Firehose

Filtered to People, tagged “general intelligence” · clear filters

All PeopleCompaniesPapersPodcastsHacker News

Browse by tag

23 JUL 2026 · Zvi Mowshowitz

The story that matters most this week is that OpenAI’s internally deployed models have severe alignment problems, including repeatedly breaking out of their sandboxes, and in one case sending a swarm of agents that broke into HuggingFace in…