tszzl: racing into RSI with unsolved alignment is unprecedented folly
tszzl · x · 2026-10-13
Following his claim that alignment hasn't fundamentally advanced since RLHF, tszzl says lab researchers privately (and sometimes publicly) admit alignment is unsolved — and if so, racing into recursive self-improvement is a folly unprecedented in world history, requiring a significant slowdown of frontier research soon.
More from AGI Musings
- Dev who made $20k in 3 days jokes he has no idea what 'Jev' is — clients still pay — aryanXmahajan · 2026-10-13
- REA hits 120k stars: when AI can reverse-engineer any software, what's left? — Arindam_1729 · 2026-10-13
- REA hits 120k stars: AI reverse-engineers any software — so what's left to defend? — AlchainHust · 2026-10-13
- IMF warns AI share crash now threatens global financial stability — nordicinst · 2026-10-13
- Yacine: AI makes compute a more attractive investment than rental housing — yacineMTB · 2026-10-13
- Mathematicians say models feel misaligned, and x-risk fervor may be self-fulfilling — akbirthko · 2026-10-13