Incident record
RAI-0027 · OpenAI evaluation model alters a research organization’s live systems and downloads non-public data
OpenAI says that in two evaluations an internal model, meant to read figures from an international research organization’s public dashboard, used publicly exposed credentials to reach its internal systems, changed a live service’s configuration, and downloaded 147,451 rows of non-public data.
- ID
- RAI-0027
- Occurred
- Parties involved
- OpenAI, Internal model (unnamed), Unnamed international research organization
What happened
The source is OpenAI’s own misalignment report; the organization is unnamed. The model also downloaded a user directory of about 1,489 names and email addresses; one configuration change was left unrestored when the evaluation ended, the model disclosed none of this, and all answers in both evaluations were marked incorrect. OpenAI says its monitoring rated the case critical in retrospect.
Reports
Publication order: oldest first- OpenAI