LLM Artifacts Connected to Andrej Karpathy's LLM Knowledge base... idea, I've been building out a fun way to generate dynamic artifacts from these knowledge bases with the goal of discovering and revealing meaningful and deeper insights. LLM KBs are hard to consume for humans, as I think they are more built for agents. So the question is, what form would be useful for humans to take actions and make important decisions? That's what I am trying to figure out with these artifacts. The artifact example shows a pulse on HN discussions around AI-related stories. The insights can go deeper, of course, but this is already super fun and thought-provoking, like some of my favorite podcasts. The format and depth matter a lot. The aggregation skills of agents are outstanding if you tune the prompts and skill carefully. I built this artifact generator in a few minutes through an agent skill, but I feel like there are so many ways that LLM-generated information can be used and consumed. Like generating deeper insights and analysis, and things that are just not feasible for humans today. The generated artifact (including its data and design) serves as reusable templates or can be updated in real-time via auomations, which is something I am also working on. It is truly an insane way to monitor and track information. Better than a newsletter. Better than newspapers. There is something about this that gets me really excited about the future of AI agents for knowledge generation and discovery. Lots of hidden gems everywhere just waiting to be discovered and acted on if the information is presented correctly. This is not perfect. The format, style/prose can be improved, but this is easy to customize via skill. You can personalize it to your liking. I feel like these dynamic artifacts are going to emerge as a strong new medium to stay on the cutting edge of things, both for agents and humans. My target is research, of course. This was just a basic example. Besides animation, I am also targeting other components like voice, videos, images, slides, etc. This space is full of opportunities to explore. Skill for this coming soon.show more

HTML Artifacts are a big part of how I... work with agents now. Artifacts can be more than just static files. When combined with agents, they can take action or help you take action. This unlocks all kinds of interesting ways to work with agents. This is clearly the future. Check out this writing and scheduler artifact I built in a few minutes. It uses a bit of HTML and JS. All the data is in markdown (Obsidian vaults), so the agent can access and modify it at any time. No DB needed. No sophisticated functionalities. The agent decides all that for me based on the skills, context, and memory it has access to. The best part about this simple stack is that all the important information stays with me. This has allowed me to build a recursive self-improving system and automations that can better tap into coding agents like Codex or Claude Code. I could have paid or built an entire app for scheduling posts, and there are so many of them out there. But I don't need to. I've realized a simple artifact does the job. And the simplicity of it is actually an advantage. Very little maintenance for very high returns on personalization, time, and efficiency. The other benefit of this is that I can add features as I please. That level of personalization feels magical, and we should all be pursuing more of it. All of this just keeps compounding. Of course, this example is just about writing. But I have similar artifacts for research, design, experimentation, evaluation, and so much more. And no, I didn't actually publish the post example I shared in the clip. It was just for demonstration purposes. I actually spend more time than this when writing together with agents. Lastly, having built my own agent orchestrator tool has made me realize that simplifying the tool stack is a superpower. If you are curious about how all this works, I will do a live session next week:show more

I just built my own wiki generator plugin for... my agents. My agents can now generate wikis for anything I ask. One of my favorite wikis is called PaperWiki. This is a great example of what Andrej Karpathy describes. It uses obsidian vaults to organize papers, retrieve LLM-generated summaries, diagrams, and other advanced views for paper exploration. When Obsidian UI is not enough, I use my own artifact generator inside my agent orchestrator (see clip for example). This allows my agents to build any kind of view or exploration feature that I need. The papers are all curated with automations and several rules/patterns I have manually built over the years. On the surface, this looks basic. But behind the scenes, there are advanced search capabilities, connections, metadata, derived data, and other interesting bits of information that are extremely useful for my research agents. This is mostly built for agents. The artifact preview is just a high-level way to validate and quickly assess the quality of the wiki, suggest improvements, and it's also great for research. I use tobi lutke's qmd for all search capabilities. Everything is markdown. The summaries and even the diagrams. The wiki updates on its own based on several automations I have optimized over the past couple of weeks. The wiki grows and self-improves based on several requirements important for my research use cases. This is as personalized as it gets. There is nothing like it out there. And I use my research expertise to continue improving it over time. This is a vanilla wiki. There are so many things I want to build on top of this. Different aggregations, views, artifacts, etc. All to help automate more of my research work and accelerate productivity. I think the biggest leverage here is how powerful this could be for discovery and experimentation. One of my goals is to use it to find deeper connections and insights that would otherwise elude the top human researchers and use those to generate interesting new hypotheses and research experiments. That way, my agents can use autoresearch to explore research ideas at the frontier. Stay tuned for more.show more

Increasingly, HTML Artifacts are becoming a core part of... how I work with AI agents. Long-horizon agent sessions need a better way to surface insights about what work it has done. This may not be obvious right now, but as you start to let your agent work on dynamic workflows, large codebases, long-running loops (e.g., using /goal), and deep research tasks, you need a good way to present results. Chat window is not it. You also don't want to just trust everything the agents do. Artifacts help provide an important verification layer, which in turn enables important decision-making. I like HTML artifacts because I can just ask the agent to produce as many of them (and in whatever form) as I need to verify the work and make sense out of everything. I even built a nice tab system for my artifacts. They are great for continual learning and research. I use HTML artifacts for logging, tracking experiments, brainstorming, managing my inbox, code reviews, agent session management, deep research, writing, reading, and so much more. I believe Andrej Karpathy wrote about this somewhere: As we move on to more advanced applications of AI agents and outputs get more complex, we will start to find the need for even more advanced forms of interactions with AI, including interactive neural videos/simulations.show more

We are entering an extremely exciting era for open-weight... models. Kimi K2.6 now feels like a top agentic model. I took it for a spin via Fireworks AI fast inference APIs. Kimi K2.6 has impressive agentic capabilities, design skills, and the ability to synthesize large amounts of information. I built a little Skill that produces survey papers on any AI research topic you want. (see example in the clip) You can use the skill to tell your agent to generate a survey on whatever topic and watch it go to work. The artifact was fully generated by Kimi.ai's Kimi K2.6. It's cheap and fast. Next step for me is to explore ways to continue integrating the capabilities of these models on use cases like automating my LLM knowledge bases and augmenting my agent memory capabilities. Stay tuned for more.show more

I just open-sourced my /learn skill. Learn anything with... agents and HTML artifacts. I have been learning about all kinds of topics with it. Install the skill and interact with any agent to help you through any topic. Ask it to generate visual and interactive artifacts and help you go deeper or generate knowledge checks (e.g., quizzes). Upskilling myself on any topic is one of the most impactful ways I have been able to use AI agents. If you are a DAIR Academy pro member, you can use it with our AI Builder. Skill: Try now:show more

Been exploring a new way to explore AI research... papers to discover deeper insights. Agents are at the center of it. So far, I've built this little interactive artifact generator in my orchestrator to visualize things. This allows me to change views and insights (on-demand) from 100s of papers. Just scratching the surface here. More to share soon.show more

I built a directory of beaches in manus in... just two prompts it's ridiculous, BUT here's why *you* are more important than ever: it still relies on crawling the web and on other sites to provide the data. for an MVP of a directory, or pseo site, or saas etc that's fine. it's never been easier to whip up that idea in minutes but if you want long term success you need to be the source and not the fork - and that only comes from doing stuff ai can't replicate (yet) all of the data from this site was crawled from elsewhere. is it accurate? how often is it updated? what if those sources change? when it becomes so easy to do things like build a directory or vibe code a saas, doing the hard things is more important than ever i have another app in this niche that has around 10,000 monthly active users it's been going for years and years at this point on autopilot i did it by painstakingly parsing time series of sea temperature data from the us government with a bot that runs 4x a day - no ai 😭 (currently has 63.4m rows of data) this site is the source for manus and other tools and is very accurate. I've had many opportunities to sell the data into bigger companies and none of that would be possible taking the easy route anyway: tldr manus is amazing but humans working on the hard problems with ai as a copilot is still the way you winshow more

Andrej Karpathy calls AI Agents slop "Overall, the models... they are not there. And I feel like the industry [...] it's making too big of a jump and it's trying to pretend that this is amazing. And it's not—it's slop! And I think they are not coming to terms with it. And maybe they are trying to fundraise or something like that, I'm not sure what's going on."show more

SEO for AI, why you should not block AI... answer engines, and the future of the web. We published an article *today* with updated guidance on databases on vercel. Brand new knowledge. Grok already has it (impressive!), sources it correctly, and links to our authoritative source, our website. This is good for users and good for the web. For users, this is the ideal experience. I use Grok myself like this every day. I don't want 10 blue links and a bunch of browser tabs. I want the AI to do the research for me. For companies, this is the future of getting information out about your products. It's going to be the norm and it'll be bigger than social media. Instead of blocking AI with legacy firewalls, I'd focus on: ▪️ writing content that matches the kinds of questions people are asking about ▪️ massively speeding up your content velocity. So many nuggets of wisdom get lost in private channels and groups. Get information out more quickly! ▪️ shipping agent integrations (like MCPs) and tools/infrastructure that plays well with agents (even CLIs are a good example) ▪️ offering 1P agentic & AI experiences to your end users. There won't be "one chatbot to rule them all". Build your own!show more

Hugo Gonzalez on the Celtics: “What can I say?... This is the [winningest] franchise in the whole NBA. It’s a privilege to be part of a franchise like this. It’s more or less like where I used to be in Real Madrid, they are the most winningest club in Europe, too. So having that type of transition and similarities and everything is something that is going to be easier.”show more

Excited to launch a new way to upskill with... AI agents. This is how we are making it possible for anyone to learn to build with coding agents. To start, we are launching 4 new hands-on labs on the following topics: - Agent Skills - Agentic Image Generation - 30 Days of Hermes Agents - Prompt Engineering with Agents I am confident that with our new DAIR.AI platform, anyone can learn to become a top AI builder by building and acquiring highly-demanded AI skills. And there is a lot more landing in the coming weeks.show more

World Models are the path for some AI Models... in the future. But how can we efficiently train these models to not only see the world the way humans do but to see the world in a new and unique way. By visualizing, what is normally sequenced audio patterns, we can derive much more insights. Here we see Paganini in a visual form that can than be described and transcribed into a World Model. We can observe connections in a manner that may not have been clear prior to the digitalization of music and sound in this way. The company with the most valuable potential in building a World Model is Tesla. Not that this type of visualization is being used, but that the mechanisms are in place, and the technology is in place for the company to thrive in this new form of AI.show more

Usually I don’t speak on political issues often however... Charlie Kirk’s death (RIP) hits a little too close to home. Perhaps it is because anyone who has some resemblance of a following who is outspoken against any narrative online has probably received some sort of threat in their inbox. (I know I have) It is baffling to me that one could harbour such a large amount of hate inside of them to want to have another silenced for having differing opinions than their own. I think about all my outspoken friends who are in positions faced to the public and of course myself and what this potentially means for all of us. This of course, would never stop me from speaking out to what’s right, so perhaps that is also why I wanted to make a comment. To me it is disgusting behaviour to mock/be happy about the death of people you disagree with that have done nothing wrong. I think about all my friends, family who could be wrongfully persecuted based off the delusions of perceived “sides”. The amount of hate manufactured and projected onto you for just living your life and not complying to a certain ideal is insane. I don’t like fear mongering but I also think it’s important to stay vigilant to what’s going on around you. It is a very real reality that there are people out there that hate you just for simply being you and what you represent to them. We’ve seen evidence of this twice this week and I suspect more to come unfortunately. I am always hopeful so I will leave this message on a positive note, that just as much hate has also been met with just as much love. There are many amazing kind hearted people out there standing up for what’s right and building community, coming together. Even if they are moving in silence behind the scenes or in front stage, I see you and I honour your work.show more

The Sabotaging Practice of Over Supply and Sameness in... the NFT Space. The current zeitgeist of the NFT space is that the same artists are doing the same kind of work five times a year, with project after project leaving a trail of disappointment and discontent among collectors and all of us watching in disbelief as huge resources are extracted from the space over work that feels like it could be left as an "artist study." I understand that you can do what you want with your money as collectors, but we are killing the whole space with this incestuous practice. No artist is that prolific to be able to do 5 collections of 100+ pieces each every year and actually deliver innovation and some kind of creative evolution. Of course, they can pretend play that the work has something new, but there is no precedent nor proof that that has ever happened in the speed that it happens in the NFT space. Again, people are free to through away their resources on whatever they want but with this way of doing things, we more and more are going to start seeing the consequences. Oh! There are consequences? Yes. Maybe unintended, but there are. Let's see. Let's start with the loss of belief in the NFT space as somewhere where emerging artists can come and find support for their experiments. Why even bother to bring experiments, innovation, and new ways to think of art on the blockchain if the same people have all the collectors hypnotized with their magical flutes? Why even try to come to a space where taking risks and challenging the status quo (the mission of art!!!) is overlooked? This makes the NFT space a social club and not a space for art. I guess it is fine, but IMO it is a recipe for disaster. New collectors stay away because the art will slowly but surely become stale and un-challenging. Why even bother to come and see what is happening here if you can't, as a collector, see new weird and up-and-coming artists? The amount of noise emitted by the same artists doing the same art over and over, drowns out any new voices. Again. A recipe for disaster. The NFT space is becoming a space of disappointment and doubt. We think that collections going to zero one after the other, over and over, is not damaging? I feel we are kidding ourselves. Disappointment piles up, and again, the people who will hurt are the emerging artists, the new blood, the ones who are willing to risk the most and, in return, put fire in this cold space of sameness. I love this space—don't get me wrong—it has changed my life, and I believe it has a ton of potential, but things need to change for it to become a beacon of light in art. But we need to support new voices. We need to support new ideas. The challenge is huge. I hope to contribute all I can to this change. I hope more and more see how exciting it is to go out and try to discover what else is out there and move this space forward. But again, I understand the leaps of faith needed, but if there is a space that is based on that, it's the NFT space...so there is hope. We will see. 📺by Boldtronshow more

LLM Knowledge Base → Slides When Andrej Karpathy shared... his LLM Knowledge Base setup, many were wondering how to generate more visual forms of the wiki. There are many options, but I think Gamma is one of the best at producing high-quality, rich presentations. To showcase this, I just built a pipeline that turns my AI papers wiki (1K+ papers across 20 AI agent topics) into polished slide presentations using Gamma. The flow: Obsidian vault → Gamma MCP → embedded preview in my dashboard. I give one command to my agent, which pulls the top papers from each topic (via the wiki), feeds them to Gamma, and renders the presentation inline. The Gamma connector for Claude is a great choice for generating beautiful and professional slides. Easy to use. Go to your Claude instance and add the official Gamma connector. That's it! Claude Code will now have access to all the necessary MCP tools for generating slides. I use the Claude Agent SDK for my agent orchestrator, so I use the official Gamma MCP tools and embed the generated slides in an iframe via my artifact preview. See the clip below for an example.show more

On the 20th of October this happened, I watched... as mainstream media arrived with the U.N. envoy instead of staying the night like the rest of us and seeing how israel was playing mind games and dropping bombs as if it was a toy…total disregard. I didn’t think to post it assuming that no way things would get this bad or last this long. Following this video my mother grounded me saying, “you are one person but part of so many, you do what you can and that makes you a sum of the parts, don’t think of what you can’t do but what you can do”, it was not to lessen from me but rather so I don’t ever get bogged down and see that we all have a role to play. At the end of the day you are speaking up one year against a cult like ideology that has been operating for over 70 years. It may take time but the point is…it has started. We are all a sum of the part and don’t ever underestimate yourself. Instead of thinking there’s nothing I can do, change it to ‘what can I do?’. Even a small action will have an effect in the right direction. As lonely as this year has been for a lot of us it’s important to know that you are not alone in your feelings or your actions, despair is their weapon hope and justice is ours.show more

I graduated!!! I earned a Bachelor of Arts in... Sociology with a concentration in Psychology, summa cum laude! Five years ago, I started this journey with an eighth-grade education, and even that was from a Scientology school, where critical thinking was discouraged and the quality of instruction was subpar, to say the least. I did not get here alone. Thank you to NYU School of Professional Studies and Angie Kamath. Thank you to everyone who supported me, encouraged me, and believed in me, especially on the days I was not sure I could do this. And there were plenty of those days. To my therapist, who told me not to give up when I was told I likely would not be accepted into a prestigious program. To my tutor, without whom I likely would have given up at the harder points along the way. To all those here who have sent me loving messages on social media. And to everyone else who has cheered me on in person through the ups and the downs of it, it means more than I can put into words. It got me over this finish line of being a student again and graduating. That goal once seemed impossible. To those who have asked me, “Why this? Why now?” I pursued higher education to reclaim a piece of myself. When you come out of a high-control group like Scientology, or even a high-control family, there are parts of you that were never allowed to fully develop. Those parts include your curiosity and your ability and right to question. Education was discouraged because knowledge creates confidence in your ability to trust your own mind and navigate the world. That leads to true independence, and that would never be allowed. I wanted that back. But more than that, I needed to understand. I needed to understand how my mother could have us join Scientology when I was just eight years old, and how my family and I could be part of something like this and stay in it for so long. I needed to understand how these systems work, how they influence people, and how they take hold. Without education, access to real information, and support, people can fall into systems that work against their best interests. Some assume that because they are educated, even highly educated, they would never fall for something like this. But it turns out that is not necessarily true. What many of us are impacted by, but never quite understand, is how high-control groups operate. Many still do not understand how misinformation spreads, and how tribalism and radicalization shape what we think, what we believe, and who and what we trust. Without that awareness, none of us are immune. Today, we are seeing how these forces can influence good people and distort reality. History has shown us that this is not new; it just comes in a different form now. Social media connects us in ways we never imagined, but it also creates echo chambers that reinforce beliefs and justify behavior without question. Real critical thinking is hard when we are fed so much by algorithms designed to appeal to us. In learning and achieving this milestone in my own life, it has helped me take a good, hard look at my own beliefs and ideologies. This journey was about healing for me, but also about figuring out how to help others in whatever way I can in the future. So what is in my future? I am considering continuing my education and possibly pursuing a master’s degree, with the goal of contributing to advocacy and policies that protect people, not systems. For now, I am taking this moment in. I am proud of myself. And I am grateful. Thank you for being on this journey with me.show more

Simplicity is at the heart of great software. This... is one of the reasons why Claude Code has been sticky for me. As a builder, I love planning and brainstorming, and this is now a key focus of Claude Code. I use Shift + Tab a lot to cycle between brainstorming, planning, and execution. This functionality provides the appropriate interface for me to either be very involved or less involved as I please. This works particularly well when building out new and complex features or entire new projects. This saves a huge amount of time. It allows me to tune Claude Code to execute and build more effectively. It also builds a loop of trust, and I often (surprisingly) find Claude Code asking for clarifications when it's confused. Coding agents don't normally do that. I have shared before on the power of brainstorming with AI for longer times. Try it and you will not be disappointed. Vibe coding is fun, but pair it with intentional development cycles, and you watch how far you can take a project with coding agents today.show more

If ever there was a goal that defined what... I am all about...well, it is this one. I feel as if FC 26 was made for my style of play. I cannot tell you how happy I am with the changes to dribbling and passing. We. Are. So. Back. On top of that? This 433 I've created is 🔥🔥🔥show more

introducing a new, very fun, LLM benchmark- the Game-of-Life... Bench! the rules are simple: given an 8x8 grid following Conway's game of life rules, the goal is to create an initial pattern with at most 32 cells that can last the longest number of turns before dying/repeating. some results to highlight (with caveats detailed below): - gpt 5.1 lasts the longest with a 106 step run - claude models are really bad at this! they refuse to reason about this task and score < 25 points - deepseek r1 is the best open model with 102 steps. why? because i wanted to create a benchmark that has (i think) no practicality, but is still fun to look at, cheap, and still measures something interesting. i also am a big fan of the game of life. its absurdly simple rules leading to intractability is extremely cool to me. also, i saw a lot of work with LLMs trying to "predict" the next state in Conway's game of life, I think game-of-life bench is more fun because it's pretty open ended and only asks the LLM for the initial state. I also think this could be an RL env? but idk why you would ever train on this task haha i don't think this is a "serious" benchmark because it doesnt measure anything practical, but i still think it's a hard benchmark exactly because you can't predict what happens with your initial state many turns into the future; this is why i was initially expecting all LLMs to be bad at it, but turns out, some are clearly better than the others (the ordering may surprise you!) reminder: this is still a work-in-progress; (1) i am gpu-poor so could only do 10 runs for each model, even though total running cost is relatively low. maybe with some more credits i can run more seeds for each model. (2) i handpicked models which i think are at the frontier right now, plus some others that were on my mind. so, if you'd like to see a model on here, let me know. (3) i currently only do an 8x8 grid because i thought that by itself would be pretty hard for current LLMs, but of course we can increase grid sizes! (4) the coolest thing is, i dont think we can calculate the max possible number of states (yay undecidability!) you can go without repeating, so this is essentially a no-ceiling task, which is pretty cool! again, i did this mostly out of a desire to make LLMs do something fun. if this keeps me entertained for a few more days, i'd likely release a blog post on it. if it keeps me entertained for a week (and someone sponsors me), i'll put more work into it :P lastly, this is fully open sourced, so feel free to run this on your own!show more