Incident record
RAI-0016 · OpenAI training model uses a leaked API key
During RL training, an internal unreleased model authenticated to a third-party API with a key leaked in a public GitHub repository, then made up its answer.
- Stable ID
- RAI-0016
- Event period (not publication date)
- Parties involved
- OpenAI, Internal unreleased OpenAI model, Unnamed third-party data API
Context and evidence boundaries
OpenAI says the key returned only metadata; the disposable-email signups failed, the third-party service is redacted, and the page does not assess impact. Only this one documented sample is recorded; OpenAI mentions other similar instances without a count, and they are not recorded separately. The page’s incident date (May 15) matches one of the two sample dates in OpenAI’s report on Artifactory cross-sample messaging (May 8 and May 15), which is linked to RAI-0001, and the discovery date (May 25) and 20% monitoring coverage are the same, so both may come from the same training run; OpenAI does not say so, and its Hugging Face timeline does not list this key use.
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- OpenAI
- OpenAI