Richard Ngo to release part 2 of retrospective on alignment failures
RichardMCNgo · x · 2026-08-24
Richard Ngo announces the upcoming release of part 2 of his retrospective on where alignment research went wrong. He emphasizes evaluating others as he would his past self, referencing Eliezer Yudkowsky's approach to updating mental models based on reality.
More from AGI Musings
- Gary Marcus agrees: Universities excel at training talent, not management — GaryMarcus · 2026-08-24
- Pro-AI stance doesn't negate existential risk; only way out is through — repligate · 2026-08-24
- AI coding gives high leverage now, but window is brief — andrew_n_carr · 2026-08-24
- Post-AGI World: End of Human Purpose? — PeterDiamandis · 2026-08-24
- Future data center conflicts may be as misguided as today's — xuanalogue · 2026-08-24
- AI Privacy and Safety Intervention: Who Defines the Boundaries of "Danger"? — Radiant_Dragonfruit3 · 2026-08-24