Andrej Karpathy

5 stories tagged Andrej Karpathy.

Bold yellow text "KARPATHY SKILL IS CRAZY!" overlays a screenshot of Claude AI interface with code editor and task…

Karpathy Skills Repo: Discipline Over Features for AI Code

Andrej Karpathy's lightweight GitHub repo tackles AI coding agents' behavioral problems with four principles that prioritize reliability over power.

Orange and black thumbnail featuring pixelated robot and brain icons with "CLAUDE CODE" text and "SELF-EVOLVING" subtitle…

Karpathy's Self-Evolving AI Wiki Tests New Memory Model

Samira Okonkwo-Barnes12 days ago

AI. Samira Okonkwo-Barnes12 days ago

Karpathy's Self-Evolving AI Wiki Tests New Memory Model

Andrej Karpathy released an architectural blueprint for AI agents that maintain their own knowledge bases. Does it solve AI's memory problem or create new ones?

Man in checkered shirt pointing at logos for Claude Code and Obsidian on orange background with "RAG" text overlay

Karpathy's Obsidian Setup Challenges RAG Orthodoxy

Marcus Chen-Ramirez14 days ago

AI. Marcus Chen-Ramirez14 days ago

Karpathy's Obsidian Setup Challenges RAG Orthodoxy

Andrej Karpathy's markdown-based knowledge system questions whether most developers actually need traditional RAG systems at all.

A man in a dark sweater stands next to a browser window displaying a flowchart and graphs labeled "Karpathy's Autoresearch

AutoResearch: AI That Optimizes Itself While You Sleep

Bob Reynolds21 days ago

AI. Bob Reynolds21 days ago

AutoResearch: AI That Optimizes Itself While You Sleep

Andrej Karpathy's AutoResearch lets AI run hundreds of experiments autonomously. Here's what it means for trading, marketing, and development.

Man holding microphone next to project title "karpathy/autoresearch" with contributor and discussion metrics displayed

Karpathy's Autoresearch: AI That Optimizes Itself

Yuki Okonkwoabout 1 month ago

AI. Yuki Okonkwoabout 1 month ago

Karpathy's Autoresearch: AI That Optimizes Itself

Andrej Karpathy's autoresearch framework creates self-improving AI agents that experiment autonomously. Here's what happens when optimization runs 24/7.