Nathan Lambert releases free 20-video post-training course with ~12 hours of content
natolambert · x · 2026-08-07
AI researcher Nathan Lambert announced the completion of his summer project: a free course on post-training consisting of 20 videos, now on YouTube, accompanying his book, with slides open for modification and reuse. The course covers core foundations and research areas he believes will grow in importance, totaling about 12 hours. He notes that the number of people wanting to learn post-training will likely 100X again in the next 1-3 years, having already 100X'ed from two years ago. He emphasizes that developing clear intuitions for how models work is one of the most important skills going forward, and learning post-training math is the best way to battle test them. To celebrate, his book is 50% off on Manning with code PBLambert.
More from AGI Musings
- antirez: Models Without CoT Training Still Benefit From Reasoning Prompts — antirez · 2026-08-07
- Agentic AI Workflows Are Driving Up CPU and Memory Compute Demand — fchollet · 2026-08-07
- AI is Increasing Work Hours, Not Productivity — nikvassev · 2026-08-07
- AI Corrigibility: Beyond an Emergency Brake, Integrating It into the Learning Architecture — tallmetommy · 2026-08-07
- Next-Gen Science Labs Built on World Models and Agent Layer — MengdiWang10 · 2026-08-07
- Could AI Education Become a New "Tutelary Power"? Tocqueville Tech Essay Winners Announced — chalmermagne · 2026-08-07