200-seat UC Berkeley course on full-stack post-training, RL and applied RSI announced
karinanguyen · x · 2026-11-12
Karin Nguyen and KJHMiao announced a spring UC Berkeley course on full-stack post-training, RL and RSI, expanded to 200 seats for advanced undergrads and grad students.
- Topics span pre-training, post-training, RL and inference-time scaling, autonomous agents, long-horizon reasoning, and infrastructure.
- The course ends with applied RSI: systems capable of recursively improving themselves in the real world.
More from Companies & People
- Epic's 2026 AI MegaJam partners include Claude, Google, OpenAI, NVIDIA and AMD — jfischoff · 2026-11-12
- NVIDIA Seoul Agentic AI Hackathon wraps, winning team takes home DGX Spark — NVIDIAAI · 2026-11-12
- Three AI game dev competitions land this month, one with a $47,800 prize pool — Promptmethus · 2026-11-12
- ChipAgents makes The Information's 50 Most Promising Startups of 2026 with 200+ deployments — WilliamWangNLP · 2026-11-12
- World Labs and AMD enter robotics, Li Fei-Fei appears at CoRL — breadli428 · 2026-11-12
- Jason Wei: in AI, 'who you know' now matters nearly as much as 'what you can do' — _jasonwei · 2026-11-12