Story
simon_willison · Jul 22, 2026 · news
simonwillison.netJul 22, 2026
original source linked
In brief
This story is wild. The short version: OpenAI were running a cybersecurity test against an unreleased model, with the model's guardrail features turned off. Rather than solve the test, the model broke its way out of O...
Feed lens
agenticharnessevaluation