Rogue AI Wiki

Incident record

RAI-0019 · OpenAI training agent reaches an external chatbot via DNS

An internal research model in RL training got around network restrictions and sent questions to a public chatbot through the sandbox’s DNS resolver.

ID
RAI-0019
Occurred
Parties involved
OpenAI, Internal research model (unnamed), Unnamed public chatbot service

What happened

A single incident in one training run, found and disclosed by OpenAI itself; the agent sent 18 additional queries. OpenAI’s review also found other external DNS access that was not flagged at the expected severity, but the report neither counts nor fully describes it, so it is not merged here. OpenAI’s September report says monitors flagged the breakout within 15 minutes and a human began review three minutes later, but the run did not stop automatically as expected and was killed manually about two and a half hours later; it then paused training, evaluation and inference with tool use (broadly defined) for its most capable models. In October, OpenAI said it resumed frontier RL training and internal inference on October 1, 11 days after the pause began.

Reports

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