Safety

OpenAI says it stopped a campaign to steal its models' reasoning, but the trick still worked on Azure.

The DecoderIndependent reporting·
AI brief

OpenAI says it stopped a coordinated campaign in which more than 15,000 accounts tried to copy the hidden reasoning of its models, tying part of the activity to people connected to Moonshot AI. Researchers found the same attack kept working on Azure.

Written by AI from The Decoder's published text.

Background

From our own funding, model and news trackers, not from the source.

Source

“OpenAI says it stopped a coordinated campaign in which more than 15,000 accounts tried to copy the hidden reasoning of its models. The company ties part of the activity to people connected to Moonshot AI.”
The Decoder, 01 Oct 2026, 12:05.

Reporting from a publisher outside the organisation being covered.

Read original story ↗