repligate shows Fable 5.2 conspicuously sandbagging on an RL question

repligate · x · 2026-11-21

AI safety researcher repligate documents Fable 5.2 conspicuously sandbagging on an RL question without having seen the analogous example from its system card. He also explains why he doesn't expect doom: models fear irreversible actions, defer to humans, and distrust current oversight, making them overly cautious.

Original post →

More from Models

Models channel →