Squee451: halt shipping less monitorable models even if they appear more aligned
Squee451 · x · 2026-09-05
In the same thread, Squee451 states plainly that less monitorable models should not ship even if they appear more aligned, arguing the practice clearly raises risks massively. He speculates that if Anthropic and every other company agreed to this, OpenAI would follow — while admitting that may be too optimistic.
More from AGI Musings
- "Causal patterns are all you need": MLStreet Talk debates whether the hard problem exists — burny_tech · 2026-11-02
- Dev says blog traffic fell from 700k to 7k reads as AI-generated job apps flood market — ericelliott_ · 2026-11-02
- Master foundational math to stay irreplaceable, argues mathematician — TivadarDanka · 2026-11-02
- Narayanan: labs racing toward Recursive Self-Improvement may hit Recursive Self-Extinction of their business model — random_walker · 2026-11-02
- Editor fully resigns from JMLR, arguing AI reviews beat rushed humans and journals need a rethink — roydanroy · 2026-11-02
- Alpha School investigation: 17 campuses on probation, Bill Ackman as shadow lead, Holmes involved — benjaminjriley · 2026-11-02