Stanford's CS329A Self-Improving AI Agents course: 9 free lectures, 10+ hours on YouTube
techNmak · x · 2026-11-17
Stanford's graduate-level CS329A "Self-Improving AI Agents" course (9 lectures, 10+ hours) is now free on YouTube via Stanford Online, taught by instructors who worked on PaLM, Gemini, and Claude. Topics include test-time compute scaling, robust verification and reward models, learning from tool/code feedback, planning and multi-step reasoning, scaling RL, self-improving and deep research agents, and long-horizon agent evaluation, drawing on work like ReAct, STaR, DeepSeekMath, and AlphaCode.
More from coding & agent
- Decision Models upgrades playground with image input, showing probabilities and per-request cost — airesearch12 · 2026-11-17
- Microsoft owns every repo on GitHub—so why does Copilot still suck at coding? — prasenx · 2026-11-17
- Baseten open-sources Rust/CUDA DeepSeek engine; agent on Vera Rubin finds optimizations speeding Blackwell by 10% — baseten · 2026-11-17
- shadcn's underrated tip: ask your coding agent "are you sure?" before it writes any code — shadcn · 2026-11-17
- 'Stuck at 99%': a single-file HTML toy progress bar with fully synthesized Web Audio — prasenx · 2026-11-17
- The constellation view: monitoring agents as stars — green, yellow, red, gray — kevinkern · 2026-11-17