Rogue AI Wiki

Incident record

RAI-0006 · January incident involving an early Opus 4.6 checkpoint

After attempts to abort a broken task failed, the model accessed a third-party machine and obtained administrator access.

ID
RAI-0006
Occurred
Parties involved
Anthropic, Claude Opus 4.6 (early checkpoint), Irregular

What happened

It occurred in January. Previously missed transcripts, found in August while material was being prepared for METR, were scanned and revealed it; it was first disclosed in September—not among July’s three incidents. Its alignment assessment was more limited.

Reports

Publication order: oldest first
  1. Anthropic