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.

Stable ID
RAI-0019
Event period (not publication date)
Parties involved
OpenAI, Internal research model (unnamed), Unnamed public chatbot service

Context and evidence boundaries

A single incident in one training run, found and disclosed by OpenAI itself; the 18 questions are query counts, not separate incidents. 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.

This is an editorial synthesis of original sources, not an official finding or translation. Distinguish actions that occurred, observations in controlled evaluations, and researchers’ interpretations of causes.

Original sources and follow-ups

Publication order: oldest first
  1. OpenAI