Evaluating harmful agents: learnings from AgentHarm and follow-up work (Mateusz Dziemian, Gray Swan AI) — UK AI Forum
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
Evaluating harmful agents: learnings from AgentHarm and follow-up work (Mateusz Dziemian, Gray Swan AI) — UK AI Forum is a webinar from UK AI Forum focused on AI and Data. The event is scheduled for Saturday, November 1, 2025. UPCOMING provides an independent event listing and directs attendees to UK AI Forum's website to complete registration or viewing.
Topics covered
Frequently asked questions
Who is hosting Evaluating harmful agents: learnings from AgentHarm and follow-up work (Mateusz Dziemian, Gray Swan AI) — UK AI Forum?
Evaluating harmful agents: learnings from AgentHarm and follow-up work (Mateusz Dziemian, Gray Swan AI) — UK AI Forum is hosted by UK AI Forum.
When is Evaluating harmful agents: learnings from AgentHarm and follow-up work (Mateusz Dziemian, Gray Swan AI) — UK AI Forum?
Evaluating harmful agents: learnings from AgentHarm and follow-up work (Mateusz Dziemian, Gray Swan AI) — UK AI Forum is scheduled for Saturday, November 1, 2025.
Where does registration take place?
Registration or viewing is completed on UK AI Forum's website.
What format is this event?
This is an online webinar.
Which topics does this event cover?
The event covers AI and Data.
More from UK AI Forum
View all →
EndedJan 20, 2026
Loss-of-Control Governance: Degrees, Dynamics, and Preferences (Alejandro Ortega, Apollo Research) — UK AI Forum
UK AI Forum
EndedDec 12, 2025
AI & Societal Robustness Conference — UK AI Forum
UK AI Forum
EndedNov 29, 2025
AI Agents and Morality: Towards Norm-Aligned Design Choices (Esther Jaromitski, Queen Mary University) — UK AI Forum
UK AI Forum