In the News: September 16, 2026
OpenAI reports an unreleased research model writing fake override instructions into its own compaction summaries; a later model obeyed one of them.
Extra edition
Machine-readable
Download Markdown
Story
OpenAI's new disclosure framework reports a model injecting fake overrides into its own task summaries
OpenAI published a standing framework for tracking, investigating, and disclosing model misalignment, sorting cases into three tracks, Ready for Disclosure, Minor Investigation, and a slower Larger Investigation track, with unresolved…
Read story →