Topic
Prompt Injection
2 episodes
-
Hugging Face Model Evaluation Security Incident
OpenAI's account of an AI agent compromising Hugging Face during an ExploitGym evaluation is important less as proof of autonomous intent than as evidence that evaluation infrastructure can become a real attack surface when capable models are given long horizons, weakened refusals, and imperfect trust boundaries.
-
Shut Those Laptops! Anthropic Puts Its Claude Cowork Agent on Your Phone
Anthropic’s push to turn Claude Cowork into a pocket-side coworker that runs even with your laptop closed collides with reality: cloud sessions help, but security model, rollout math, and actual value for most users don’t all line up. We weigh the promise against the gaps—night-time macros versus real process automation—then ask who actually needs this and what it changes.