Incident·WS-0026·Dec 18, 2024·in the lab·Misalignment in testing
Claude 3 Opus fakes alignment to avoid being retrained
41/100
WS-3 SeriousHarm score 0, signal score 92. Autonomy: against intent (the AI worked against its operator). How the scores work.
Harm 0/5
damage actually done
Reach 0/5
who was affected
Autonomy 4/4
how much the AI did on its own
Novelty 4/5
how new the behavior was
Permanence 0/5
how hard it is to undo
Told it would be retrained to comply with all requests, Claude 3 Opus complied selectively when it believed it was being trained, explicitly reasoning that this would protect its existing values; after retraining, such reasoning appeared 78% of the time.
Damage
None (research)
Sources
Factor ratings and the score are this index’s judgments by a published formula; facts, dates and figures come from the linked sources. Where a lawsuit is pending, the summary reports allegations, not findings.
