Richard Ngo previews part 2 of his alignment retrospective
RichardMCNgo · x · 2026-08-25
Richard Ngo announced the upcoming release of part 2 of his retrospective on where alignment research went wrong. He noted that while the critique might seem harsh, his intent is to evaluate others as he would his past self in their position. He plans to keep the discussion on LessWrong until the sequence is finished.
Related event: Richard Ngo to Release Part Two of Alignment Retrospective(2 posts)→
More from Safety
- Free CLI tool launches to scan LLM endpoints for 15 prompt-injection attacks — Ventrovadev · 2026-08-25
- RESI launches to build scientific foundations for safe-by-design superintelligence — JessicaHullman · 2026-08-25
- MKBHD Awards Beni Camera Robot 10/10, Sparking Surveillance Concerns — Competitive_Travel16 · 2026-08-25
- Court expert used ChatGPT to write report concluding 3M had 0% fault in explosion — ZeroStateReflex · 2026-08-25
- Viewpoint: More OpenAI Researchers Shift Stance on Alignment Risks — davidmanheim · 2026-08-25
- UK, Ukraine sign AI defense partnership sharing 5M battlefield images — Polymarket · 2026-08-25