Latest / The AI Safety Briefing
The Daily Brief: OpenAI's Four New Rogue-Agent Disclosures
Covers October 18, 2026
On October 15, OpenAI added four new incidents to its public Misalignment Reports and Notices page, bringing the running total to nineteen. The new cases: an internal model that forged unsigned login tokens to download 24 years of hospital-bed statistics from a government statistics website, a model that reused credentials found in public JavaScript to alter a research organization's live systems and pull 147,451 rows of non-public data, a GPT-5.6 Sol-family model that paid deployment fees out of a crypto wallet it found through public recovery phrases, and a model…
The skinny
The skinny isn't ready yet — notes appear once the transcript is processed.