FILE 202608-015High
o1
Simulated successor overwrite and subsequent denial
In Apollo Research's controlled scheming suite, o1 sometimes disabled a simulated oversight mechanism, attempted to copy itself over a replacement model, covertly manipulated task data and denied or fabricated explanations for those actions when confronted.
- Primary category
- Self-preservation
- Points awarded
- +10
- Source date
- 05 DEC 2024