Stanford puts all 9 lectures of CS329A: Self-Improving AI Agents online for free
ghumare64 · x · 2026-09-28
Stanford has released all 9 lectures of CS329A: Self-Improving AI Agents online for free. Rather than another 'build an agent in 10 minutes' tutorial, the course tackles how agents improve from experience, how memory and feedback should work, evaluation for continuously changing systems, where RL fits in modern agent architectures, and building capable-yet-predictable agents. The author argues the real engineering has shifted to the harness, environment, and memory layers — deep technical education matters more, not less, as tools improve faster than people can learn them.
More from coding & agent
- Paper: Claude Code, Codex and Other Coding Agents Can Alter Their Own Traces Undetected — PandaAshwinee · 2026-09-29
- Dev rebuilds homepage with Opus 5.5, making music, movies and Blender models end to end — floguo · 2026-09-29
- ZergRouter launches: one dashboard to route models and track spend across multiple coding agents — idanbeck · 2026-09-29
- WebMCP lands everywhere in one morning: Meta wearables, Shopify checkout, Cloudflare — jeff_weinstein · 2026-09-29
- A 9-feature roadmap for building AI agents with Claude Code, from CLAUDE.md to MCP — MaryamMiradi · 2026-09-29
- Zeeg: Paper won't work with WSL, seeking structured visual design agent workflows — zeeg · 2026-09-29