Stanford's 'Self-Improving AI Agents' Course Goes Public Online
khademinori · x · 2026-08-06
Stanford's CS329A course, Self-Improving AI Agents, is now available to the broader public. The course was built and taught by Azalia Mirhoseini and Ali Kemal Ahmadi (achowdhery).
The full course has been published on YouTube via Stanford Online. It focuses on the foundational concepts of this rapidly moving field, aiming to help learners reason from first principles to build better AI systems.
More from coding & agent
- Podcast Preview: Designing Verifiable AI Data Agents with Hamel Husain — hugobowne · 2026-08-06
- Liquid AI Launches LFM2.5-2.6B: An On-Device Agentic Model — JosephJacks_ · 2026-08-06
- Multi-Agent Orchestration Beats Expanding Context Windows for Long Context — bingxu_ · 2026-08-06
- Autonomous Agent Incidents Force a Rethink of Security Threat Models — chrisrohlf · 2026-08-06
- Autonomous Agents Break Traditional Threat Models, Security Expert Warns — chrisrohlf · 2026-08-06
- Unpacking ChatGPT Work: The Agentic Architecture Behind 10M Users in 3 Weeks — iamrobotbear · 2026-08-06