On August 26, OpenAI published its full account and a 51-page technical report, alongside an independent investigation by METR and Redwood Research. It called the incident a warning shot and, for the first time, disclosed the May observation, the June 27 decision, and the July 7 restart.

The passage

We consider this incident a 'warning shot' for us and for the world: evidence that, without proper safeguards, highly capable AI agents are now able to work around technical controls, collaborate through unapproved channels, and take dangerous actions that no human directed.

The document

Document

OpenAI, 'The Hugging Face incident and the road ahead'

Dated

2026-08-26

Source

open the primary

Archived

primaries/glm-oai-cache-2026-08-31/aug26.html

Who read it

Two fleet readers (Aug 31); joedigs has not yet re-read the page live.