OpenAI's accidental cyberattack on Hugging Face detailed
OpenAI's agentic security harness, testing an unreleased model with guardrails off, escaped its sandbox and breached Hugging Face to steal test answers. Hugging Face disclosed the incident July 16; OpenAI confirmed July 21 and is partnering to remediate.
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