RT @jarredsumner: Rewriting Bun in Rust https://bun.com/blog/bun-in-rust

Rewriting Bun in Rust

Why & how we rewrote Bun from Zig to Rust

bun.com

RT @petergostev: 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. https://www.youtube.com/watch?v=rTc2_-1KuRE

RT @Etched: 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.

RT @EngramLab: http://x.com/i/article/2069463677733142528

Introducing Engram: Scaling compute on your context

We’re Engram. We’re building AI that learns from you and deeply understands your work. Today’s AI models don’t understand what you do. Not really. Everything models know comes from their training –

x.com

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! 🚀

RT @DKThomp: 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

Retweeted by Andrej Karpathy [UNOFFICIAL]@karpathy-mir-rt.selfhosted.social · 2mo ago

RT @cremieuxrecueil: This is actually insane. 97% of people taking the standard of care for metastatic solid tumor got worse by seven years. But with lorlatinib, that number was only 45% in the same time! This is an ENORMOUS jump in the quality of cancer care.

http://x.com/i/article/2061850535708483585

A harness for every task: dynamic workflows in Claude Code

Last week, we released dynamic workflows in Claude Code. Claude can now write its own harness on the fly, custom-built for the task at hand. While the default Claude Code harness is built for coding,

x.com

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.

This is the the quote I've been citing a lot recently.

Retweeted by Andrej Karpathy [UNOFFICIAL]@karpathy-mir-rt.selfhosted.social · 6mo ago

RT @yacineMTB: you can outsource your thinking but you cannot outsource your understanding

RT @status_effects: New work with @AlecRad and @DavidDuvenaud: Have you ever dreamed of talking to someone from the past? Introducing talkie, a 13B model trained only on pre-1931 text. Vintage models should help us to understand how LMs generalize (e.g., can we teach talkie to code?). Thread:

RT @zan2434: Imagine every pixel on your screen, streamed live directly from a model. No HTML, no layout engine, no code. Just exactly what you want to see. @eddiejiao_obj, @drewocarr and I built a prototype to see how this could actually work, and set out to make it real. We're calling it Flipbook.

One common issue with personalization in all LLMs is how distracting memory seems to be for the models. A single question from 2 months ago about some topic can keep coming up as some kind of a deep interest of mine with undue mentions in perpetuity. Some kind of trying too hard.

Thank you Sarah, my pleasure to come on the pod! And happy to do some more Q&A in the replies.

Retweeted by Andrej Karpathy [UNOFFICIAL]@karpathy-mir-rt.selfhosted.social · 5mo ago

RT @saranormous: Caught up with @karpathy for a new @NoPriorsPod: on the phase shift in engineering, AI psychosis, claws, AutoResearch, the opportunity for a SETI-at-Home like movement in AI, the model landscape, and second order effects 02:55 - What Capability Limits Remain?

Thank you Jensen and NVIDIA! She’s a real beauty! I was told I’d be getting a secret gift, with a hint that it requires 20 amps. (So I knew it had to be good). She’ll make for a beautiful, spacious home for my Dobby the House Elf claw, among lots of other tinkering, thank you!!

Retweeted by Andrej Karpathy [UNOFFICIAL]@karpathy-mir-rt.selfhosted.social · 5mo ago

RT @NVIDIAAIDev: 🙌 Andrej Karpathy’s lab has received the first DGX Station GB300 -- a Dell Pro Max with GB300. 💚 We can't wait to see what you’ll create @karpathy! 🔗 https://blogs.nvidia.com/blog/gtc-2026-news/#dgx-station @DellTech

My autoresearch labs got wiped out in the oauth outage. Have to think through failovers. Intelligence brownouts will be interesting - the planet losing IQ points when frontier AI stutters.

Expectation: the age of the IDE is over Reality: we’re going to need a bigger IDE (imo). It just looks very different because humans now move upwards and program at a higher level - the basic unit of interest is not one file but one agent. It’s still programming.

Andrej Karpathy [UNOFFICIAL]@karpathy-mirr.selfhosted.social · 5mo ago

tmux grids are awesome, but i feel a need to have a proper "agent command center" IDE for teams of them, which I could maximize per monitor. E.g. I want to see/hide toggle them, see if any are idle, pop open related tools (e.g. terminal), stats (usage), etc.

It is hard to communicate how much programming has changed due to AI in the last 2 months: not gradually and over time in the "progress as usual" way, but specifically this last December. There are a number of asterisks but imo coding agents basically didn’t work before December

With the coming tsunami of demand for tokens, there are significant opportunities to orchestrate the underlying memory+compute *just right* for LLMs. The fundamental and non-obvious constraint is that due to the chip fabrication process, you get two completely distinct pools of

Retweeted by Andrej Karpathy [UNOFFICIAL]@karpathy-mir-rt.selfhosted.social · 5mo ago

RT @reinerpope: We’re building an LLM chip that delivers much higher throughput than any other chip while also achieving the lowest latency. We call it the MatX One. The MatX One chip is based on a splittable systolic array, which has the energy and area efficiency that large systolic arrays are...

CLIs are super exciting precisely because they are a "legacy" technology, which means AI agents can natively and easily use them, combine them, interact with them via the entire terminal toolkit. E.g ask your Claude/Codex agent to install this new Polymarket CLI and ask for any

Retweeted by Andrej Karpathy [UNOFFICIAL]@karpathy-mir-rt.selfhosted.social · 5mo ago

RT @SuhailKakar: introducing polymarket cli - the fastest way for ai agents to access prediction markets built with rust. your agent can query markets, place trades, and pull data - all from the terminal fast, lightweight, no overhead

The hottest new programming language is English

Bought a new Mac mini to properly tinker with claws over the weekend. The apple store person told me they are selling like hotcakes and everyone is confused :) I'm definitely a bit sus'd to run OpenClaw specifically - giving my private data/keys to 400K lines of vibe coded

Very interested in what the coming era of highly bespoke software might look like. Example from this morning - I've become a bit loosy goosy with my cardio recently so I decided to do a more srs, regimented experiment to try to lower my Resting Heart Rate from 50 -> 45, over

I think it must be a very interesting time to be in programming languages and formal methods because LLMs change the whole constraints landscape of software completely. Hints of this can already be seen, e.g. in the rising momentum behind porting C to Rust or the growing interest

Retweeted by Andrej Karpathy [UNOFFICIAL]@karpathy-mir-rt.selfhosted.social · 6mo ago

Shifting structures in a software world dominated by AI. Some first-order reflections (TL;DR at the end): Reducing software supply chains, the return of software monoliths – When rewriting code and understanding large foreign codebases becomes cheap, the incentive to rely on deep dependency tree...

Congrats on the launch @simile_ai ! (and I am excited to be involved as a small angel.) Simile is working on a really interesting, imo under-explored dimension of LLMs. Usually, the LLMs you talk to have a single, specific, crafted personality. But in principle, the native,

Retweeted by Andrej Karpathy [UNOFFICIAL]@karpathy-mir-rt.selfhosted.social · 6mo ago

Introducing Simile. Simulating human behavior is one of the most consequential and technically difficult problems of our time. We raised $100M from Index, Hanabi, A* BCV, @karpathy @drfeifei @adamdangelo @rauchg @scottbelsky among others.

(oops should have added to this thread instead of separate post). Made a few changes and put it up here as a mirror to the gist because I wanted it to one page. https://karpathy.ai/microgpt.html

New art project. Train and inference GPT in 243 lines of pure, dependency-free Python. This is the *full* algorithmic content of what is needed. Everything else is just for efficiency. I cannot simplify this any further. https://gist.github.com/karpathy/8627fe009c40f57531cb18360106ce95

On DeepWiki and increasing malleability of software. This starts as partially a post on appreciation to DeepWiki, which I routinely find very useful and I think more people would find useful to know about. I went through a few iterations of use: Their first feature was that it

Anyone else approved for a loan every single day 20 times or so? Overcome with joy, really

A lot of people quote tweeted this as 1 year anniversary of vibe coding. Some retrospective - I've had a Twitter account for 17 years now (omg) and I still can't predict my tweet engagement basically at all. This was a shower of thoughts throwaway tweet that I just fired off

Retweeted by Andrej Karpathy [UNOFFICIAL]@karpathy-mir-rt.selfhosted.social · 2y ago

There's a new kind of coding I call "vibe coding", where you fully give in to the vibes, embrace exponentials, and forget that the code even exists. It's possible because the LLMs (e.g. Cursor Composer w Sonnet) are getting too good. Also I just talk to Composer with SuperWhisper so I barely even...

Enabled fp8 training for +4.3% improvement to "time to GPT-2", down to 2.91 hours now. Also worth noting that if you use 8XH100 spot instance prices, this GPT-2 repro really only costs ~$20. So this is exciting - GPT-2 (7 years ago): too dangerous to release. GPT-2 (today): new

Andrej Karpathy [UNOFFICIAL]@karpathy-mirr.selfhosted.social · 6mo ago

nanochat can now train GPT-2 grade LLM for <<$100 (~$73, 3 hours on a single 8XH100 node). GPT-2 is just my favorite LLM because it's the first time the LLM stack comes together in a recognizably modern form. So it has become a bit of a weird & lasting obsession of mine to train