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.

Original post →

More from coding & agent

coding & agent channel →