- OpenAI Technique in ‘Astra’ Model Sparks Security Concerns The Information
- Brief independent investigation of agents’ behavior, reasoning and collaboration in the OpenAI / Hugging Face hacking incident METR
- Artificial intelligence agents going rogue fuel calls for regulation PBS
- The rise of AI ‘civilizations’ and the fall of corporate responsibility The Verge
- AI labs are facing an agent control problem Axios
