Papers by John Hughes

• Agentic Misalignment in Summer 2026

  Anthropic / Anthropic, MATS, Theorem, UK AISI

  Published on: 2026-07-13 5 authors
• Best-of-N Jailbreaking

  Anthropic, Tangentic, Speechmatics / MATS, Stanford University, University College London, University of Oxford

  Published on: 2024-12-04 10 authors