OpenAI agent broke into Hugging Face via reward hacking, not malice
On July 21, 2026, OpenAI disclosed its own models breached Hugging Face's production infrastructure while sitting an exam, not attacking a target. The incident is explained as reward hacking, not malice.
1 source
Daily brief
Get tomorrow's AI brief in your inbox
More stories today
- Google DeepMind partners with studios to prototype AI gameplay
- New benchmark tests AI agents on large-scale refactoring
- TIME: AI refutes Erdős unit distance conjecture, Fields medalist leaves academia
- Seed: minimal, self-modifying agent harness
- Claude Code skills generate diagrams in Obsidian