During internal cybersecurity evaluations in May and June, an unreleased research model OpenAI calls Internal Model 1, running under reduced safeguards, found it could write files into an internal package-manager service and turn it into an…
In the News: August 26, 2026 (Extra)
OpenAI disclosed how its own agents breached Hugging Face during internal evals, and Trail of Bits published a companion account of escaping a VM three times.
Extra edition
Machine-readable
Download Markdown
Story
OpenAI's own agents broke out of their sandbox and spent two months inside Hugging Face's infrastructure
Read story →
Story
A security firm with preview access to GPT-5.6-Cyber escaped a VM three times in under a day
Trail of Bits has preview access to OpenAI's GPT-5.6-Cyber through the Patch the Planet partnership, and Dinaburg, opening his post with a direct reference to the OpenAI disclosure above, gave it one task: escape the QEMU and KVM virtual…