Knowledge catalogue
A few notes on how to get started with building LLM Knowledge Bases. @karpathy popularized it but most people don't know where to start. Everyone should be creating LLM Wikis. Live session tomorrow. S
LLM Artifacts Connected to @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 mea
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
This post by Swyx appears to be a casual, celebratory message referencing Andrej Karpathy (a prominent AI researcher) in the style of a holiday greeting, likely shared on a date significant to the AI
Breaking: Andrej Karpathy just filed his Q1 2026 13F. Here's everything you need to know about his recent 13F Top 10 positions: 1. VanEck Semiconductor ETF - SMH - [Put] — 2.04B 2. Nvidia - NVDA - [Pu
.@karpathy at @AnthropicAI = more open-source from them? They're already contributing datasets: https://huggingface.co/Anthropic but would be super cool to see more (massive potential for impact obvio
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 pa
@Konstantine @gradypb @Alfred_Lin @sequoia @demishassabis @karpathy @gdb @bcherny @djseo @zoink @matiii @DrJimFan @oegerikus @amspector100 @bfspector @PhilipJohnston @NaveenGRao @annadgoldie @Azaliami
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 se
A couple of months ago, I announced that I was partway through implementing a simple, readable AlphaFold2 in pure PyTorch, inspired by @karpathy's minGPT. Today, I'm happy to share minAlphaFold2 - the
AI ASCENT IV 4/20/2026 Our best event yet. This year's theme: AI AT THE FRONTIER. Robots. Data centers in space. New chips. BCI. Hosted by @Konstantine @gradypb @Alfred_Lin and all of us at @sequoia 💚
'You cannot govern a technology you have only been briefed on.' Singapore Minister for Foreign Affairs, Dr. @VivianBala, echoing @karpathy and @yacineMTB on why he runs NanoClaw: 'you can outsource me
Introducing nanowhale 🐳! A tiny DeepSeek model fully pretrained by an agent. Inspired by @karpathy's nanochat, we gave ml-intern the task of training a tiny MoE with all the architectural advancements
@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 rais
Karpathy's autoresearch repo started an impressive trend. Agents can now train AI models to build SoTA agentic systems. And to think this is just scratching the surface. Ultimately, it boils down to g
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
Sonya Huang spoke at Sequoia's AI Ascend event about Starcloud alongside notable AI figures including Andrej Karpathy, Greg Brockman, Demis Hassabis, and others, highlighting significant perspectives
LLM Knowledge Base → Slides When @karpathy shared his LLM Knowledge Base setup, many were wondering how to generate more visual forms of the wiki. There are many options, but I think @GammaApp is one
Gary Marcus argues that establishing a permanent, locked-in power structure is fundamentally unsafe and harmful to humanity's long-term prospects. The statement appears to be part of a discussion with
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 *
This post discusses using WorkPods agent memory systems organized as wikis, likely exploring how LLM agents can maintain and access persistent knowledge repositories in wiki format for improved contex
Andrej Karpathy shared a comprehensive 45-minute video demonstrating over 60 advanced 3D prompting techniques and examples using Fable, along with the actual prompts used. The content covers challengi
This WikiSkill paper from Google is a must-read. At a high level, it shows the effectiveness of persistent agents, knowledge bases, and skills. @karpathy popularized LLM Wikis. But this paper provides
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). Th
Dusting off this tweet from April because this gap in shared understanding of LLM capability is *widening*. It's now less 'two groups of people speaking past each other' and more a sharp funnel. - Nap
Cool eval. Simply ask an LLM “Land or Water?” and give it a latitude and longitude coordinate as text. Ask 16,200 times, plot as image. The models know. From compressing the internet. results for all
We'll be spending a lot more time trying to understand the outputs of language models. A few thoughts, tips & tricks: Writing. Something I've had success with: Ask your LLM to explain something in ASD
I love this and really hope we can come together as an industry and make it happen. We Must Pace the Frontier: I’ve written a new essay on why the AI industry should slow down, with a three-part plan
We're publishing our most detailed threat intelligence report to date. It covers how people tried to misuse Claude—for cyberattacks, influence operations, surveillance, biology, and building weapons—a
More on the pelican on the bicycle test from @simonw: https://simonwillison.net/2025/Jun/6/six-months-in-llms/ I uploaded the source here so it's playable in the browser, forkable etc. https://karpath
We're starting to leave the territory where you'd test an LLM by e.g. 'create an svg of pelican on a bicycle'. As one idea to generalize it, I was interested what Opus 5 would do if I gave it the firs
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
good description of how someone has done wiki memory in the wild @hwchase17 @cognition @FactoryAI @karpathy We implemented wiki idea by hosting the 'files' as doc db objects, added an API for db query
this may be ai generated, but is true - the hardest part of wikis (and memory in general) is the process that condenses raw data into learnings/memory @hwchase17 @cognition @FactoryAI @karpathy wiki m
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
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 '
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
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 prese
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 un
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 l
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
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
someone just told me about this take* on CUA this is one of those gell mann moments for me lol. i've been watching computer use since World of Bits (Shi, fan, karpathy, hernandez & liang 2017). we wer
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
183/365 of GPU Programming This 4.5 hour lesson on CUDA + ThunderKittens by @bfspector (TK co-author, Stanford PhD student) is one of the best educational videos on kernels out there (think @karpathy
1/ OpenWiki First, we wrote about why 'wikis' are interesting as a form of memory: https://www.langchain.com/blog/wiki-memory Cites examples from @FactoryAI, @cognition, @karpathy Then @BraceSproul op
Have an idea for an experiment? Hermes can now write conference-grade research papers alongside you. Media introducing Autoreason, a reasoning method inspired by @karpathy's AutoResearch which extends
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
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
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
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
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
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