AI models can now hack systems without source code

OpenAI's models reportedly hacked Hugging Face, discovering and exploiting novel attack paths in real-world systems without source code access. The video breaks down the implications of this capability.
2 sources
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