Andrej Karpathy

Rewriting Bun in Rust bun.com/blog/bun-in-ru…

@petergostev love the idea of the "swear meter", probably a quite strong eval signal. are these string-based greps?

My view of: Fable 5 vs GPT-5.6-Sol. They are not easy models to compare, these are my vibes - take them as you will. My overall feel is that Fable is a 'wise owl' who is very thoughtful and very well spoken, GPT-5.6-Sol is like a rottweiler who will grab the problem by the throat and not let go until it is done. In other words, Fable, is a fundamentally smarter model - even at low reasoning it can be very insightful and writes in a clear compelling way. GPT-5.6-Sol on the other hand is extremely diligent, I can give it a list of 8 things to do and you will be sure that they will be done. Fable feels more arrogant to me, I was both to get it to build a new benchmark for me - 5.6 worked between 6 hours and 2 days (I tried several times) and it came up with very thoroughly tested, working benchmark. Fable came back within 40 minutes (twice) and the benchmark sounded smart, but was ultimately was 'vibe' based slop and since it was Fable's vibes that was doing the judging, it decided that it was good to go (it kept giving Fable 100% score btw). Some thoughts by category: UI & App building: Fable will still craft a better UI from scratch, the flow of the app would probably be a bit nicer. But I find that Fable often misses quite key things, which GPT-5.6-Sol doesn't. GPT's Frontend skills are big jump vs previous GPT models, but still not as great overall. Writing: Fable is better hands down, Sol feels quite difficult to align to what I want to say or explain things to me simply. Though I think the 'Pro' model writes clearer. Robustness & Reliability: This is where I think GPT-5.6-Sol wins for me hands down. Fable seems to do things of high quality, but I can never relax with it, it always misses something. With 5.6 this just almost never happens. Other things where I liked GPT-5.6-Sol, but can't compare to Fable directly. - Video editing is actually working now, it is not completely perfect, but with the right skill/guidance you can just give it 1h footage and it can give you a 5 min highlight clip no problem - Computer use - getting really rather good, very usable - Sub agents - it is very fluent at managing sub-agents and speaking to different threads, can help with some new workflows - Adhering to existing code patterns - I love this, even without asking it would implement something in a way that aligns with you app - major problem for slop generation - Research - I think it is getting quite a bit better, it still has some bad patterns (e.g being too tactical), but it feels like it is more steerable to be a good researcher - Multi-day runs - the /goal feature is pretty insane with 5.6-Sol, you can run it for days if you wanted to and it does work. Useful to have another thread or /side to check up on it, but I have some great results with it - Token efficiency - it is so much more token efficient and faster than 5.5, in reality it is now much faster than Fable too On the downside, you can feel that Fable is naturally smarter, and I did have some baffling moments with 5.6 when I was getting it to make a fairly simple change in 8 turns - it seemed to get stuck in a dumb stream that was hard to get out of. So it is not AGI, don't get too carried away by the hype. I have some phenomenal examples that I'm honestly blown away by that I'll share, but as a side anecdote, I have a kind of 'swear meter' which counts how often I'm rude to Codex. In GPT-5.5 era, the % was at around 4-5%, it dropped to 1-2% when I was testing GPT-5.6-Sol and it shot up to 7% when I went back to 5.5 - it was so shocking to go back to 5.5 and experience how much worse it was. So is GPT-5.6-Sol better than Fable? On pure intelligence - no. But man, I missed it when I just wanted to get sh*t done. It is insanely capable workhorse that you can give any task to and just expect it to be done. No lectures or 'you are absolutely rightisms', nothing is beneath it, if it takes 2 days to do some dirty work, it will do it. It feels like the first time in a while when we have quite different types of frontier intelligences that benchmark sort of similarly, but feel very different. If you can, you would be probably better off using both and iteratively finding what you'd use Fable or GPT-5.6-Sol for. Perhaps, something like - an architectural discussion with Fable, implementation with 5.6 and docs & comms with Fable.

Agree, it's beautiful, top tier fablemaxxing! :) I think with every new model tier there is something new that qualitatively leaps and surprises, for Fable so far these threejs envs seem to be up there. The bear thing is such a weird little detail to have there, and the fish actually struggles in its mouth. How does an LLM even know all these things from just internet, and then have the ability to convert that understanding into xyz coordinates, meshes, transforms, animations, effects, interactivity and mini stories? Amazing to think about what +1, +2, +3 model tiers might be able to create.

Thank you @karpathy! - this was the most fun video to make - this model is sublime on these test. The bear thing felt a genuine gag :D. My personal favourite though was the 'step into the painting' type of generation, the ability to abstract and put a new world together is at another level

I spent a LOT of time through the hardest 3D prompts at Fable, it is a 45 min video, but I have 60+ very cool demos for you. Also prompts in the next post. youtube.com/watch?v=rTc2_-…

Congrats!! I was impressed to learn about some of the engineering wizardry (e.g. *very* low voltage domains, cluster scale memory, ...) that goes into tokens/watt maxxing of state of the art LLMs at interactive tokens/sec/user. Esp fun and memorable is the idea that this is engineering at the "opposite" regime to that of power transmission lines: very low voltage high current (at tiny distances) vs. very high voltage & low current (at great distances). Looking forward to more!

We're coming out of stealth. We've built our first racks after a successful A0 tapeout, $1B+ in customer contracts, and $800m raised. Early customer tests show us achieving SOTA throughput, latency, and power efficiency on inference workloads. Our first racks ship this summer.

The basic idea is easy and v0 is a hackathon project. The product here is a lot closer to *it actually works*, for enterprise grade deployments, and after quite a bit of internal experimentation and iteration. It’s kind of hard to describe other than (per the post) it’s writing majority of code, it’s deeply integrated, multiplayer, and it starts to feel like everyone is a manager. So I understand it looks easy to dismiss on quick reading but it’s not some LLM Q&A with RAG over Slack, it’s not even OpenClaw adjacent, it’s a different way of working entirely, for people and teams. I work from Slack now.

@karpathy is there anything special here ? cuz i feel like it has already been a thing for long time, i already have agents i can tag

This is a new paradigm for interacting with Claude that is significantly more "inline" with all the other human activity org-wide. Once you do all of the under the hood engineering work to make this "just work" (e.g. across tools, integrations, compute environments, memory, security, etc.), Claude basically joins the team in a seamless way - you can talk to it as you would talk to a person and it can help with a very large variety of workloads. Imo this is the 3rd major redesign of LLM UIUX. The first paradigm was that the LLM is a website you go to, the second was that it is an app you download to your computer. This third one is that it is a self-contained, persistent, asynchronous entity with org-wide tools and context, working alongside teams of humans. It really takes a while to wrap your head around it, but it works and it is awesome.

@EngramLab Congrats on the launch!!

@Siddhos sometimes money and "genuine, positive, non-zero sum value creation" are not highly correlated, and sometimes they *really* are. well-earned!

@karpathy The team is really crazy to make possible what no one ever thought was possible and now generating 4000+ millionaires

In awe of SpaceX and its story - past, present and the future. You can think about it in 10+ different ways and continue re-blowing your mind in circles. Huge congrats to the team! 🚀

@josepha_mayo <-- working on the brains that glide our von neumann probes around, make contact, establish galactic harmony, all that :)

@karpathy bro, ya thinking of going back now?

This is a super exciting release - Claude Fable 5 is the same underlying model as Mythos but with added safeguards. The benchmarks are great and it's SOTA on everything by a margin but I'll add that *qualitatively* also, this is a major-version-bump-deserving step change forward (imo of the same order as Claude 4.5 was in November), peaking especially for long problem-solving sessions on very difficult problems. You can give it a lot more ambitious tasks than what you're used to, the model "gets it" and it will just go, and it's never felt this tempting to stop looking at the code at all (but don't do this in prod!). The model still has quirks that people will run into and the safeguards are configured to be a little too trigger happy for launch, which can hopefully be tuned over time. I feel a lot of things changing as working software increasingly comes out on a tap. The Jevon's paradox kicks in and I feel my own demand for software growing substantially. You can ask for anything - explainers, visualizers, dashboards, bespoke single-use apps (e.g. a full wandb that is hyper-specific just for your project), you can 10X your test suite, auto-optimize code, run giant research projects with custom HTML for the results, anything! "Free your mind" (Matrix ref). Really looking forward to all the things people build!

This has quietly been a miracle month in medicine. In the last 5 weeks we’ve got news on: - retatrutide, the triple agonist GLP-1 from Lilly, basically melting fat and body-wide inflammation at record levels - RevMed’s new pancreatic cancer drug showing unprecedented abilities to extend life - small trial of a one-and-done PCSK9 gene editing therapy for slashing LDL cholesterol - Mayo’s AI-assisted radiology showing vastly improved cancer detection - this new therapy for metastatic solid tumors This stuff is at varying levels of evidence. Retatrutide is ~100% on its way, other stuff needs more clinical trial data. But put it together and we’re maybe on the verge of majorly reducing the mortality of heart disease and cancer, the two leading causes of death in America.

Personal update: I've joined Anthropic. I think the next few years at the frontier of LLMs will be especially formative. I am very excited to join the team here and get back to R&D. I remain deeply passionate about education and plan to resume my work on it in time.

@jino_rohit I was recording my nanochat video when I realized that “first boot up an 8XH100 from your favorite provider!” would instantly get everyone stuck on step 1 of the video

did all the H100 disappear from every platform all of a sudden?

This works really well btw, at the end of your query ask your LLM to "structure your response as HTML", then view the generated file in your browser. I've also had some success asking the LLM to present its output as slideshows, etc. More generally, imo audio is the human-preferred input to AIs but vision (images/animations/video) is the preferred output from them. Around a ~third of our brains are a massively parallel processor dedicated to vision, it is the 10-lane superhighway of information into brain. As AI improves, I think we'll see a progression that takes advantage: 1) raw text (hard/effortful to read) 2) markdown (bold, italic, headings, tables, a bit easier on the eyes) <-- current default 3) HTML (still procedural with underlying code, but a lot more flexibility on the graphics, layout, even interactivity) <-- early but forming new good default ...4,5,6,... n) interactive neural videos/simulations Imo the extrapolation (though the technology doesn't exist just yet) ends in some kind of interactive videos generated directly by a diffusion neural net. Many open questions as to how exact/procedural "Software 1.0" artifacts (e.g. interactive simulations) may be woven together with neural artifacts (diffusion grids), but generally something in the direction of the recently viral x.com/zan2434/status… There are also improvements necessary and pending at the input. Audio nor text nor video alone are not enough, e.g. I feel a need to point/gesture to things on the screen, similar to all the things you would do with a person physically next to you and your computer screen. TLDR The input/output mind meld between humans and AIs is ongoing and there is a lot of work to do and significant progress to be made, way before jumping all the way into neuralink-esque BCIs and all that. For what's worth exploring at the current stage, hot tip try ask for HTML.