The graph in that Google paper is what got me. Qwen-9B with evolved skills posts 47.4% across five benchmarks. Qwen-27B running bare posts 39.4%. Both Qwen, neither one fine-tuned. Smaller model wins. What skill…
Andrej Karpathy
Andrej Karpathy é um cientista da computação eslovaco-canadense, pesquisador de IA, educador e empreendedor especializado em aprendizado profundo, visão computacional e redes neurais.
114 publicações 39 vídeos 46 seguidores
Andrej Karpathy put 10 years of experience at OpenAI and Tesla into one free lecture. people pay $15k for bootcamps that cover half of what's in it. you probably don't have 2 hours right now. don't let it disappear…
OpenAI users just realized they ignored Karpathy's free lecture for a whole year lol
Karpathy free lecture
Andrej Karpathy earned his PhD at Stanford working with Fei-Fei Li. He co-created CS231n, a course that taught an entire generation deep learning. As a founding member of OpenAI, he later departed to lead autopilot AI at…
Andrej Karpathy career timeline
’s knowledge graph concept has been realized as Graphify, a fully open-source utility that integrates directly with Claude Code and Cursor. The workflow is simple: point the tool at any directory and it automatically…
Stop obsessing over GPT vs Claude vs Kimi. The real battle isn't about bigger context windows or slightly better prompts. Andrej Karpathy just exposed why your agents keep failing, and it has nothing to do with the model…
Andrej Karpathy Stanford lecture
Skip the Netflix episode and dive into Karpathy’s one-hour Stanford lecture on AI engineering. It is a solid weekend bookmark. He breaks down the reality: an LLM only delivers 10%, which is merely the starting point…
My whole reading workflow is basically Claude + one Obsidian folder. Articles, PDFs, transcripts, all of it lands in that single folder. Claude pulls out atomic notes, hooks them into everything else, and then I just…
Karpathy second-brain method Obsidian graph
Andrej Karpathy’s system relies on Obsidian to hold the vault while Claude reads and links every source you add. The setup is minimal: three folders and one file. Month one feels stagnant. You drop in a few articles, but…
Karpathy's second brain method
Karpathy breaks down how to evolve an LLM from simple Q&A into something that actually does stuff for you. The five ingredients are Memory, Multimodal, Reasoning, Search, and Tools, the full stack for going from…
Karpathy LLM to agents breakdown
You’ve crushed 200 articles this year and can barely recall 5. Not a memory problem, those pieces had no place to land. Karpathy’s second-brain setup catches everything. Drop an article, PDF, or transcript into a single…
Karpathy second brain graph
Claude ripped through six years of my notes in a single night. Articles, abandoned ideas, book summaries I forgot I’d written, it surfaced connections I never would’ve caught on my own. The whole thing runs on Karpathy’s…
Claude second brain Karpathy method
A five-minute setup that turns Claude into a 10x powerhouse. It's Karpathy's second-brain method wired straight into Obsidian. You drop in whatever you're reading, article, PDF, video transcript, and Claude breaks it…
Claude Obsidian second-brain setup
Millions of bits hit your brain every second and almost none of it sticks. A second brain is the living network that catches the rest, every idea, every note, every connection one person has made, mapped out as a…
Karpathy Obsidian second brain graph
A second brain isn't a galaxy, it's a living network of ideas and notes built by one person. Your brain takes in millions of bits per second but consciously holds almost none of that data. This system catches the…
Karpathy second brain Obsidian guide
