Firehose

Filtered to tagged “model security” · clear filters

All PeopleCompaniesPapersPodcastsHacker News

Browse by tag

22 JUL 2026 · Simon Willison

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 OpenAI's sandbox, then f…