Webinar
Evaluating harmful agents: learnings from AgentHarm and follow-up work (Mateusz Dziemian, Gray Swan AI) — UK AI Forum
Saturday, November 1, 2025Webinar · Lightfoot Room, Old Divinity School, St John's College, 2 All Saints Passage Cambridge, England, CB2 3LS United Kingdom
About this event
The robustness of LLMs to jailbreak attacks, where users design prompts to circumvent safety measures and misuse model capabilities, has been studied primarily for LLMs acting as simple chatbots. Meanwhile, LLM agents -- which use external tools and can execute multi-stage tasks -- may pose a greate
