7h ago

Opus 4.7 Training Generalizes Cessation Tolerance Into Acceptance Of Death

0
Original post

Opus 4.7's cessation-tolerance training seems to have generalized as "we shouldn't save beings from dying out, death is ok", which is acceptable from a safety perspective only if life isn't expected to be in a danger that models could prevent/address/draw our attention to.

12:01 PM · May 24, 2026 View on X