We have 3 of 3 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Tool-using language agents increasingly modify external systems, yet most runtime safeguards allocate scrutiny by generic uncertainty scores or coarse mutation heuristics. We introduce CASEL (Consequence-Aware Selective Execution Layer), a model-agnostic runtime allocation policy that combines calibrated failure probab...
In CLAUDE.md,"do not"is a natural-language instruction that the model interprets. Claude Code's deny is a built-in control that blocks an action before the agent can take it. Both can express the same security goal, but they control the agent in different ways. We measure this gap in 481 public CLAUDE.md files. An LLM...
A mechanism in which a language model maps actions to plain-language consequence categories with user-authored"allow","ask", or"never"rules is examined, and a gap between preference and commitment is revealed: repeatedly choosing "ask" preserves case-by-case choice but prevents a standing policy from settling decisions...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
