Tengyu Ma's 2.5-hour Stanford lecture unpacks what happens before ChatGPT's first word
stanfordnlp · x · 2026-10-15
A 2:34:52 Stanford lecture by Tengyu Ma is recommended as worth a focused watch: he writes the next-token rule on the board at 44:38, covers attention at 1:00:01, and training updates at 2:00:03 — unpacking the machinery behind ChatGPT's answer before the first word appears.
The recommender's closing prompt: if a model builds an answer one token at a time, what do we mean when we say it understands us?
More from Companies & People
- SpaceXSI hiring a solo Tableau admin to power data decisions across X and Grok — Kyrannio · 2026-10-15
- NVIDIA's open-sourced CAD kernel explained: code dating back to the 1970s — rms80 · 2026-10-15
- Modal culture lesson: grow people 4-5x a year instead of hiring to scale — charles_irl · 2026-10-15
- a16z gutted its 34-person talent team, signaling tougher times ahead — SumitGup · 2026-10-15
- Northwood Space CEO Bridgit Mendler wants 1,000 SpaceXs in five years, not 25 — a16z · 2026-10-15
- McKinsey makes entry-level job candidates spar with a fake AI client in interviews — The Verge AI · 2026-10-15