While personal agents like Instinct, Grok Bot or Muse... are getting really good at long-horizon tasks, there is also an entire class of problems where I need something simple done right now. We keep building new widgets for these. Long term, they could be generated on the fly with generative UI, like json-render from Chris Tate. Jev-based and inspired by anish.. Was fun hacking on this with Konstantin Hohr!show more

The context size of video world models is only... a few frames. Like a human with severe memory loss! We design a long-term memory for world models based on explicit 3D representations inspired by the human mind. This enables long-term consistency. 1/3show more

New experiment: json-render + jev The future Generative UI... is instant Your components, your actions, your design system Rendered in millisecondsshow more

To me so far the big news with Grok... 4.7 is it's speed. The new "fast" mode is actually extremely fast (idk what the TPS is but it's really good) It's very obviously not Astra/Fable class, SpaceXAi (or anyone else really) has yet to make one so far. Grok 4.7 is pretty clearly competing with Opus/Sol, and I would definitely take Grok 4.7 over either of them Price is very good, my gut says it's more efficient but I don't have hard numbers on that yet, and it's got all the main capabilities u need to actually be useful these days: subagents, long running tasks, looping, etc. Supposedly they trained it on the Grok Bot harness so it's really good at conversation + knowledge work. Really curious how that plays out, good product is SpaceXAi's biggest advantage right now so getting the models tailor made for those could work. Especially if that lets them keep the model on the cheaper side so they can serve more of itshow more

Today, we're joining Google's release of A2UI v0.9 🎉... Declarative Generative UI with your own design system. Works with any AG-UI Agent. Your agents describes UI via JSON, your frontend renders it using your components catalog like lego building blocks UI is alive and dead. CLI for agents, Generative UI for humans. Try it out: npx copilotkit@latest create my-app --framework a2uishow more

𝙾𝚙𝚎𝚗 𝙱𝚘𝚝 now supports Open Generative UI Get interactive,... AI-generated UI on the fly, streamed directly inside of the chat. Sandboxed, with controlled access 👇show more

For new followers: - I'm a long-time investor and... builder in this space. - Founding Contributor of Realms.World ☁️. - Co-founder of Dojo. - Builder with the kings at Cartridge. - Starknet (Privacy Arc) class of '21. - Founder and Game Director of ETERNUM HAS MOVED. - Founder of Daydreams.Systems (x402, 8004 agents) My prime purpose for the past three years has been to build onchain infrastructure to enable the next generation of onchain experiences. This is done Starknet (Privacy Arc) as it is the superior VM for building complex applications—this will become clear soon enough. I work up and down the entire stack, from low-level indexing and contracts to GUI design. Nothing is out of scope. I have been pushing on agents for two years, mostly using existing frameworks like , until I came across @ElizaOS_ai in October. As I focused on building agents for ETERNUM HAS MOVED, it became clear that agents playing games require infinite paths to achieve goals. Thus, it's not scalable to hardcode functions—agents need to have total fluidity to take any action or call anything the game requires in any order. And ironically onchain infra is perfect for agent playgrounds because of its open nature. This exploration led me to create Daydreams.Systems (x402, 8004 agents), which focuses on the hardest problems of agents: long time-horizon goals using Hierarchical task networks (HTN). Daydreams agents don't require custom code—they work entirely based on 'sleeves'—which are just markdown files that explain how the agent can interact with the service (API docs, game guides, etc.) My thesis is simple. By focusing on the hardest problem (games), the design of the library will naturally lean towards an optimal structure for any problem an agent could face. We are early in this path and iterating with speed. If you are an onchain app developer or game builder—DM me, I want to know the architecture of your game so we can build sleeves together.show more

Over the past week, you shared your New Year... Resolutions for us. Features, ideas, hopes and thoughtful nudges on how we can simply be, the most Based version of us. Thank you for showing up and once again reminding us about why we do what we do. Our #BasedNewYear campaign is now officially closed but the job's not finished. We started 2026 by listening and now, we continue by building. We really loved what was communicated to us and some of these ideas will be the starting points of new verticals in our long-term roadmap. Excited to be building Based together with you. Winners of this campaign will be announced very soon and there will definitely be more upcoming initiatives to look forward to. Stay tuned & Stay Based!show more

Vibe coding, with guardrails. json-render now exports production-ready source... code using @𝚓𝚜𝚘𝚗-𝚛𝚎𝚗𝚍𝚎𝚛/𝚌𝚘𝚍𝚎𝚐𝚎𝚗 The best of Generative UI paired with traditional code generationshow more

Introducing: Odysseys2 - hardest long horizon benchmark for web... agents based on real user tasks 🏗️ We collaborated with Lawrence Jang Russ Salakhutdinov from Carnegie Mellon University > SOTA agent fully completes only 47/100 > 5 agents complete none > 8-12 real rubrics per task, 60 min on the live web Web agents are becoming better than humans at knowledge work.show more

I was really impressed with some of the long... passes he made yesterday, We could have scored them on a good dayshow more

I’m releasing OpenTTD-Bench, a benchmark for measuring frontier LLM... agents on real-time, long-horizon tasks, based on a complex business simulation game OpenTTD, where models run competing transportation companies and must make the most amount of profit.show more

Inspired by the new Airbnb release and my passion... for interactive animation in Rive , I made some exploration! With the rise of AI-generated raster assets, I wonder could Skeuomorphism become trendy again? Will we soon start seeing design briefs say: “We want an Apple-like style, OpenAI-like style… and now Airbnb-like style”? :)show more

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

On August 11, SpaceXAI shipped Grok Bot. Grok Bot... was built to stay on, gets its own computer, works inside apps and tools like you do, and keep working 24/7 even when your laptop is off. And a lot of AI agents existed before this, including OpenAI’s earlier agent products, but most of them worked more like where you give it a job, let it finish, and then it stops. Grok Bot pushed the idea of having an AI worker that is always there, always running, and organized more like a team. You can have a chief of staff at the top, different specialists handling different jobs, and now the same bot can even be shared across a team. Then on September 8, Meta launched Muse, 28 days later. Meta called it “The World’s First Personal AI Agent Built for Everyone.” Muse also gets its own computer in the cloud. It can work across apps, keep going after you close it, and ask before doing things like sending emails or spending money. Zuck made it a huge part of Meta Connect and talked about bringing this kind of agent to billions of people. Then yesterday, 49 days after Grok Bot launched, Sam introduced dots. OpenAI describes them as always-on agents with their own cloud computers that can work on your goals 24/7 and connect across thousands of apps. A full team of dots is part of the bigger vision too. So when I see people framing this as OpenAI vs. Meta, a huge part of the story is missing… Grok Bot shipped first. The shift toward always-on AI workers with their own computers is clearly where the industry is going now and Grok Bot kicked off the next big AI product category… it’s one of the hottest products in AI. But don’t get it twisted, everyone is copying Elon right now.show more

The Nihilanth model I made earlier this year was... one of my favorite personal projects I've done so far. Seems fitting that something might be right on the horizon from the franchise.... #halflifeshow more

Been working on my Ballistic Practice Map Rework for... a while now. Here's a sneak peek at the new UI I made 👀 This will also be used in something big towards the end of the year with ... 🧐show more

Generative UI agents can now render real shadcn/ui components.... shadcn /ui support is now live in OpenUI.show more

Connor Norby postgame: "They just want me to be... me, and it felt like for a long time I was trying to be someone that I wasn't, and I got away from the things I was good at. There's always time to work on your weaknesses. Those never stop, but it was when I was getting away from my strengths, that was what really hurt me. From day one, from the first conversation I had [with the #Rockies], it was we want you to be you."show more

Opus 5.5 + GrokBot + Jev... I can't believe... that I build it I packed the best of AI into ONE agent - now 99% of people’s AI agents look dumb, slow, and expensive Try here (free): prompt → GrokBot → Jev chooses LLM → Claude / GPT working on GrokBot's computer 24/7 → result → Jev sends only the tasks Grok is weak at to Opus or GPT → Jev picks the best model for each task - for example, Claude for motion design and Codex for web design → runs on the ChatGPT and Claude subscriptions you already pay for (API also work) → works on GrokBot computer while you keep chatting → checks every result against the goal before you see it → GrokBot gets smarter and cheaper at the same time → And plenty more features in a bot everyone will call "obvious" by 2030 Try Jevopus, thank me later - then read the article on the full Jev architecture ↓show more