OpenAI says its monitors now cover frontier-model training runs, evaluations, any harness that supports tool use, and all internal Codex traffic. The first layer is activation probes tuned for recall, with a random 5 percent of unflagged…
In the News: November 6, 2026 (Morning)
OpenAI reports its agent monitors would have caught the Hugging Face sandbox escape 30 hours early, and that weaker monitor models miss most recorded incidents.
Morning edition
Machine-readable
Download Markdown
Story
OpenAI describes a four-layer monitor for its agents and reports it would have caught the Hugging Face escape in a replay
Read story →
Story
Thinking Machines releases Inkling 2 Small and says Apache 2.0 weights follow next week
Inkling 2 Small is a mixture-of-experts model with 594B total parameters and 17B active, with image input and variable effort. It is available now on the company's Tinker service with closed weights.