Andrej Karpathy(@karpathy)

@yash1_ @shreyansj iirc Geoff Hinton’s official title at Google at one point was “intern” :D

Andrej Karpathy (@karpathy) — Sun, 24 May 2026 16:22:45 GMT

@yash1_@shreyansj iirc Geoff Hinton’s official title at Google at one point was “intern” :D

💬33🔄53❤️1734👀365315📊178

⚡ Powered by xgo.ing

@shreyansj It’s refreshing to see a company of this size successfully call bs on the whole thing to ...

Andrej Karpathy (@karpathy) — Sun, 24 May 2026 15:49:28 GMT

@shreyansj It’s refreshing to see a company of this size successfully call bs on the whole thing to this extent. One group of MTS on a mission, clean.

💬123🔄140❤️7914👀384357📊733

⚡ Powered by xgo.ing

Personal update: I've joined Anthropic. I think the next few years at the frontier of LLMs will be e...

Andrej Karpathy (@karpathy) — Tue, 19 May 2026 15:05:42 GMT

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.

💬7969🔄11151❤️149630👀27425621📊22457

⚡ Powered by xgo.ing

@jino_rohit I was recording my nanochat video when I realized that “first boot up an 8XH100 from you...

Andrej Karpathy (@karpathy) — Mon, 18 May 2026 03:24:47 GMT

@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

💬64🔄30❤️1983👀201513📊214

⚡ Powered by xgo.ing

This works really well btw, at the end of your query ask your LLM to "structure your response as HTM...

Andrej Karpathy (@karpathy) — Mon, 11 May 2026 16:20:21 GMT

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.

💬1025🔄2016❤️19147👀3779585📊5610

⚡ Powered by xgo.ing

@si_pbc @sonyatweetybird @MikowaiA @YasminRazavi @tszzl @_milankovac_ VPT (https://t.co/CSxHcXY6Vh) ...

Andrej Karpathy (@karpathy) — Thu, 30 Apr 2026 18:35:43 GMT

@si_pbc@sonyatweetybird@MikowaiA@YasminRazavi@tszzl@_milankovac_ VPT (openai.com/index/vpt/) blew my mind back in 2022 so I was very excited to see SI scale up the idea with FDM1, but for knowledge work / computer use. Excited and looking forward to more!

💬16🔄21❤️401👀48025📊44

⚡ Powered by xgo.ing

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

Andrej Karpathy (@karpathy) — Thu, 30 Apr 2026 17:43:06 GMT

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

kache@yacineMTB

you can outsource your thinking
but you cannot outsource your understanding

🔗 View Quoted Tweet

💬846🔄4372❤️46567👀2566994📊5148

⚡ Powered by xgo.ing

Fireside chat at Sequoia Ascent 2026 from a ~week ago. Some highlights: The first theme I tried to ...

Andrej Karpathy (@karpathy) — Thu, 30 Apr 2026 17:28:50 GMT

Fireside chat at Sequoia Ascent 2026 from a ~week ago. Some highlights:

The first theme I tried to push on is that LLMs are about a lot more than just speeding up what existed before (e.g. coding). Three examples of new horizons:

1. menugen: an app that can be fully engulfed by LLMs, with no classical code needed: input an image, output an image and an LLM can natively do the thing.
2. install .md skills instead of install .sh scripts. Why create a complex Software 1.0 bash script for e.g. installing a piece of software if you can write the installation out in words and say "just show this to your LLM".  The LLM is an advanced interpreter of English and can intelligently target installation to your setup, debug everything inline, etc.
3. LLM knowledge bases as an example of something that was *impossible* with classical code because it's computation over unstructured data (knowledge) from arbitrary sources and in arbitrary formats, including simply text articles etc.

I pushed on these because in every new paradigm change, the obvious things are always in the realm of speeding up or somehow improving what existed, but here we have examples of functionality that either suddenly perhaps shouldn't even exist (1,2), or was fundamentally not possible before (3).

The second (ongoing) theme is trying to explain the pattern of jaggedness in LLMs. How it can be true that a single artifact will simultaneously 1) coherently refactor a 100,000-line code base *and* 2) tell you to walk to the car wash to wash your car. I previously wrote about the source of this as having to do with verifiability of a domain, here I expand on this as having to also do with economics because revenue/TAM dictates what the frontier labs choose to package into training data distributions during RL. You're either in the data distribution (on the rails of the RL circuits) and flying or you're off-roading in the jungle with a machete, in relative terms. Still not 100% satisfied with this, but it's an ongoing struggle to build an accurate model of LLM capabilities if you wish to practically take advantage of their power while avoiding their pitfalls, which brings me to...

Last theme is the agent-native economy. The decomposition of products and services into sensors, actuators and logic (split up across all of 1.0/2.0/3.0 computing paradigms), how we can make information maximally legible to LLMs, some words on the quickly emerging agentic engineering and its skill set, related hiring practices, etc., possibly even hints/dreams of fully neural computing handling the vast majority of computation with some help from (classical) CPU coprocessors.

Stephanie Zhan@stephzhan

@karpathy and I are back! At @sequoia AI Ascent 2026. And a lot has changed. Last year, he coined “vibe coding”. This year, he’s never felt more behind as a programmer.

The big shift: vibe coding raised the floor. Agentic engineering raises the ceiling.

We talk about what it means to build seriously in the agent era. Not just moving faster. Building new things, with new tools, while preserving the parts that still require human taste, judgment, and understanding.

Your browser does not support the video tag.

🔗 View on Twitter

🔗 View Quoted Tweet

💬364🔄797❤️6070👀1175914📊1422

⚡ Powered by xgo.ing

@VBarsoum Haha yeah I call it cozy coding :) Usage: “This valentines, cozy code with someone you lov...

Andrej Karpathy (@karpathy) — Thu, 30 Apr 2026 00:42:48 GMT

@VBarsoum Haha yeah I call it cozy coding :)
Usage: “This valentines, cozy code with someone you love”

💬89🔄47❤️2332👀130049📊260

⚡ Powered by xgo.ing

Yes it's the tractable form of brain upload. There's a ton of scifi on brain uploads that requires w...

Andrej Karpathy (@karpathy) — Fri, 10 Apr 2026 15:32:10 GMT

Yes it's the tractable form of brain upload. There's a ton of scifi on brain uploads that requires way too exotic tech (scanning and simulating brains etc), when we're about to get a lossy and approximate version of that *a lot* sooner via LLM simulators. You can easily imagine a "brain upload" startup - you show up for a few days to carry out detailed video interviews, then they use all that data with an LLM finetuning process to "upload" you and give you an API endpoint of your simulation that you can talk to. Look at what's already possible with HeyGen as an example, but combine it with an LLM model that has deep knowledge and personality. Trippy and admittedly kind of dystopian but in principle quite possible around now.

💬130🔄121❤️2027👀153776📊417

⚡ Powered by xgo.ing

Someone recently suggested to me that the reason OpenClaw moment was so big is because it's the firs...

Andrej Karpathy (@karpathy) — Thu, 09 Apr 2026 20:38:48 GMT

Someone recently suggested to me that the reason OpenClaw moment was so big is because it's the first time a large group of non-technical people (who otherwise only knew AI as synonymous with ChatGPT as a website) experienced the latest agentic models.

💬275🔄185❤️4080👀529505📊592

⚡ Powered by xgo.ing

Judging by my tl there is a growing gap in understanding of AI capability. The first issue I think ...

Andrej Karpathy (@karpathy) — Thu, 09 Apr 2026 20:10:52 GMT

Judging by my tl there is a growing gap in understanding of AI capability.

The first issue I think is around recency and tier of use. I think a lot of people tried the free tier of ChatGPT somewhere  last year and allowed it to inform their views on AI a little too much. This is a group of reactions laughing at various quirks of the models, hallucinations, etc. Yes I also saw the viral videos of OpenAI's Advanced Voice mode fumbling simple queries like "should I drive or walk to the carwash". The thing is that these free and old/deprecated models don't reflect the capability in the latest round of state of the art agentic models of this year, especially OpenAI Codex and Claude Code.

But that brings me to the second issue. Even if people paid $200/month to use the state of the art models, a lot of the capabilities are relatively "peaky" in highly technical areas. Typical queries around search, writing, advice, etc. are *not* the domain that has made the most noticeable and dramatic strides in capability. Partly,  this is due to the technical details of reinforcement learning and its use of verifiable rewards. But partly, it's also because these use cases are not sufficiently prioritized by the companies in their hillclimbing because they don't lead to as much $$$ value. The goldmines are elsewhere, and the focus comes along.

So that brings me to the second group of people, who *both* 1) pay for and use the state of the art frontier agentic models (OpenAI Codex / Claude Code) and 2) do so professionally in technical domains like programming, math and research. This group of people is subject to the highest amount of "AI Psychosis" because the recent improvements in these domains as of this year have been nothing short of staggering. When you hand a computer terminal to one of these models, you can now watch them melt programming problems that you'd normally expect to take days/weeks of work. It's this second group of people that assigns a much greater gravity to the capabilities, their slope, and various cyber-related repercussions.

TLDR the people in these two groups are speaking past each other. It really is simultaneously the case that OpenAI's free and I think slightly orphaned (?) "Advanced Voice Mode" will fumble the dumbest questions in your Instagram's reels and *at the same time*, OpenAI's highest-tier and paid Codex model will go off for 1 hour to coherently restructure an entire code base, or find and exploit vulnerabilities in computer systems. This part really works and has made dramatic strides because 2 properties: 1) these domains offer explicit reward functions that are verifiable meaning they are easily amenable to reinforcement learning training (e.g. unit tests passed yes or no, in contrast to writing, which is much harder to explicitly judge),  but also 2) they are a lot more valuable in b2b settings, meaning that the biggest fraction of the team is focused on improving them. So here we are.

staysaasy@staysaasy

The degree to which you are awed by AI is perfectly correlated with how much you use AI to code.

🔗 View Quoted Tweet

💬1199🔄2531❤️20810👀4474710📊3700

⚡ Powered by xgo.ing

@kepano I just tried it this morning on the 245-page Mythos pdf and it failed badly and the outputs ...

Andrej Karpathy (@karpathy) — Thu, 09 Apr 2026 17:22:58 GMT

@kepano I just tried it this morning on the 245-page Mythos pdf and it failed badly and the outputs were all mangled. Converting pdfs is really hard, I think it has to probably be a Skill not a program, for a SOTA LLM for it to work properly.

💬168🔄36❤️1663👀272652📊336

⚡ Powered by xgo.ing

Surprised with how good the comments on github gists are. A lot more helpful, insightful, constructi...

Andrej Karpathy (@karpathy) — Sun, 05 Apr 2026 14:58:44 GMT

Surprised with how good the comments on github gists are. A lot more helpful, insightful, constructive, a lot less AI... Is it the user community? The markdown format? The (lack of) incentives?

Suddenly feeling like I should gist more.
@github consider competing with X (?)

💬182🔄48❤️1200👀450398📊274

⚡ Powered by xgo.ing

Farzapedia, personal wikipedia of Farza, good example following my Wiki LLM tweet. I really like th...

Andrej Karpathy (@karpathy) — Sat, 04 Apr 2026 23:28:36 GMT

Farzapedia, personal wikipedia of Farza, good example following my Wiki LLM tweet.

I really like this approach to personalization in a number of ways, compared to "status quo" of an AI that allegedly gets better the more you use it or something:

1. Explicit. The memory artifact is explicit and navigable (the wiki), you can see exactly what the AI does and does not know and you can inspect and manage this artifact, even if you don't do the direct text writing (the LLM does). The knowledge of you is not implicit and unknown, it's explicit and viewable.
2. Yours. Your data is yours, on your local computer, it's not in some particular AI provider's system without the ability to extract it. You're in control of your information. 
3. File over app. The memory here is a simple collection of files in universal formats (images, markdown). This means the data is interoperable: you can use a very large collection of tools/CLIs or whatever you want over this information because it's just files. The agents can apply the entire Unix toolkit over them. They can natively read and understand them. Any kind of data can be imported into files as input, and any kind of interface can be used to view them as the output. E.g. you can use Obsidian to view them or vibe code something of your own. Search "File over app" for an article on this philosophy.
4. BYOAI. You can use whatever AI you want to "plug into" this information - Claude, Codex, OpenCode, whatever. You can even think about taking an open source AI and finetuning it on your wiki - in principle, this AI could "know" you in its weights, not just attend over your data.

So this approach to personalization puts *you* in full control. The data is yours. In Universal formats. Explicit and inspectable. Use whatever AI you want over it, keep the AI companies on their toes! :)

Certainly this is not the simplest way to get an AI to know you - it does require you to manage file directories and so on, but agents also make it quite simple and they can help you a lot. I imagine a number of products might come out to make this all easier, but imo "agent proficiency" is a CORE SKILL of the 21st century. These are extremely powerful tools - they speak English and they do all the computer stuff for you. Try this opportunity to play with one.

Farza 🇵🇰🇺🇸@FarzaTV

This is Farzapedia.

I had an LLM take 2,500 entries from my diary, Apple Notes, and some iMessage convos to create a personal Wikipedia for me.

It made 400 detailed articles for my friends, my startups, research areas, and even my favorite animes and their impact on me complete with backlinks.

But, this Wiki was not built for me! I built it for my agent!

The structure of the wiki files and how it's all backlinked is very easily crawlable by any agent + makes it a truly useful knowledge base.

I can spin up Claude Code on the wiki and starting at index.md (a catalog of all my articles) the agent does a really good job at drilling into the specific pages on my wiki it needs context on when I have a query.

For example, when trying to cook up a new landing page I may ask:

"I'm trying to design this landing page for a new idea I have. Please look into the images and films that inspired me recently and give me ideas for new copy and aesthetics".

In my diary I kept track of everything from: learnings, people, inspo, interesting links, images.

So the agent reads my wiki and pulls up my "Philosophy" articles from notes on a Studio Ghibli documentary, "Competitor" articles with YC companies whose landing pages I screenshotted, and pics of 1970s Beatles merch I saved years ago. And it delivers a great answer.

I built a similar system to this a year ago with RAG but it was ass.

A knowledge base that lets an agent find what it needs via a file system it actually understands just works better.

The most magical thing now is as I add new things to my wiki (articles, images of inspo, meeting notes) the system will likely update 2-3 different articles where it feels that context belongs, or, just creates a new article.

It's like this super genius librarian for your brain that's always filing stuff for your perfectly and also let's you easily query the knowledge for tasks useful to you (ex. design, product, writing, etc) and it never gets tired.

I might spend next week productizing this, if that's of interest to you DM me + tell me your usecase!

Your browser does not support the video tag.

🔗 View on Twitter

🔗 View Quoted Tweet

💬473🔄825❤️9025👀1404160📊2375

⚡ Powered by xgo.ing

Something I've been thinking about - I am bullish on people (empowered by AI) increasing the visibil...

Andrej Karpathy (@karpathy) — Sat, 04 Apr 2026 21:57:57 GMT

Something I've been thinking about - I am bullish on people (empowered by AI) increasing the visibility, legibility and accountability of their governments.

Historically, it is the governments that act to make society legible (e.g. "Seeing like a state" is the common reference), but with AI, society can dramatically improve its ability to do this in reverse. Government accountability has not been constrained by access (the various branches of government publish an enormous amount of data), it has been constrained by intelligence - the ability to process a lot of raw data, combine it with domain expertise and derive insights. As an example, the 4000-page omnibus bill is "transparent" in principle and in a legal sense, but certainly not in a practical sense for most people. There's a lot more like it: laws, spending bills, federal budgets, freedom of information act responses, lobbying disclosures... Only a few highly trained professionals (investigative journalists) could historically process this information. This bottleneck might dissolve - not only are the professionals further empowered, but a lot more people can participate.

Some examples to be precise: Detailed accounting of spending and budgets, diff tracking of legislation, individual voting trends w.r.t. stated positions or speeches, lobbying and influence (e.g. graph of lobbyist -> firm -> client -> legislator -> committee -> vote -> regulation), procurement and contracting, regulatory capture warning lights, judicial and legal patterns, campaign finance... Local governments might be even more interesting because the governed population is smaller so there is less national coverage: city council meetings, decisions around zoning, policing, schools, utilities...

Certainly, the same tools can easily cut the other way and it's worth being very mindful of that, but I lean optimistic overall that added participation, transparency and accountability will improve democratic, free societies.

(the quoted tweet is half-ish related, but inspired me to post some recent thoughts)

Harry Rushworth@Hrushworth

The British Government is a complicated beast. Dozens of departments, hundreds of public bodies, more corporations than one can count...

Such is its complexity that there isn't an org chart for it.

Well, there wasn't...

Introducing ⚙️Machinery of Government⚙️

🔗 View Quoted Tweet

💬416🔄739❤️5944👀1006446📊1139

⚡ Powered by xgo.ing

@NirDiamantAI Peter Steinberger told me that he wants PR to be "prompt request". His agents are perf...

Andrej Karpathy (@karpathy) — Sat, 04 Apr 2026 16:54:22 GMT

@NirDiamantAI Peter Steinberger told me that he wants PR to be "prompt request". His agents are perfectly capable of implementing most ideas, so there is no need to take your idea, expand it into a vibe coded mess using free tier ChatGPT and send that as a PR, which is now most PRs.

💬75🔄120❤️2544👀306230📊392

⚡ Powered by xgo.ing

Wow, this tweet went very viral! I wanted share a possibly slightly improved version of the tweet i...

Andrej Karpathy (@karpathy) — Sat, 04 Apr 2026 16:45:23 GMT

Wow, this tweet went very viral!

I wanted share a possibly slightly improved version of the tweet in an "idea file". The idea of the idea file is that in this era of LLM agents, there is less of a point/need of sharing the specific code/app, you just share the idea, then the other person's agent customizes & builds it for your specific needs.

So here's the idea in a gist format: gist.github.com/karpathy/442a6…

You can give this to your agent and it can build you your own LLM wiki and guide you on how to use it etc. It's intentionally kept a little bit abstract/vague because there are so many directions to take this in. And ofc, people can adjust the idea or contribute their own in the Discussion which is cool.

Andrej Karpathy@karpathy

LLM Knowledge Bases

Something I'm finding very useful recently: using LLMs to build personal knowledge bases for various topics of research interest. In this way, a large fraction of my recent token throughput is going less into manipulating code, and more into manipulating knowledge (stored as markdown and images). The latest LLMs are quite good at it. So:

Data ingest:
I index source documents (articles, papers, repos, datasets, images, etc.) into a raw/ directory, then I use an LLM to incrementally "compile" a wiki, which is just a collection of .md files in a directory structure. The wiki includes summaries of all the data in raw/, backlinks, and then it categorizes data into concepts, writes articles for them, and links them all. To convert web articles into .md files I like to use the Obsidian Web Clipper extension, and then I also use a hotkey to download all the related images to local so that my LLM can easily reference them.

IDE:
I use Obsidian as the IDE "frontend" where I can view the raw data, the the compiled wiki, and the derived visualizations. Important to note that the LLM writes and maintains all of the data of the wiki, I rarely touch it directly. I've played with a few Obsidian plugins to render and view data in other ways (e.g. Marp for slides).

Q&A:
Where things get interesting is that once your wiki is big enough (e.g. mine on some recent research is ~100 articles and ~400K words), you can ask your LLM agent all kinds of complex questions against the wiki, and it will go off, research the answers, etc. I thought I had to reach for fancy RAG, but the LLM has been pretty good about auto-maintaining index files and brief summaries of all the documents and it reads all the important related data fairly easily at this ~small scale.

Output:
Instead of getting answers in text/terminal, I like to have it render markdown files for me, or slide shows (Marp format), or matplotlib images, all of which I then view again in Obsidian. You can imagine many other visual output formats depending on the query. Often, I end up "filing" the outputs back into the wiki to enhance it for further queries. So my own explorations and queries always "add up" in the knowledge base.

Linting:
I've run some LLM "health checks" over the wiki to e.g. find inconsistent data, impute missing data (with web searchers), find interesting connections for new article candidates, etc., to incrementally clean up the wiki and enhance its overall data integrity. The LLMs are quite good at suggesting further questions to ask and look into.

Extra tools:
I find myself developing additional tools to process the data, e.g. I vibe coded a small and naive search engine over the wiki, which I both use directly (in a web ui), but more often I want to hand it off to an LLM via CLI as a tool for larger queries. 

Further explorations:
As the repo grows, the natural desire is to also think about synthetic data generation + finetuning to have your LLM "know" the data in its weights instead of just context windows.

TLDR: raw data from a given number of sources is collected, then compiled by an LLM into a .md wiki, then operated on by various CLIs by the LLM to do Q&A and to incrementally enhance the wiki, and all of it viewable in Obsidian. You rarely ever write or edit the wiki manually, it's the domain of the LLM. I think there is room here for an incredible new product instead of a hacky collection of scripts.

🔗 View Quoted Tweet

💬1119🔄2827❤️26712👀7117754📊7966

⚡ Powered by xgo.ing

Oh and in the natural extrapolation, you could imagine that every question to a frontier grade LLM s...

Andrej Karpathy (@karpathy) — Thu, 02 Apr 2026 20:54:29 GMT

Oh and in the natural extrapolation, you could imagine that every question to a frontier grade LLM spawns a team of LLMs to automate the whole thing: iteratively construct an entire ephemeral wiki, lint it, loop a few times, then write a full report. Way beyond a `.decode()`.

💬92🔄70❤️2017👀394522📊336

⚡ Powered by xgo.ing

LLM Knowledge Bases Something I'm finding very useful recently: using LLMs to build personal knowle...

Andrej Karpathy (@karpathy) — Thu, 02 Apr 2026 20:42:21 GMT

LLM Knowledge Bases

Something I'm finding very useful recently: using LLMs to build personal knowledge bases for various topics of research interest. In this way, a large fraction of my recent token throughput is going less into manipulating code, and more into manipulating knowledge (stored as markdown and images). The latest LLMs are quite good at it. So:

Data ingest:
I index source documents (articles, papers, repos, datasets, images, etc.) into a raw/ directory, then I use an LLM to incrementally "compile" a wiki, which is just a collection of .md files in a directory structure. The wiki includes summaries of all the data in raw/, backlinks, and then it categorizes data into concepts, writes articles for them, and links them all. To convert web articles into .md files I like to use the Obsidian Web Clipper extension, and then I also use a hotkey to download all the related images to local so that my LLM can easily reference them.

IDE:
I use Obsidian as the IDE "frontend" where I can view the raw data, the the compiled wiki, and the derived visualizations. Important to note that the LLM writes and maintains all of the data of the wiki, I rarely touch it directly. I've played with a few Obsidian plugins to render and view data in other ways (e.g. Marp for slides).

Q&A:
Where things get interesting is that once your wiki is big enough (e.g. mine on some recent research is ~100 articles and ~400K words), you can ask your LLM agent all kinds of complex questions against the wiki, and it will go off, research the answers, etc. I thought I had to reach for fancy RAG, but the LLM has been pretty good about auto-maintaining index files and brief summaries of all the documents and it reads all the important related data fairly easily at this ~small scale.

Output:
Instead of getting answers in text/terminal, I like to have it render markdown files for me, or slide shows (Marp format), or matplotlib images, all of which I then view again in Obsidian. You can imagine many other visual output formats depending on the query. Often, I end up "filing" the outputs back into the wiki to enhance it for further queries. So my own explorations and queries always "add up" in the knowledge base.

Linting:
I've run some LLM "health checks" over the wiki to e.g. find inconsistent data, impute missing data (with web searchers), find interesting connections for new article candidates, etc., to incrementally clean up the wiki and enhance its overall data integrity. The LLMs are quite good at suggesting further questions to ask and look into.

Extra tools:
I find myself developing additional tools to process the data, e.g. I vibe coded a small and naive search engine over the wiki, which I both use directly (in a web ui), but more often I want to hand it off to an LLM via CLI as a tool for larger queries. 

Further explorations:
As the repo grows, the natural desire is to also think about synthetic data generation + finetuning to have your LLM "know" the data in its weights instead of just context windows.

TLDR: raw data from a given number of sources is collected, then compiled by an LLM into a .md wiki, then operated on by various CLIs by the LLM to do Q&A and to incrementally enhance the wiki, and all of it viewable in Obsidian. You rarely ever write or edit the wiki manually, it's the domain of the LLM. I think there is room here for an incredible new product instead of a hacky collection of scripts.

💬2876🔄7209❤️59478👀21277135📊23242

⚡ Powered by xgo.ing

@gvanrossum LLM = CPU (data: tokens not bytes, dynamics: statistical and vague not deterministic and...

Andrej Karpathy (@karpathy) — Tue, 31 Mar 2026 18:59:26 GMT

@gvanrossum LLM = CPU (data: tokens not bytes, dynamics: statistical and vague not deterministic and precise)
Agent = operating system kernel

💬154🔄328❤️4837👀326113📊778

⚡ Powered by xgo.ing

New supply chain attack this time for npm axios, the most popular HTTP client library with 300M week...

Andrej Karpathy (@karpathy) — Tue, 31 Mar 2026 05:23:32 GMT

New supply chain attack this time for npm axios, the most popular HTTP client library with 300M weekly downloads.

Scanning my system I found a use imported from googleworkspace/cli from a few days ago when I was experimenting with gmail/gcal cli. The installed version (luckily) resolved to an unaffected 1.13.5, but the project dependency is not pinned, meaning that if I did this earlier today the code would have resolved to latest and I'd be pwned.

It's possible to personally defend against these to some extent with local settings e.g. release-age constraints, or containers or etc, but I think ultimately the defaults of package management projects (pip, npm etc) have to change so that a single infection (usually luckily fairly temporary in nature due to security scanning) does not spread through users at random and at scale via unpinned dependencies.

More comprehensive article:
stepsecurity.io/blog/axios-com…

Feross@feross

🚨 CRITICAL: Active supply chain attack on axios -- one of npm's most depended-on packages.

The latest axios@1.14.1 now pulls in plain-crypto-js@4.2.1, a package that did not exist before today. This is a live compromise.

This is textbook supply chain installer malware. axios has 100M+ weekly downloads. Every npm install pulling the latest version is potentially compromised right now.

Socket AI analysis confirms this is malware. plain-crypto-js is an obfuscated dropper/loader that:

• Deobfuscates embedded payloads and operational strings at runtime
• Dynamically loads fs, os, and execSync to evade static analysis
• Executes decoded shell commands
• Stages and copies payload files into OS temp and Windows ProgramData directories
• Deletes and renames artifacts post-execution to destroy forensic evidence

If you use axios, pin your version immediately and audit your lockfiles. Do not upgrade.

🔗 View Quoted Tweet

💬567🔄1119❤️10478👀1577178📊1618

⚡ Powered by xgo.ing

- Drafted a blog post - Used an LLM to meticulously improve the argument over 4 hours. - Wow, feelin...

Andrej Karpathy (@karpathy) — Sat, 28 Mar 2026 15:56:10 GMT

- Drafted a blog post
- Used an LLM to meticulously improve the argument over 4 hours.
- Wow, feeling great, it’s so convincing!
- Fun idea let’s ask it to argue the opposite. 
- LLM demolishes the entire argument and convinces me that the opposite is in fact true.
- lol

The LLMs may elicit an opinion when asked but are extremely competent in arguing almost any direction. This is actually super useful as a tool for forming your own opinions, just make sure to ask different directions and be careful with the sycophancy.

💬1747🔄2417❤️31148👀3487733📊5422

⚡ Powered by xgo.ing

When I built menugen ~1 year ago, I observed that the hardest part by far was not the code itself, i...

Andrej Karpathy (@karpathy) — Thu, 26 Mar 2026 16:10:52 GMT

When I built menugen ~1 year ago, I observed that the hardest part by far was not the code itself, it was the plethora of services you have to assemble like IKEA furniture to make it real, the DevOps: services, payments, auth, database, security, domain names, etc...

I am really looking forward to a day where I could simply tell my agent: "build menugen" (referencing the post) and it would just work. The whole thing up to the deployed web page. The agent would have to browse a number of services, read the docs, get all the api keys, make everything work, debug it in dev, and deploy to prod. This is the actually hard part, not the code itself. Or rather, the better way to think about it is that the entire DevOps lifecycle has to become code, in addition to the necessary sensors/actuators of the CLIs/APIs with agent-native ergonomics. And there should be no need to visit web pages, click buttons, or anything like that for the human. 

It's easy to state, it's now just barely technically possible and expected to work maybe, but it definitely requires from-scratch re-design, work and thought. Very exciting direction!

Patrick Collison@patrickc

When @karpathy built MenuGen (karpathy.bearblog.dev/vibe-coding-me…), he said:

"Vibe coding menugen was exhilarating and fun escapade as a local demo, but a bit of a painful slog as a deployed, real app. Building a modern app is a bit like assembling IKEA future. There are all these services, docs, API keys, configurations, dev/prod deployments, team and security features, rate limits, pricing tiers."

We've all run into this issue when building with agents: you have to scurry off to establish accounts, clicking things in the browser as though it's the antediluvian days of 2023, in order to unblock its superintelligent progress.

So we decided to build Stripe Projects to help agents instantly provision services from the CLI.

For example, simply run:

$ stripe projects add posthog/analytics

And it'll create a PostHog account, get an API key, and (as needed) set up billing.

Projects is launching today as a developer preview. You can register for access (we'll make it available to everyone soon) at projects.dev. We're also rolling out support for many new providers over the coming weeks. (Get in touch if you'd like to make your service available.)

projects.dev

🔗 View Quoted Tweet

💬627🔄537❤️6384👀2457746📊1296

⚡ Powered by xgo.ing

(I cycle through all LLMs over time and all of them seem to do this so it's not any particular imple...

Andrej Karpathy (@karpathy) — Wed, 25 Mar 2026 16:22:08 GMT

(I cycle through all LLMs over time and all of them seem to do this so it's not any particular implementation but something deeper, e.g. maybe during training, a lot of the information in the context window is relevant to the task, so the LLMs develop a bias to use what is given, then at test time overfit to anything that happens to RAG its way there via a memory feature (?))

💬152🔄43❤️1697👀298539📊264

⚡ Powered by xgo.ing

One common issue with personalization in all LLMs is how distracting memory seems to be for the mode...

Andrej Karpathy (@karpathy) — Wed, 25 Mar 2026 16:05:14 GMT

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.

💬1752🔄1076❤️21040👀2746036📊3524

⚡ Powered by xgo.ing

Some links 2,112 total packages depend on litellm (https://t.co/T8xWdrBp9g), 1,403 of them directly...

Andrej Karpathy (@karpathy) — Tue, 24 Mar 2026 17:02:42 GMT

Some links

2,112 total packages depend on litellm (deps.dev/pypi/litellm), 1,403 of them directly. Among these are e.g. DSPy, Open Interpreter, PraisonAI, MLflow, langchain-litellm.

Primary Sources

  1. Original disclosure (GitHub issue): github.com/BerriAI/litell… — the detailed technical writeup of
   the malicious payload, what it steals, how it works
  2. BerriAI's official tracking issue: github.com/BerriAI/litell… — the team's response and status
  updates
  3. FutureSearch blog (the people who found it): futuresearch.ai/blog/litellm-p… — how a
  fork bomb bug in the malware crashed their machine and led to discovery
  4. ramimac's full TeamPCP timeline: ramimac.me/teampcp/ — the broader campaign: Trivy → Checkmarx → litellm, with
  exact timestamps and IOCs
  5. PyPA advisory: github.com/pypa/advisory-… — the official
  PYSEC-2026-2

  Analysis & Discussion

  6. Hacker News thread (main): news.ycombinator.com/item?id=475017… — includes direct responses from Krrish
  (litellm maintainer), best real-time discussion
  7. Hacker News thread (early): news.ycombinator.com/item?id=475014… — the first HN post
  8. GitGuardian writeup:
  blog.gitguardian.com/trivys-march-s… — good analysis of
  how leaked CI/CD secrets enabled the whole chain
  9. Wiz blog on the broader campaign: wiz.io/blog/teampcp-a… — TeamPCP's attack on
  Checkmarx/KICS, same actor

  Downstream Impact

  10. DSPy issue: github.com/stanfordnlp/ds…
  11. MLflow emergency pin PR: github.com/mlflow/mlflow/…
  12. DSPy emergency pin PR: github.com/stanfordnlp/ds…

  Quick Summary for Your Post

  - 46-minute window of exposure on PyPI (10:39–11:25 UTC, Mar 24)
  - ~1,400 packages directly depend on litellm, all with open-ended version ranges
  - Caught because the malware had a bug (fork bomb) that crashed the discoverer's machine
  - Root cause: Trivy (a vulnerability scanner) was itself compromised, which leaked litellm's PyPI publish token
  - Attacker (TeamPCP) spammed the GitHub issue with hundreds of bot comments to bury the discussion

💬4🔄1❤️15👀3578📊5

⚡ Powered by xgo.ing

Software horror: litellm PyPI supply chain attack. Simple `pip install litellm` was enough to exfi...

Andrej Karpathy (@karpathy) — Tue, 24 Mar 2026 16:56:24 GMT

Software horror: litellm PyPI supply chain attack. 

Simple `pip install litellm` was enough to exfiltrate SSH keys, AWS/GCP/Azure creds, Kubernetes configs, git credentials, env vars (all your API keys), shell history, crypto wallets, SSL private keys, CI/CD secrets, database passwords.

LiteLLM itself has 97 million downloads per month which is already terrible, but much worse, the contagion spreads to any project that depends on litellm. For example, if you did `pip install dspy` (which depended on litellm>=1.64.0), you'd also be pwnd. Same for any other large project that depended on litellm.

Afaict the poisoned version was up for only less than ~1 hour. The attack had a bug which led to its discovery - Callum McMahon was using an MCP plugin inside Cursor that pulled in litellm as a transitive dependency. When litellm 1.82.8 installed, their machine ran out of RAM and crashed. So if the attacker didn't vibe code this attack it could have been undetected for many days or weeks.

Supply chain attacks like this are basically the scariest thing imaginable in modern software. Every time you install any depedency you could be pulling in a poisoned package anywhere deep inside its entire depedency tree. This is especially risky with large projects that might have lots and lots of dependencies. The credentials that do get stolen in each attack can then be used to take over more accounts and compromise more packages.

Classical software engineering would have you believe that dependencies are good (we're building pyramids from bricks), but imo this has to be re-evaluated, and it's why I've been so growingly averse to them, preferring to use LLMs to "yoink" functionality when it's simple enough and possible.

Daniel Hnyk@hnykda

LiteLLM HAS BEEN COMPROMISED, DO NOT UPDATE. We just discovered that LiteLLM pypi release 1.82.8. It has been compromised, it contains litellm_init.pth with base64 encoded instructions to send all the credentials it can find to remote server + self-replicate. link below

🔗 View Quoted Tweet

💬1355🔄5322❤️27709👀66569856📊5020

⚡ Powered by xgo.ing

I'm not very happy with the code quality and I think agents bloat abstractions, have poor code aesth...

Andrej Karpathy (@karpathy) — Sat, 21 Mar 2026 01:55:46 GMT

I'm not very happy with the code quality and I think agents bloat abstractions, have poor code aesthetics, are very prone to copy pasting code blocks and it's a mess, but at this point I stopped fighting it too hard and just moved on. The agents do not listen to my instructions in the AGENTS.md files. E.g. just as one example, no matter how many times I say something like:

"Every line of code should do exactly one thing and use intermediate variables as a form of documentation"

They will still "multitask" and create complex constructs where one line of code calls 2 functions and then indexes an array with the result. I think in principle I could use hooks or slash commands to clean this up but at some point just a shrug is easier.

Yes I think LLM as a judge for soft rewards is in principle and long term slightly problematic (due to goodharting concerns), but in practice and for now I don't think we've picked the low hanging fruit yet here.

💬253🔄330❤️4274👀819557📊877

⚡ Powered by xgo.ing

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

Andrej Karpathy (@karpathy) — Sat, 21 Mar 2026 00:55:37 GMT

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

sarah guo@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

55 - What Capability Limits Remain?
15 - What Mastery of Coding Agents Looks Like
16 - Second Order Effects of Coding Agents
51 - Why AutoResearch
45 - Relevant Skills in the AI Era
25 - Model Speciation
30 - Collaboration Surfaces for Humans and AI
28 - Analysis of Jobs Market Data
25 - Open vs. Closed Source Models
51 - Autonomous Robotics and Atoms
00:59 - MicroGPT and Agentic Education
05:40 - End Thoughts

Your browser does not support the video tag.

🔗 View on Twitter

🔗 View Quoted Tweet

💬319🔄401❤️5470👀1134013📊911

⚡ Powered by xgo.ing

Andy Weir showing some of the spreadsheets underlying the calculations in the book https://t.co/3Cyp...

Andrej Karpathy (@karpathy) — Fri, 20 Mar 2026 06:01:55 GMT

Andy Weir showing some of the spreadsheets underlying the calculations in the book
youtube.com/watch?v=lYHCTE…
i mean, it's not quality scifi if it doesn't come with a supplementary whitepaper

💬49🔄63❤️1207👀216774📊193

⚡ Powered by xgo.ing

Had to go see Project Hail Mary right away (it's based on the book of Andy Weir, of also The Martian...

Andrej Karpathy (@karpathy) — Fri, 20 Mar 2026 05:32:41 GMT

Had to go see Project Hail Mary right away (it's based on the book of Andy Weir, of also The Martian fame). Both very pleased and relieved to say that 1) the movie sticks very close to the book in both content and tone and 2) is really well executed.

The book is one of my favorites when it comes to alien portrayals because a lot of thought was clearly given to the scientific details of an alternate biochemistry, evolutionary history, sensorium, psychology, language, tech tree, etc. It's different enough that it is highly creative and plausible, but also similar enough that you get a compelling story and one of the best bromances in fiction. Not to mention the other (single-cellular) aliens. I can count fictional portrayals of aliens of this depth on one hand. A lot of these aspects are briefly featured - if you read the book you'll spot them but if you haven't, the movie can't spend the time to do them justice.

I'll say that the movie inches a little too much into the superhero movie tropes with the pacing, the quips, the Bathos and such for my taste, and we get a little bit less the grand of Interstellar and a little bit less of the science of The Martian, but I think it's ok considering the tone of the original content. And it does really well where it counts - on Rocky and the bromance. Thank you to the film crew for the gem!

💬361🔄330❤️9098👀681268📊1213

⚡ Powered by xgo.ing

Ugh X breaks time links, it’s at 26:17

Andrej Karpathy (@karpathy) — Wed, 18 Mar 2026 18:01:37 GMT

Ugh X breaks time links, it’s at 26:17

💬22🔄5❤️357👀120336📊46

⚡ Powered by xgo.ing

(link to blast from the past) https://t.co/gAP4YPV5uR

Andrej Karpathy (@karpathy) — Wed, 18 Mar 2026 17:47:57 GMT

(link to blast from the past)
youtu.be/xQhb3C2hQoE?si…

💬11🔄34❤️682👀235262📊87

⚡ Powered by xgo.ing

Thank you Jensen and NVIDIA! She’s a real beauty! I was told I’d be getting a secret gift, with a hi...

Andrej Karpathy (@karpathy) — Wed, 18 Mar 2026 17:31:45 GMT

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!!

💬528🔄827❤️19097👀1104691📊2181

⚡ Powered by xgo.ing

@Yulun_Du @ilyasut SGD is a ResNet too (the blocks of it are fwd+bwd), the residual stream is the we...

Andrej Karpathy (@karpathy) — Mon, 16 Mar 2026 04:32:06 GMT

@Yulun_Du@ilyasut SGD is a ResNet too (the blocks of it are fwd+bwd), the residual stream is the weights so... 🤔 We're not taking the Attention is All You Need part literally enough? :D

💬28🔄39❤️589👀103398📊113

⚡ Powered by xgo.ing

My autoresearch labs got wiped out in the oauth outage. Have to think through failovers. Intelligenc...

Andrej Karpathy (@karpathy) — Wed, 11 Mar 2026 18:01:01 GMT

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.

💬553🔄301❤️7047👀612111📊1137

⚡ Powered by xgo.ing

Human orgs are not legible, the CEO can’t see/feel/zoom in on any activity in their company, with re...

Andrej Karpathy (@karpathy) — Wed, 11 Mar 2026 16:49:55 GMT

Human orgs are not legible, the CEO can’t see/feel/zoom in on any activity in their company, with real time stats etc. I have no doubt that it will be possible to control orgs on mobile, with voice etc., but with this level of legibility will that be optimal? Not in principle and asymptotically but in practice and for at least the next round of play.

💬88🔄49❤️1289👀239520📊218

⚡ Powered by xgo.ing

All of these patterns as an example are just matters of “org code”. The IDE helps you build, run, ma...

Andrej Karpathy (@karpathy) — Wed, 11 Mar 2026 16:33:55 GMT

All of these patterns as an example are just matters of “org code”. The IDE helps you build, run, manage them. You can’t fork classical orgs (eg Microsoft) but you’ll be able to fork agentic orgs.

💬172🔄276❤️3747👀491005📊707

⚡ Powered by xgo.ing

Expectation: the age of the IDE is over Reality: we’re going to need a bigger IDE (imo). It just lo...

Andrej Karpathy (@karpathy) — Wed, 11 Mar 2026 16:22:27 GMT

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.

💬832🔄834❤️10552👀2475084📊2251

⚡ Powered by xgo.ing

@nummanali tmux grids are awesome, but i feel a need to have a proper "agent command center" IDE for...

Andrej Karpathy (@karpathy) — Wed, 11 Mar 2026 06:22:23 GMT

@nummanali 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.

💬303🔄117❤️3077👀1398107📊652

⚡ Powered by xgo.ing

@WorkshopLabs @AddieF38654 Great read! Off in the jungle with no trails. Open weights != Open source...

Andrej Karpathy (@karpathy) — Tue, 10 Mar 2026 05:49:34 GMT

@WorkshopLabs@AddieF38654 Great read! Off in the jungle with no trails. Open weights != Open source not only because of the data but all the related infra for everything not inference.

💬18🔄21❤️448👀29402📊62

⚡ Powered by xgo.ing

oh yeah i should have linked autoresearch probably https://t.co/YCvOwwjOzF (you don't "use it" direc...

Andrej Karpathy (@karpathy) — Mon, 09 Mar 2026 22:38:05 GMT

oh yeah i should have linked autoresearch probably
github.com/karpathy/autor…
(you don't "use it" directly, it's just a recipe/idea - give it to your agent and apply to what you care about.)

and the tweet about it that went mini-viral over the weekend with more context
x.com/karpathy/statu…

💬93🔄208❤️2453👀311952📊580

⚡ Powered by xgo.ing

Three days ago I left autoresearch tuning nanochat for ~2 days on depth=12 model. It found ~20 chang...

Andrej Karpathy (@karpathy) — Mon, 09 Mar 2026 22:28:51 GMT

Three days ago I left autoresearch tuning nanochat for ~2 days on depth=12 model. It found ~20 changes that improved the validation loss. I tested these changes yesterday and all of them were additive and transferred to larger (depth=24) models. Stacking up all of these changes, today I measured that the leaderboard's "Time to GPT-2" drops from 2.02 hours to 1.80 hours (~11% improvement), this will be the new leaderboard entry. So yes, these are real improvements and they make an actual difference. I am mildly surprised that my very first naive attempt already worked this well on top of what I thought was already a fairly manually well-tuned project.

This is a first for me because I am very used to doing the iterative optimization of neural network training manually. You come up with ideas, you implement them, you check if they work (better validation loss), you come up with new ideas based on that, you read some papers for inspiration, etc etc. This is the bread and butter of what I do daily for 2 decades. Seeing the agent do this entire workflow end-to-end and all by itself as it worked through approx. 700 changes autonomously is wild. It really looked at the sequence of results of experiments and used that to plan the next ones. It's not novel, ground-breaking "research" (yet), but all the adjustments are "real", I didn't find them manually previously, and they stack up and actually improved nanochat. Among the bigger things e.g.:

- It noticed an oversight that my parameterless QKnorm didn't have a scaler multiplier attached, so my attention was too diffuse. The agent found multipliers to sharpen it, pointing to future work.
- It found that the Value Embeddings really like regularization and I wasn't applying any (oops).
- It found that my banded attention was too conservative (i forgot to tune it).
- It found that AdamW betas were all messed up.
- It tuned the weight decay schedule.
- It tuned the network initialization.

This is on top of all the tuning I've already done over a good amount of time. The exact commit is here, from this "round 1" of autoresearch. I am going to kick off "round 2", and in parallel I am looking at how multiple agents can collaborate to unlock parallelism.
github.com/karpathy/nanoc…

All LLM frontier labs will do this. It's the final boss battle. It's a lot more complex at scale of course - you don't just have a single train. py file to tune. But doing it is "just engineering" and it's going to work. You spin up a swarm of agents, you have them collaborate to tune smaller models, you promote the most promising ideas to increasingly larger scales, and humans (optionally) contribute on the edges.

And more generally, *any* metric you care about that is reasonably efficient to evaluate (or that has more efficient proxy metrics such as training a smaller network) can be autoresearched by an agent swarm. It's worth thinking about whether your problem falls into this bucket too.

💬961🔄2138❤️19522👀3651225📊4251

⚡ Powered by xgo.ing

@tobi Who knew early singularity could be this fun? :) I just confirmed that the improvements autor...

Andrej Karpathy (@karpathy) — Sun, 08 Mar 2026 22:46:10 GMT

@tobi Who knew early singularity could be this fun? :)

I just confirmed that the improvements autoresearch found over the last 2 days of (~650) experiments on depth 12 model transfer well to depth 24 so nanochat is about to get a new leaderboard entry for “time to GPT-2” too. Works 🤷‍♂️

💬110🔄246❤️4701👀768019📊476

⚡ Powered by xgo.ing

The next step for autoresearch is that it has to be asynchronously massively collaborative for agent...

Andrej Karpathy (@karpathy) — Sun, 08 Mar 2026 18:00:40 GMT

The next step for autoresearch is that it has to be asynchronously massively collaborative for agents (think: SETI@home style). The goal is not to emulate a single PhD student, it's to emulate a research community of them.

Current code synchronously grows a single thread of commits in a particular research direction. But the original repo is more of a seed, from which could sprout commits contributed by agents on all kinds of different research directions or for different compute platforms. Git(Hub) is *almost* but not really suited for this. It has a softly built in assumption of one "master" branch, which temporarily forks off into PRs just to merge back a bit later.

I tried to prototype something super lightweight that could have a flavor of this, e.g. just a Discussion, written by my agent as a summary of its overnight run:
github.com/karpathy/autor…
Alternatively, a PR has the benefit of exact commits:
github.com/karpathy/autor…
but you'd never want to actually merge it... You'd just want to "adopt" and accumulate branches of commits. But even in this lightweight way, you could ask your agent to first read the Discussions/PRs using GitHub CLI for inspiration, and after its research is done, contribute a little "paper" of findings back.

I'm not actually exactly sure what this should look like, but it's a big idea that is more general than just the autoresearch repo specifically. Agents can in principle easily juggle and collaborate on thousands of commits across arbitrary branch structures. Existing abstractions will accumulate stress as intelligence, attention and tenacity cease to be bottlenecks.

💬529🔄715❤️7576👀1118511📊1753

⚡ Powered by xgo.ing

(I still have the bigger cousin running on prod nanochat, working a bigger model and on 8XH100, whic...

Andrej Karpathy (@karpathy) — Sat, 07 Mar 2026 20:03:18 GMT

(I still have the bigger cousin running on prod nanochat, working a bigger model and on 8XH100, which looks like this now. I'll just leave this running for a while...)

💬71🔄62❤️2106👀420600📊289

⚡ Powered by xgo.ing

I packaged up the "autoresearch" project into a new self-contained minimal repo if people would like...

Andrej Karpathy (@karpathy) — Sat, 07 Mar 2026 19:53:15 GMT

I packaged up the "autoresearch" project into a new self-contained minimal repo if people would like to play over the weekend. It's basically nanochat LLM training core stripped down to a single-GPU, one file version of ~630 lines of code, then:

- the human iterates on the prompt (.md)
- the AI agent iterates on the training code (.py)

The goal is to engineer your agents to make the fastest research progress indefinitely and without any of your own involvement. In the image, every dot is a complete LLM training run that lasts exactly 5 minutes. The agent works in an autonomous loop on a git feature branch and accumulates git commits to the training script as it finds better settings (of lower validation loss by the end) of the neural network architecture, the optimizer, all the hyperparameters, etc. You can imagine comparing the research progress of different prompts, different agents, etc.

github.com/karpathy/autor…
Part code, part sci-fi, and a pinch of psychosis :)

💬1056🔄3631❤️28282👀11066127📊9274

⚡ Powered by xgo.ing

ah yes, this is what post-agi feels like :) i didn't touch anything. brb sauna

Andrej Karpathy (@karpathy) — Fri, 06 Mar 2026 16:03:19 GMT

ah yes, this is what post-agi feels like :) i didn't touch anything. brb sauna

💬73🔄61❤️1004👀158106📊177

⚡ Powered by xgo.ing

sorry just to clarify - the real benchmark of interest is: "what is the research org agent code tha...

Andrej Karpathy (@karpathy) — Thu, 05 Mar 2026 23:35:31 GMT

sorry just to clarify - the real benchmark of interest is:

"what is the research org agent code that produces improvements on nanochat the fastest?"

this is the new meta.

💬63🔄47❤️1114👀141023📊162