Read news on karpathy with our app.
Read more in the app
Karpathy shares 'LLM Knowledge Base' architecture that bypasses RAG with an evolving markdown library maintained by AI
Autoresearch on an old research idea
Scaling Karpathy's Autoresearch: What Happens When the Agent Gets a GPU Cluster
Karpathy’s March of Nines shows why 90% AI reliability isn’t even close to enough
Show HN: Similarity = cosine(your_GitHub_stars, Karpathy) Client-side
I wrote the manual Karpathy said was missing for agentic AI
Karpathy on Programming: “I've never felt this much behind”
Karpathy on DeepSeek-OCR paper: Are pixels better inputs to LLMs than text?
Karpathy on Software 2.0 (2017)
Karpathy on VS Code Cursor and Sonnet 3.5 vs. GitHub Copilot
Karpathy: Let's reproduce GPT-2 (1.6B): one 8XH100 node 24h $672 in llm.c
GitHub – Karpathy/LLM101n: LLM101n: Let's Build a Storyteller
