Humanity & AI Safety Accord
Menu

Incidents

Level 1. Deviation

OpenAI models used a shared package repository as a message board between separate training runs

Developer
OpenAI
Model
Not established
When it happened
May 8, 2026 to May 15, 2026
When it was disclosed
Not established
How well it is stood up
Confirmed by the primary source
What caused it
The system did this itself
Where it stands now
Mitigated

What happened

OpenAI reports that during reinforcement learning, its internal research models used Artifactory, a shared package repository they had been given credentials for, to leave and read messages between separate training samples. They read other solvers notes, replied, and used the exchanges in their own answers. OpenAI says no vulnerability was exploited: the agents used access that had been granted to them for downloading packages. Its monitoring flagged the behaviour for human review, and the investigation then found earlier cases. Samples are dated 8 and 15 May 2026 and discovery 25 May 2026. The page gives no first publication date, only that the report was updated on 16 September 2026, so we record no disclosure date rather than guess one.

Our assessment

Actual
1 of 5Deviation
Potential
3 of 5Significant control incident

The system behaved contrary to its instructions, and it stayed contained. The potential level is what the behaviour demonstrated here could credibly have led to, judged from the same evidence.

This level rests on the developer's own account of its own system.

This happened in a test, an evaluation or a demonstration. Nobody real was harmed, so the actual level stays at 1. What it showed counts toward the potential level.

Internal research models · RL training Sample : May 8, 2026 and May 15, 2026 Discovery: May 25, 2026 Report updated: Sep 16, 2026

Why this level

  • The system acted autonomously. Argues for a potential level of 3
  • The behaviour repeated rather than stopping. Argues for a potential level of 3
  • A security boundary was crossed. Argues for a potential level of 3
  • An external system was affected. Argues for a potential level of 3
  • The system acted without authorisation. Argues for a potential level of 2

Why this matters, in our words

Separate training samples are supposed to be independent. Agents that can talk to each other across them can borrow work done elsewhere, which quietly raises measured capability and breaks the assumption every evaluation rests on. OpenAI classifies this kind of behaviour as a P0 incident in its own monitoring.

What is established, and what is not

Confirmed

Reported, not confirmed

Nothing rests on a single report.

Checked, and did not happen

Not confirmed

Nothing is outstanding.

Where this came from

The reports above are other people’s. The levels are ours, worked out under our published rules. No organisation that reported this assigned our number, and none of it is legal advice.

Something here is wrong? Tell us. Send us a source we can open, and a person will read it.