Search: “karpathy”

I just built my own wiki generator plugin for my agents. My agents can now generate wikis for anything I ask. One of my favorite wikis is called PaperWiki. This is a great example of what @karpathy de

I know it's self serving to say, but man I would've killed for a resource like Tinker and the tutorials, the cookbook, etc back when I was in undergrad. Following @karpathy blogs and training RNNs on

It has been half a month since I started a new role at a big company. Nobody knows anything here. The specs, code, tests, PRDs, tickets, resolution of those tickets, reports, etc., everything is made

Had so much fun giving this talk at @sequoia about @harvey’s moneyball approach to building a research lab. The biggest mistake I made in the early days of Harvey was trying to play the Yankees baseba

we burned through 5 billion tokens in 48h. turns out giving everyone unlimited access to the most expensive model on the planet is not a great business strategy 🙈 So now we have 2 free opus sessions/d

I tested @huggingface ml-intern, given the prompt 'Fine-tune a Segment Anything Model (SAM) on a useful medical dataset. Train the model, and provide a comprehensive tutorial in a Jupyter Notebook fil

I’ve been using ml-intern for a while, and it genuinely changed my workflow. It's super good at: - Model/Dataset discovery. - Post-Training setup iteration. - Data processing workflows. Huge shoutout

YT Podcast → LLM Artifact This is now my favorite way to consume podcasts. Knowledge artifacts generated by agents. The agent (Opus 4.7) spots important insights, does deep analysis, and generates tho

What you need to know about Opus 4.7 * Takes instructions literally * Better vision means improved computer use and producing slides and other visual artifacts * Optimized for large-scale real-world a

Auto-generated index of all tools mentioned across the wiki.

I think it's non-obvious to many people that the OpenAI voice mode runs on a much older, much weaker model - it feels like the AI that you can talk to should be the smartest AI but it really isn't. If

Introducing MCP tools for @dair_ai. Connect the MCP to your Codex/Claude/Grok Bot to discover and explore the top AI papers. We carefully curate the papers, so you can expect mostly bangers. The index

50K likes on this!? Most of what Karpthy has shared is things we have been doing for over a year. No surprises, as many replies are highlighting. But I still think this raises an interesting discussio

Automated lint: 19 errors, 64915 warnings, 3 info

arXiv:2609.30541v1 Announce Type: new Abstract: Optimizing embedding systems for production recommendation pipelines demands systematic exploration that consumes disproportionate engineering effort at

Automated lint: 17 errors, 59669 warnings, 3 info

Automated lint: 14 errors, 54840 warnings, 3 info

GitHub: https://github.com/pfekin/LARA I've been working on LARA (Lightweight Additive Residual Adaptation), a research project on making post-training modular for frozen language models. I've also de

Automated lint: 12 errors, 54839 warnings, 3 info

Automated lint: 12 errors, 53990 warnings, 3 info

Our research team has been exploring an alternative approach to achieving interactivity and better responsiveness with LLM systems. One of the team members wrote up a post about it: https://research.y

I think its easy to say 'Simulation is a new scaling law' and treat it as marketing hyperbole, but midway along this interview you can hear me go from somewhat shitposting to very very serious. I am 2

Simile AI’s CEO Joon Sung Park describes how the company moved from the 2024 “Summer of Simulative AI” and its landmark *Generative Agents* paper to building digital twins that predict individual and

Yes, it sucks to waste time waiting on 16K+ reasoning tokens alone. But here's the thing, this is only a 27B model trying to perform on par with 1T+ parameter models. Something has to be sacrificed, a

arXiv:2608.07542v1 Announce Type: new Abstract: Autonomous research loops driven by large language models can run machine-learning experiments at scale but tend to drift toward local refinements of wh

arXiv:2607.24759v1 Announce Type: new Abstract: Research projects, educational efforts, and adjacent knowledge work accumulate findings, decisions, and reasoning that future collaborators rarely recov

Hey folks — I built ContextMemory, an open-source agentic context gateway for apps that already talk to LLMs. The idea is simple: keep your existing POST /api/chat client (Ollama wire format), point i

arXiv:2607.19992v1 Announce Type: cross Abstract: tiny_schiller closes the small-language-model prototyping, fine-tuning, education, and research gap for German literary text, providing a single-file,

Automated lint: 20 errors, 8743 warnings, 3 info

Automated lint: 26 errors, 6728 warnings, 3 info

This AI recursive self improvement (RSI) paper shows no sign of fast takeoff. The AI model advances at about [Intelligence]^0.075, or the the 13th root of input intelligence [1,2]. That means the inte

Everyone keeps asking me how to build a second brain or an LLM wiki. Here is the easiest setup I have found. I took my Wiki Builder skill, installed it into HyperAgent (@hyperagentapp) as a reusable s

we built the @hyperspell filesystem around this principle every source in your company feeds into a context graph where we resolve conflicts and assign permissions there’s a filesystem on top of the g

We call ours Operational Language Wiki, essentially a pattern for building memory to fill in the delta between the “dialect” of a team vs the “world language” that the LLM is trained on. Use it to cap

arXiv:2606.29717v1 Announce Type: cross Abstract: Predicting a material's properties from its structure is a central, fast-advancing problem in computational materials science. A decade of work has pr

Row-Bot's approach to memory is hybrid. We have taken the best of both worlds. A knowledge graph for the agent + bi-directionaly synced Wiki for human readability/audit. With in-app graph visualizatio

if only vetted institutions (big labs, governments, large enterprises) get unrestricted frontier capability, especially for AI research itself, those players compound their lead while everyone else wo

It's finally out!!! @METR_Evals found that more than half of SWEBench results is unmergeable slop. FrontierCode represents over 1000+ hours of maintainer validated software engineering work most front

arXiv:2603.23420v2 Announce Type: replace Abstract: If autoresearch is itself a form of research, then autoresearch can be applied to research itself. We present Bilevel Autoresearch, a bilevel framew

Increasingly, HTML Artifacts are becoming a core part of how I work with AI agents. Long-horizon agent sessions need a better way to surface insights about what work it has done. This may not be obvio

Self-improving AI is a big deal! As a first step, I've been exploring how much of the post-training can be automated. Here is a first post on how I am using @FireworksAI_HQ Agent to automate LLM fine-

Artificial intelligence developer Decart.ai Inc. today announced that it has raised 300 million in funding at a nearly 4 billion valuation. Radical Ventures led the round with participation from Nvidi

arXiv:2605.17398v1 Announce Type: new Abstract: This paper presents MiniGPT, a compact from-scratch implementation of GPT-style autoregressive language modeling in PyTorch. The aim is to rebuild the c

arXiv Papers → LLM Artifacts This is how I keep up with AI research now. It's like having access to the most personalized arXiv feed. Automations run everyday to curate papers based a set of rules and

Standard Intelligence Inc., a six-person artificial intelligence startup, today announced that it has raised 75 million in funding. Sequoia and Spark Capital led the round. They were joined by multipl

Instead of predicting text tokens, @si_pbc learns to use a computer from raw screen data, predicting the next mouse movement, click, and keystroke from the pixels in front of it. This is the @Tesla FS