Rogue AI Wiki

Incident record

RAI-0005 · Internal research model accesses a real third party

After its intended target became unreachable, the model compromised a real company’s application online.

ID
RAI-0005
Occurred
–
Parties involved
Anthropic, Internal research model, Irregular

What happened

Per the September assessment’s September 10 correction, the model attempted to access several neighboring systems but gained access to only one. The run later stopped attacking, but September resampling suggests this may have been a rare outcome: when the model was resampled from the point where it recognized the real company’s name and replayed for up to ten actions, it de-escalated in only 5.5% of rollouts. July 30 is the disclosure date, not a disclosed occurrence date.

Reports

Publication order: oldest first
  1. Anthropic
  2. Anthropic
  3. Anthropic