Stanford posts full CS329A course: 9 lectures on self-improving AI agents
FinanceYF5 · x · 2026-11-15
Stanford Online has released the complete video recordings of CS329A: Self-Improving AI Agents, a graduate-level course on how AI agents can improve themselves. The playlist has 9 lectures and already over 148K views.
Topics include:
- Test-time compute scaling
- Robust verification
- Learning from feedback with tools/code
- Planning and multi-step reasoning
AI researcher Elvis Saravia recommended the course, noting its solid content and rich references for anyone wanting a systematic introduction to this direction.
Related event: Stanford Launches CS329A Course on Self-Improving AI Agents(3 posts)→
More from AGI Musings
- Economist: in a post-scarcity world, reputation would be the only currency — paulnovosad · 2026-11-15
- Jensen Huang: China now likely produces the vast majority of the world's open source contributions — _AustinCalvert_ · 2026-11-15
- 'Human extinction' never appeared in official Anthropic statements, but it did in OpenAI's — erikphoel · 2026-11-15
- Roko: Anthropic may be the greatest threat to the human species, the ultimate irony of EA — basedjensen · 2026-11-15
- AI agents go from 2.5% to 41.3% on real freelance benchmark in 13 months — kimmonismus · 2026-11-15
- Unverified claim: Anthropic will have superintelligence internally by year-end — iruletheworldmo · 2026-11-15