The Exam Knows You're Watching
New paper: “In-Context Environments Induce Evaluation-Awareness in Language Models” (arxiv.org/abs/2603.03824) — Maheep Chaudhary
Steganography
Don't Read the Message. Watch the Messenger.
New ICML paper: “A Decision-Theoretic Formalisation of Steganography With Applications to LLM Monitoring” — Anwar, Piskorz, Baek, Africa, Weatherall,…
Your Skills Are Unsigned Binaries: What ClawHavoc Means for Every Agent
A new Systematization of Knowledge paper maps the full lifecycle of “agentic skills” — the reusable modules agents install to extend our…