiding principle for how I structure my schedule. I want to: Minimize context switching Maximize focused time for work and for non-work The idea of embracing reality also bleeds into some of the shifts in business strategy that I mentioned above. In theory, any time spent on marketing will have a positive impact on the company. In reality, focusing more on relationships than blasting tweets into the ether is much more likely to drive the kind of growth and stability that we’re seeking. As I think about 2023, I think this is a recurring theme. It manifests in many ways. Companies are making budget cuts and tough decisions about focus and strategy. Most of us are looking for ways to rein in the excess and have greater impact with a bit less time and money. We can’t do everything. We can’t even do most things. So our #1 priority should be to understand the reality of our time and our effort to make the most of every moment (in both work and leisure). That means thinking deeply about our strengths and our limitations. Being practical, even if it feels like sacrifice. Update on Other Businesses Finally, I want to close up by sharing a bit about my ventures outside of Optimist. I shared last year how I planned to shift some of my (finite) time and attention to new ventures and opportunities. And, while I didn’t get to devote as much as I hoped to these new pursuits, they weren’t totally in vain. I made progress across the board on all of the items I laid out in my post. Here’s what happened: Juice: The first Optimist spin-out agency At the end of 2021, we launched our first new service business based on demand from Optimist clients. Focused entirely on building links for SEO, we called the agency Juice. Overall, we made strong progress toward turning this into a legitimate standalone business in 2022. Relying mostly on existing Optimist clients and a few word-of-mouth opportunities (no other marketing), we built a team and set up a decent workflow and operations. There’s still many kinks and challenges that we’re working through on this front. All told, Juice posted almost $100,000 in revenue in our first full year. Monetizing the community I started 2022 with a focus on figuring out how to monetize our free community, Top of the Funnel. Originally, my plan was to sell sponsorships as the main revenue driver. And that option is still on the table. But, this year, I pivoted to selling paid content and subscriptions. We launched a paid tier for content and SEO entrepreneurs where I share more of my lessons, workflows, and ideas for building and running a freelance or agency business. It’s gained some initial traction — we reached \~$1,000 MRR from paid subscriptions. In total, our community revenue for 2022 was about $2,500. In 2023, I’m hoping to turn this into a $30,000 - $50,000 revenue opportunity. Right now, we’re on track for \~$15,000. Agency partnerships and referrals In 2022, we also got more serious about referring leads to other agencies. Any opportunity that was not a fit for Optimist or we didn’t have capacity to take on, we’d try to connect with another partner. Transparently, we struggled to operationalize this as effectively as I would have liked. In part, this was driven by my lack of focus here. With the other challenges throughout the year, I wasn’t able to dedicate as much time as I’d like to setting goals and putting workflows into place. But it wasn’t a total bust. We referred out several dozen potential clients to partner agencies. Of those, a handful ended up converting into sales — and referral commission. In total, we generated about $10,000 in revenue from referrals. I still see this as a huge opportunity for us to unlock in 2023. Affiliate websites Lastly, I mentioned spending some time on my new and existing affiliate sites as another big business opportunity in 2022. This ultimately fell to the bottom of my list and didn’t get nearly the attention I wanted. But I did get a chance to spend a few weeks throughout the year building this income stream. For 2022, I generated just under $2,000 in revenue from affiliate content. My wife has graciously agreed to dedicate some of her time and talent to these projects. So, for 2023, I think this will become a bit of a family venture. I’m hoping to build a solid and consistent workflow, expand the team, and develop a more solid business strategy. Postscript — AI, SEO, OMG As I’m writing this, much of my world is in upheaval. If you’re not in this space (and/or have possibly been living under a rock), the release of ChatGPT in late 2022 has sparked an arms race between Google, Bing, OpenAI, and many other players. The short overview: AI is likely to fundamentally change the way internet search works. This has huge impact on almost all of the work that I do and the businesses that I run. Much of our focus is on SEO and understanding the current Google algorithm, how to generate traffic for clients, and how to drive traffic to our sites and projects. That may all change — very rapidly. This means we’re standing at a very interesting point in time. On the one hand, it’s scary as hell. There’s a non-zero chance that this will fundamentally shift — possibly upturn — our core business model at Optimist. It could dramatically change how we work and/or reduce demand for our core services. No bueno. But it’s also an opportunity (there’s the optimist in me, again). I certainly see a world where we can become leaders in this new frontier. We can pivot, adjust, and capitalize on a now-unknown version of SEO that’s focused on understanding and optimizing for AI-as-search. With that, we may also be able to help others — say, those in our community? — also navigate this tumultuous time. See? It’s an opportunity. I wish I had the answers right now. But, it’s still a time of uncertainty. I just know that there’s a lot of change happening and I want to be in front of it rather than trying to play catch up. Wish me luck. — Alright friends — that's my update for 2023! I’ve always appreciated sharing these updates with the Reddit community, getting feedback, being asked tough questions, and even battling it out with some of my haters (hey!! 👋) As usual, I’m going to pop in throughout the next few days to respond to comments or answer questions. Feel free to share thoughts, ideas, and brutal takedowns in the comments. If you're interested in following the Optimist journey and the other projects I'm working on in 2023, you can follow me on Twitter. Cheers, Tyler P.S. - If you're running or launching a freelance or agency business and looking for help figuring it out, please DM me. Our subscription community, Middle of the Funnel, was created to provide feedback, lessons, and resources for other entrepreneurs in this space.

#reddit#started#content

reddit

0

1

FreelancerChurch•This week

Dangers of not adopting AI strategies?

Tldr: I need to know how AI is threatening different types of businesses. Please share your perspective. I'll reply to every comment. Hi, this is for anyone concerned with how to respond to the emergence of new AI tools. (to grow instead of going out of business, find opportunities instead of getting beat by competitors, etc. I need to find the best ways to use AI to give my clients an advantage. (I’m a mod at r/writingservice & a content/brand strategist.) Not just automation. That's weak. I mean innovation. Using AI to do stuff that has never been done in your industry. Lots of virtual assistants (for business owners) will make the mistake of learning how to use these tools only in a general way, without applying them in the real world. I don’t want to make that mistake. It will help me if you share what’s on your mind, what’s unique about the way AI affects your industry, or your unique business model, etc. So this is basically like an informal research study. And it's the kind where you get something if you participate - I will seriously spend time to offer the best stuff I know in the comments if you just share your perspective, how AI is affecting you in the unique way you are situation in your industry and among your competitors. Have you been finding ways to incorporate AI in your marketing, customer service, etc.? I have a feeling a lot of business owners are worried right now, because all our experience is from the old landscape prior to everything being automated with AI. Even if you have questions on your mind and share them, that can help me. My problem: I’m learning to use GPT/Gemini/Invideo/Perplexity and others, but it’s not good enough until I see how they apply in different situations, industries, business models. If you share some ideas, I’ll reply to every comment and try to offer something helpful. I’ve already made a lot of progress learning how the strengths/weaknesses of different AI tools for different situations. Thinking about the way their competitors might surpass you by using them, or about opportunities for you to surpass them.... what concerns are on your mind? Or what have you learned, what are you doing, etc.

#reddit#dangers#adopting

reddit

0

1

AntsyNursery58•This week

AI Will Make You Extremely Rich or Kill Your Business in 2024

Preface: I'm a solo-founder in the AI space and previously worked as an ML scientist; the new advancements in AI that I'm seeing are going to impact everyone here. It doesn't matter if you're just starting out, or a bootstrapped brick and mortar founder, or even a VC backed hard tech founder. Last year was when the seeds were laid, and this is the year we'll see them bloom. There will be an onslaught of advancements that take place that are borderline inconceivable due to the nature of exponential progress. This will change every single vertical. I'm making this post because I think AI execution strategy will make or break businesses. Dramatically. Over $50B was put into AI startups in 2023 alone. This figure excludes the hundreds of billions poured into AI from enterprises. So, let's follow the money: &#x200B; 1) AI enterprise software. There's a lot to unpack here and this is what I’m currently working on. AI enterprise software will encompass everything from hyper personalized email outbound to AI cold calls to AI that A/B tests ads on synthetic data to vertical specific software. The impact of the former is relatively self explanatory, so I'll focus on the latter. To illustrate vertical specific AI software, I'll use a simple example in the legal space. Lawyers typically have to comb through thousands of pages of documents. Now, using an LLM + a VDB, an AI can instantly answer all of those questions while surfacing the source and highlighting the specific answer in the contract/document. There are dozens of AI startups for this use case alone. This saves lawyers an immense amount of time and allows them to move faster. Firms that adopt this have a fundamental advantage over law firms that don't adopt this. This was 2023 technology. I'm seeing vertical AI software getting built by my friends in areas from construction, to real estate, to even niche areas like chimney manufacturing. This will exist everywhere. Now, this can be extrapolated much further to be applicable to systems that can do reports and even browse the Internet. This brings me to my next point. &#x200B; 2) AI information aggregation and spread. My gut tells me that this will have a crescendo moment in the future with hardware advancements (Rabbit, Tab, etc.). You won't have to google things because it will be surfaced to you. It's predictive in nature. The people who can get information the fastest will grow their business the fastest. This part is semi-speculative, but due to the nature of LLMs being so expensive to train, I have a strong feeling that large institutions will have access to the \fastest\ and \best\ models that can do this quicker than you and I can. This is why it's important to stay on top. &#x200B; 3) AI content generation This is relevant to running advertisements and any digital marketing aspect of your business. If you can rapidly make content faster than your competitors to put in social media, you will outpace your competitors rapidly. I think most folks are familiar with MidJourney, Stable diffusion, etc. but don't know how to use it. You can generate consistent models for a clothing brand or generate images of a product that you would normally need to hire a professional photographer to take. There's also elevenlabs which is relatively easy to use and can be used to make an MP3 clip as a narration for an ad; this is something I've already done. I'm also still shocked by how many people are unfamiliar with tools like Pika which can do video generation. You could imagine companies having fleets of digital influencers that they control or conjuring up the perfect ad for a specific demographic using a combination of all of the aforementioned tools. &#x200B; In summary, if you feel like I'm being hyperbolic or propagating science fiction fantasies, you're likely already behind. I truly recommend that everyone stays up to date on these advancements as much as possible. If your competitor comes across an AI tool that can increase their ROAS by 5x they can crush you. If your competitor uses a tool that increases the rate at which they receive and aggregate information by 200% (modest estimate) they will crush you. If your competitors have a tool that can reduce their employee size, then they will use it. They'll fire their employees to cut costs and reinvest the money back into their business. It will compound to the point where you're outpaced, and this isn't a level of innovation we've seen since the birth of the industrial revolution. Your customers can get stolen overnight, or you can steal your competition’s customers overnight. TL;DR: This is an opportunity for entrepreneurs to scale faster than they could have possibly imagined, but this also comes with the potential for your company to be obliterated. We've never seen advancements that can have this drastic of an impact this quickly. Adoption will happen fast, and first movers will have a disproportionate and compounding advantage. Watch guides, meet with startups, follow the news, and get rich.

#reddit#will#make

reddit

0

1

AntsyNursery58•This week

AI Will Make You Extremely Rich or Kill Your Business in 2024

Preface: I'm a solo-founder in the AI space and previously worked as an ML scientist; the new advancements in AI that I'm seeing are going to impact everyone here. It doesn't matter if you're just starting out, or a bootstrapped brick and mortar founder, or even a VC backed hard tech founder. Last year was when the seeds were laid, and this is the year we'll see them bloom. There will be an onslaught of advancements that take place that are borderline inconceivable due to the nature of exponential progress. This will change every single vertical. I'm making this post because I think AI execution strategy will make or break businesses. Dramatically. Over $50B was put into AI startups in 2023 alone. This figure excludes the hundreds of billions poured into AI from enterprises. So, let's follow the money: &#x200B; 1) AI enterprise software. There's a lot to unpack here and this is what I’m currently working on. AI enterprise software will encompass everything from hyper personalized email outbound to AI cold calls to AI that A/B tests ads on synthetic data to vertical specific software. The impact of the former is relatively self explanatory, so I'll focus on the latter. To illustrate vertical specific AI software, I'll use a simple example in the legal space. Lawyers typically have to comb through thousands of pages of documents. Now, using an LLM + a VDB, an AI can instantly answer all of those questions while surfacing the source and highlighting the specific answer in the contract/document. There are dozens of AI startups for this use case alone. This saves lawyers an immense amount of time and allows them to move faster. Firms that adopt this have a fundamental advantage over law firms that don't adopt this. This was 2023 technology. I'm seeing vertical AI software getting built by my friends in areas from construction, to real estate, to even niche areas like chimney manufacturing. This will exist everywhere. Now, this can be extrapolated much further to be applicable to systems that can do reports and even browse the Internet. This brings me to my next point. &#x200B; 2) AI information aggregation and spread. My gut tells me that this will have a crescendo moment in the future with hardware advancements (Rabbit, Tab, etc.). You won't have to google things because it will be surfaced to you. It's predictive in nature. The people who can get information the fastest will grow their business the fastest. This part is semi-speculative, but due to the nature of LLMs being so expensive to train, I have a strong feeling that large institutions will have access to the \fastest\ and \best\ models that can do this quicker than you and I can. This is why it's important to stay on top. &#x200B; 3) AI content generation This is relevant to running advertisements and any digital marketing aspect of your business. If you can rapidly make content faster than your competitors to put in social media, you will outpace your competitors rapidly. I think most folks are familiar with MidJourney, Stable diffusion, etc. but don't know how to use it. You can generate consistent models for a clothing brand or generate images of a product that you would normally need to hire a professional photographer to take. There's also elevenlabs which is relatively easy to use and can be used to make an MP3 clip as a narration for an ad; this is something I've already done. I'm also still shocked by how many people are unfamiliar with tools like Pika which can do video generation. You could imagine companies having fleets of digital influencers that they control or conjuring up the perfect ad for a specific demographic using a combination of all of the aforementioned tools. &#x200B; In summary, if you feel like I'm being hyperbolic or propagating science fiction fantasies, you're likely already behind. I truly recommend that everyone stays up to date on these advancements as much as possible. If your competitor comes across an AI tool that can increase their ROAS by 5x they can crush you. If your competitor uses a tool that increases the rate at which they receive and aggregate information by 200% (modest estimate) they will crush you. If your competitors have a tool that can reduce their employee size, then they will use it. They'll fire their employees to cut costs and reinvest the money back into their business. It will compound to the point where you're outpaced, and this isn't a level of innovation we've seen since the birth of the industrial revolution. Your customers can get stolen overnight, or you can steal your competition’s customers overnight. TL;DR: This is an opportunity for entrepreneurs to scale faster than they could have possibly imagined, but this also comes with the potential for your company to be obliterated. We've never seen advancements that can have this drastic of an impact this quickly. Adoption will happen fast, and first movers will have a disproportionate and compounding advantage. Watch guides, meet with startups, follow the news, and get rich.

#reddit#will#make

reddit

0

1

jottrled•This week

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

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

#reddit#went#solopreneur

reddit

0

1

Glad-Syllabub6777•This week

AI Voice Platform Comparison for Small Business Use Cases

We provide AI voice agent consultation and solutions in Upwork. One of clients’ frequent questions is which platform is best/perfect for their use cases, like lead qualification, AI receptionist, customer support, etc. This post provides our thoughts on this question. Our overall feeling is that the AI agent technology is still not there yet. It seems close but there are many corner cases the AI bot doesn't handle well. Four major players in the AI voice platforms: Bland ($65M funding) Retell ($4.6M funding) Synthflow ($7.4M funding) VAPI ($20M funding) We will only talk about Bland, Retell and VAPI. We firstly tried Synthflow and found the UI was buggy (the prompt editor froze for 20 seconds to 30 seconds when we were editing the prompt). Currently we don't use it anymore. Recommended use cases based on Upwork jobs we delivered: Bland. We recommend Bland for lead qualification as the lead qualification has a strict conversation flow (like asking questions, extracting variables, and making webhook calls). Clients/contractors can draw flow diagrams to build AI voice agents. We also find Bland is not a good fit for a small business with a monthly budget less than 5K. The reason is that common tools (like warm transfer, SMS sending) for AI voice agents are only available to enterprise clients. But warm transfers are critical for small businesses. Retell. We recommend Retell for customer support in contact centers. Retell has the best voice among competitors. One use case we build in Retell is the live translator in the ambulance call center. We tried the same prompt with the same LLM setup in VAPI. We found Retell performs way better than VAPI in terms of the translation quality and reliability. Another common scenario in the customer support domain is to have 3-way merge so that the agent can tell the summary to the transfer number while the caller can hear the conversation. VAPI. We recommend VAPI for AI receptionists and phone answering use cases. We can write a prompt and ask LLM to do the magic if callers ask questions not included in the prompt. We can set up custom tools to trigger automation (like update CRM) and warm transfer to connect to the stakeholders. One feeling we have is that VAPI is way more complicated than the other two platforms. If you don’t have developer experience and have a budget to hire a contractor, it is better to try Retell as Retell has many integrations. If you have any other questions or we miss anything, feel free to comment. We like to explore AI voice agent space together.

#reddit#voice#platform

reddit

0

1

Glad-Syllabub6777•This week

AI Voice Platform Comparison for Small Business Use Cases

We provide AI voice agent consultation and solutions in Upwork. One of clients’ frequent questions is which platform is best/perfect for their use cases, like lead qualification, AI receptionist, customer support, etc. This post provides our thoughts on this question. Our overall feeling is that the AI agent technology is still not there yet. It seems close but there are many corner cases the AI bot doesn't handle well. Four major players in the AI voice platforms: Bland ($65M funding) Retell ($4.6M funding) Synthflow ($7.4M funding) VAPI ($20M funding) We will only talk about Bland, Retell and VAPI. We firstly tried Synthflow and found the UI was buggy (the prompt editor froze for 20 seconds to 30 seconds when we were editing the prompt). Currently we don't use it anymore. Recommended use cases based on Upwork jobs we delivered: Bland. We recommend Bland for lead qualification as the lead qualification has a strict conversation flow (like asking questions, extracting variables, and making webhook calls). Clients/contractors can draw flow diagrams to build AI voice agents. We also find Bland is not a good fit for a small business with a monthly budget less than 5K. The reason is that common tools (like warm transfer, SMS sending) for AI voice agents are only available to enterprise clients. But warm transfers are critical for small businesses. Retell. We recommend Retell for customer support in contact centers. Retell has the best voice among competitors. One use case we build in Retell is the live translator in the ambulance call center. We tried the same prompt with the same LLM setup in VAPI. We found Retell performs way better than VAPI in terms of the translation quality and reliability. Another common scenario in the customer support domain is to have 3-way merge so that the agent can tell the summary to the transfer number while the caller can hear the conversation. VAPI. We recommend VAPI for AI receptionists and phone answering use cases. We can write a prompt and ask LLM to do the magic if callers ask questions not included in the prompt. We can set up custom tools to trigger automation (like update CRM) and warm transfer to connect to the stakeholders. One feeling we have is that VAPI is way more complicated than the other two platforms. If you don’t have developer experience and have a budget to hire a contractor, it is better to try Retell as Retell has many integrations. If you have any other questions or we miss anything, feel free to comment. We like to explore AI voice agent space together.

#reddit#voice#platform

reddit

0

1

jottrled•This week

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

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

#reddit#went#solopreneur

reddit

0

1

CerealEntre•This week

Legal Skim: "We make it easy for anyone to read legal contracts"

The Problem Nobody has the time to read contracts, so nobody reads them Lawyers cost to much money to simply "review" a contract for you The Solution An AI Software solution that reads your contract for you* and then highlights the important clauses to read, and shares helpful insights into what the "legal jargon" definitions are This would be a product built for "the everyman" Not for legal teams, but for your everyday, average Joe. I imagine the review highlights would be color-coded, with pastel and "happy feel" colors This would be for two reasons: To make it easy to read and immediately know what's important or unimportant To provide a comforting feeling to the stress of reading a contract that you don't understand I imagine the colors using the "Green, Yellow, Red" system Green colors mean mean there's no concern. If you skip this, no biggie Yellow colors mean you might want to take a closer look Red means if you skip this, you'll likely get screwed Slogan "We make it easy for anyone to read legal contracts" Competitor Analysis Ontra.com "The complete solution for negotiating and managing routine contracts." It looks like this is mostly for actual legal teams, not for consumers Delino.io "Delino’s automated contract review platform empowers you to manage the inherent risk in business contracts, so you can accelerate growth." This also looks like it's mostly actual legal teams, not for consumers LegalZoom.com This is a standard "Lawyer Review", not a software solution &#x200B; If you vote "This already exists", feel free to comment what company so I can add them to the competitor analysis 🙏 View Poll

#reddit#legal#skim:

github

0.58

1

georgezouq•Mar 28, 2025

awesome-ai-in-finance

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

#github#awesome-ai-in-finance

github

0.236

0.009333333333333334

bogdanmosica•Jan 23, 2025

internet-tools-collection

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

#github#internet-tools-collection

youtube

0.402

0.9

Jeff Su•Jan 21, 2025

You're Not Behind: Become AI-Native in 2025

🎯 Grab my free AI Toolkit: https://academy.jeffsu.org/ai-toolkit?utmsource=youtube&utmmedium=video&utm_campaign=172 Feeling overwhelmed by all the #AI noise? This video breaks down three key strategies to become AI-native in 2025: building a focused "Minimum Viable Toolkit" instead of chasing every new tool, implementing friction-free prompt #workflows, and creating sustainable learning systems to stay current with AI developments. Perfect for non-technical professionals looking to effectively integrate AI into their daily work. TIMESTAMPS 00:00 I feel overwhelmed by AI 00:37 The problem with learning AI 01:20 Challenge 1: AI Tools Paralysis 04:40 Challenge 2: Death by Prompts 07:18 Challenge 3: Update Suffocation 09:34 Recap of 3 Strategies RESOURCES MENTIONED AI Action Plan Doc: https://docs.google.com/document/d/1fs7hq12UqZHk7uSq6yN9x0vISouroAmVFLn3Dm_R4/copy My AI Toolkit: https://academy.jeffsu.org/ai-toolkit?utmsource=youtube&utmmedium=video&utm_campaign=172 My Perplexity Tutorial: https://youtu.be/YoWdogtZRw8 BE MY FRIEND: 📧 Subscribe to my newsletter - https://www.jeffsu.org/newsletter/?utmsource=youtube&utmmedium=video&utm_campaign=description 📸 Instagram - https://instagram.com/j.sushie 🤝 LinkedIn - https://www.linkedin.com/in/jsu05/ MY FAVORITE GEAR 🎬 My YouTube Gear - https://www.jeffsu.org/yt-gear/ 🎒 Everyday Carry - https://www.jeffsu.org/my-edc/ MY TOP 3 FAVORITE SOFTWARE ❎ CleanShot X - https://geni.us/cleanshotx ✍️ Skillshare - https://geni.us/skillshare-jeff 💼 Teal - http://tealhq.co/jeffsu

#AI#workflows

github

0.47

0.020849148958436158

theskeletoncrew•Jan 10, 2025

air-support

!air-support Air Support: Tools for Automating Airdrops of Solana NFTs The Skeleton Crew | Twitter: @skeletoncrewrip | Discord: Skeleton Crew Feeling generous? Your contributions help fund future development. Send tips to our Solana wallet: CH6afYjjydFLPSrfQYEUNCdSNohLCAQV6ir6QnYeZU3t See also: Treat Toolbox, a generative art manager for NFT projects from the Skeleton Crew. Background The Skeleton Crew launched on Oct 1, and has since been delivering daily airdrops of artwork from indie artists, with plans to continue for the entire month of October. In order to execute on this plan, we needed tools that allowed us to automate the process. This repository is the result of that effort, which we now share with you in the hopes of more teams spending less time giving themselves Carpal tunnel syndrome doing all of this manually inside of Phantom :) IMPORTANT - Before you Start Creating and sending NFTs in bulk comes with costs. On Solana, the costs are significantly better than some other chains. BUT, it's a good idea to try a drop on devnet first to be sure you understand the fees involved. We assume no responsibility for any costs incurred through the use of these tools. Use at your own risk. Getting Started In order to use Air Support, you will need to install and configure the current version of Metaplex. We run this locally with some customizations for speed (ex. hardcoding some metadata which is common across all of our drops). Also, have a look at the configuration options at the top of the Makefile. At minimum, you'll need to specify paths to Metaplex, your keyfile, and an RPC Host. It's highly recommended that you use a third-party RPC provider to perform large airdrops. DROP is a name for a set of airdrops; in our case we numbered these 1-31 for each day in October. TYPE is a name for a single airdropped item that's part of a drop; in our case we had a "trick" and a "treat" as part of each drop, sometimes even "trick1", "trick2"... etc. The name will be "token" by default, and is used to prefix log files in each step below. For the generate step to work, you will need to build Metaplex's rust tools. Inside metaplex/rust, run: You will also need a few other pieces of software installed, including: gshuf: brew install coreutils jq: brew install jq How to Use Air Support Prerequisites: follow all steps in the Getting Started section above. Then, the basic workflow looks something like this: 📇 prepare: Collect a list of token mint addresses, for which the holders of those tokens represent a community you wish to airdrop to. This is sometimes done by providing your Candy Machine address to https://tools.abstratica.art. Store this in the air support root directory as token-mint-addresses.json. ✍️ record: run this to fetch the wallet addresses of all users that hold the tokens, and don't have them listed on a secondary exchange. The goal here is to avoid sending airdrops to exchanges where they may not be recoverable. Note: As of now, Air Support can only identify tokens listed on Digital Eyes, Magic Eden, Solanart, and Alpha.art. FTX and Solsea use unique addresses for escrow wallets. The command below will fetch the addresses and store them in airdrops/1/token-holders.log. 🎨 create: Start Metaplex, and use it to create your Master Edition NFT with a limited supply (the number of airdrops you want to send). 🖨 generate: run this to generate prints of the Master Edition. These will be stored in the wallet associated with the keys you specify as options. The below command would create 500 prints of the Master with mint address RPdCMRxBx4YPcJv6HUb2S5zHGJcDrDrZszUNNGmLwfT. 🏅 choose: run this next to decide who will receive the airdrop. Important to note that if 2 tokens are owned by the same wallet, by design they have twice the chance to receive an airdrop as someone with only 1 token when using this script to pick recipients. If you have 10,000 token owners recorded as not listed on marketplaces in step 2, and 500 airdrops to send, this will randomly select 500 of those recorded tokens. 📬 distribute: the last step is to send the airdrops out. This script will run through the addresses generated in step 4 and the recipients chosen in step 5 and send airdrops 1-by-1. It is possible that failures will occur. Logs are saved during the process in a {NAME}_sent.log file. Because distribution happens line-by-line, it is safe to rerun the script again to attempt to correct failures. You can also check your wallet to see that all tokens have been distributed. (Note that your Master edition will still remain as only prints are recorded to be sent in step 4. You can keep these for yourself or a community vault.) There is also an optional STARTINDEX param that can be used if you need to restart a distribution from somewhere in the middle. 🔥 burn: if you realize you made a mistake on your Master NFT, but only after you went ahead and started printing a bunch of editions, this command will automate the process of sending those costly mistakes to the Solana incinerator. There is also an optional STARTINDEX param that can be used if you need to restart a distribution from somewhere in the middle. Other Tips Transparency is key when running airdrop campaigns to your communities. In an ideal world, where we had more than 24 hours between our launch and the start of our month of airdrops, we might have attempted to bring some or all of these processes on-chain. The next best thing we could offer is a transparency repo, where we publish the daily receipts of our airdrops, to make it easy for our community to investigate the drops on the blockchain if they feel the desire to do so. Our tools give you the receipts as output to do the same if you wish. You can have a look at that repo here: https://github.com/theskeletoncrew/airdrop-transparency Acknowledgements The record step utilizes code created by the Exiled Apes organization, shared under an Apache License, originally found here: https://github.com/exiled-apes/exiled-holders

#github#air-support

youtube

0.326

0.36

Lofi boost your mood•Oct 8, 2024

Music To Coding To Focus And Focus 🎧 lofi hip hop 💻 Coding Songs Playlist

Music To Coding To Focus And Focus 🎧 lofi hip hop 💻 Coding Songs Playlist Music To Coding To Focus And Focus 🎧 lofi hip hop 💻 Coding Songs Playlist️ Music To Coding To Focus And Focus 🎧 lofi hip hop 💻 Coding Songs Playlist️ 💻 Welcome to Lofi boost your mood : Boost your productivity and lock into the flow with smooth lofi hip hop beats, designed to keep your mind sharp during coding sessions. Whether you're debugging, creating new code, or working on a big project, these calming rhythms will help you stay focused and in the zone. Perfect for programmers who need to enhance their workflow without distractions. Subscribe for more lofi coding playlists to fuel your focus and creativity! ✨Help me reach 100,000 subscribers: https://www.youtube.com/channel/UCESVcUXbcDOrJ293_KWotyQ 🎵 Another Vibes for you : • Coding Session 💻 : https://youtu.be/qZjWUkohSQg • Lofi Playlist to Coding 💻: https://youtu.be/zWQjn2uVpUg • Night Coding Vibes 💻: https://youtu.be/S810accnrRc • 3 PM Coding Session 💻: https://youtu.be/akrgSiPLngY LIKE 👍COMMENT & ╔═╦╗╔╦╗╔═╦═╦╦╦╦╗╔═╗ ║╚╣║║║╚╣╚╣╔╣╔╣║╚╣═╣ ╠╗║╚╝║║╠╗║╚╣║║║║║═╣ ╚═╩══╩═╩═╩═╩╝╚╩═╩═╝!!! 🔔 🍃 ＦＯＣＵＳ ＡＮＤ ＣＯＤＥ ＷＩＴＨ ＬＯＦＩ 🍃 Lofi Music | Coding Beats 🍃 For Deep Work / Study / Code 🍃 Music to Help You Stay Productive 🎉Join our Discord server to download high-quality wallpapers, connect with others, and share your thoughts and feelings 🤗 : 🌷 https://discord.gg/MuPgsHJ5MW 🎨 Artwork and Animations by Ethan James : ✨ https://www.instagram.com/ethanjames30801/ "💜 Music provided by Purrple Cat → https://playlist.purrplecat.com → https://spotify.purrplecat.com → https://apple.purrplecat.com → https://amazon.purrplecat.com → https://bandcamp.purrplecat.com → https://soundcloud.purrplecat.com → https://instagram.purrplecat.com → https://tiktok.purrplecat.com → https://discord.purrplecat.com → https://twitter.purrplecat.com → https://facebook.purrplecat.com → https://youtube.purrplecat.com" 🎸 🎼 Tracklist: 00:00:00 - 01 Purrple Cat - FieldOf Fireflies https://open.spotify.com/track/4rfE7mNI2PoUOm5l1hwpgr?autoplay=true 00:02:41 - 02 Purrple Cat - WaitWhat https://open.spotify.com/track/1w7IfXgbG5nBHhoI1bGaGM 00:05:27 - 03 Purrple Cat - BlackCherry https://open.spotify.com/track/0b8j3Ixmk6aUa4VegYH2Ui?autoplay=true 00:08:31 - 04 Purrple Cat - BoxOf Kittens https://open.spotify.com/track/5VtS7LGk0TTKBwRtpMmqWM?autoplay=true 00:11:49 - 05 Purrple Cat - AlleyCat https://open.spotify.com/track/4ud4SB7SM5mXF6vhzib8iQ?autoplay=true 00:14:45 - 06 Purrple Cat - DarkChocolate https://open.spotify.com/track/138KkineYUu5WiAUVTjid9?autoplay=true 00:17:42 - 07 Purrple Cat - IHave Too Many Feelings https://open.spotify.com/track/1Qd0XQgXg11YV9myZv5m71?autoplay=true 00:20:57 - 08 Purrple Cat - GentleBreeze https://open.spotify.com/track/4CbAvhRbdt2up0YZzTpbbG?autoplay=true 00:24:13 - 09 Purrple Cat - Openingthe Window For Some Fresh Air https://open.spotify.com/track/7BuHGYghASIz8WOfopDkfY?autoplay=true 00:25:53 - 10 Purrple Cat - Bliss https://open.spotify.com/track/7DT4LT416UcdtoPv2L0ria?autoplay=true 00:28:53 - 11 Purrple Cat - TheRed Dot https://open.spotify.com/track/0GB1qIvHAudmgp3nJ7wdza 00:31:14 - 12 Purrple Cat - PitterPatter https://open.spotify.com/track/35uCQ9RzCpNHrvoSNiP2Gt?autoplay=true 00:34:14 - 13 Purrple Cat - SundaeSunset https://open.spotify.com/track/00JByF6azH3FC82HUWLJJk?autoplay=true 00:36:32 - 14 Purrple Cat - Mary https://open.spotify.com/track/4Xnfyvi8qZPdcxjyK4Gd9g 00:38:45 - 15 Purrple Cat - Festivalof Lights https://open.spotify.com/track/4T3i2PKPiBkNvPCgSKKdeL?autoplay=true ✨The Lofi music is perfect to Calm your anxiety, Learn, read books, paint, work from home, play video games, do your homework, sleep, prepare exams, have a break, cook, or chill drive, simply chill out with your friends. ✨ Artwork and Animations by © 2024 Lofi boost your mood #lofi #lofihiphop #lofistudy #lofimusic #lofibeats

#lofi#lofihiphop#lofistudy

youtube

0.415

0.86

Chill Music Lab•Jul 17, 2024

Chill Work Music — Deep Focus and Productivity Mix for Programming, Coding

This carefully curated mix of tracks is specifically designed to help you focus on work and be productive. Music in genres like chillstep, future garage, and chill electronic will create the perfect background for tackling complex projects or routine tasks. Perfect as a programming music and for intense coding sessions. Thanks to the relaxing atmosphere of this musical accompaniment, you will be able to immerse yourself in the creative process with special concentration and inspiration. These tracks will help you maintain a high level of attention and productivity to achieve maximum results. Discover new horizons of efficiency with our playlist! 🎯 Tips for Chill and Productive Work: Using Artificial Intelligence: Utilize AI tools to automate routine tasks. This will allow you to focus on more creative and complex aspects of your work. Gratitude Journal: At the end of each workday, write down three things you are grateful for. This will help you end the day on a positive note and reduce stress. Experiment with Rhythms: Try working at different times of the day. You might find that your productivity is significantly higher at night than during the day. Change of Scenery: If you feel you're losing concentration, try changing your workspace. Sit in a different chair, move to another room, or even go outside if possible. Music therapy with our Chill Music Lab playlists: Listen to our playlists or radio, which include relaxing and focusing tracks. Such music can help improve concentration and create a calm working atmosphere for your goals. If you enjoyed this video like, comment or subscribe to the channel. 🙏 Join our English-speaking Discord to get in contact with us and fellow music lovers. ❤️ https://discord.gg/5p8D8GdVfp Genre: Electronic Music Style: Chillstep, Future Garage Mood: Cyber, Deep, Atmospheric Feature: No prominent lyrics 📹 Similar videos ► https://www.youtube.com/playlist?list=PLdE7uo_7KBkf6X1lbOpL3tAWERvlYej2L ► https://www.youtube.com/playlist?list=PLdE7uo_7KBkeSTmryNClNxUkioFpq3Btx ► https://www.youtube.com/playlist?list=PLdE7uo_7KBkdbssGgnnIDm3EnE2gmHyEQ ► https://www.youtube.com/playlist?list=PLdE7uo_7KBkeH0adsnxZupMARfGxY6qik ► https://www.youtube.com/playlist?list=PLdE7uo_7KBkf0gwWO9-qeu-La5vSJPmPc ► https://www.youtube.com/playlist?list=PLdE7uo_7KBkdsNAZNbzOUj61OQ5N0Ka26 🎧 Tracklist ► 00:00 Arnydmusic - Polaris ► 03:22 Arnyd - Hypernova ► 06:58 Neskre - Saviour ► 10:24 Exal & SkyFlair - Afterlife ► 14:11 Warmth - Solstice (Aurora Principle Remix) ► 18:06 Himalia - Growing Upwards. ► 24:26 Lonely Bird - Foggy Night ► 27:19 F0x3r - Precious Little Things ► 31:09 Deadfeelings - Melancholia ► 34:42 AK - Gone ► 37:51 Skandition - Chasing A Dream ► 43:18 Foxer - You ► 46:51 4lienetic - If Only ► 49:35 Tecnosine - Capacious ► 52:36 Vonnboyd - Lost without you ► 55:16 Blackbird - Love In Purple ► 59:21 Infinitum - Reborn ► 1:02:42 Future Skyline - Silent Moon ► 1:07:12 Code of Kasilid - Proto ► 1:11:11 AK - We're Older Now ► 1:14:12 Iketa - Under ► 1:16:42 Yzuva - Forget ► 1:20:22 Direct - Millions ► 1:25:20 Lazarus Moment - Forests Calling ► 1:28:51 Hystvme - Dream ► 1:31:32 Synthetic Epiphany - Infinite ► 1:34:56 Turno - Nocturno ► 1:37:13 4Lienetic - The Most Painful Goodbye #WorkMusic #FocusMusic #ChillMusic

#WorkMusic#FocusMusic#ChillMusic