Webinar
Chain-of-thought interpretability for AI Agents (Uzay Macar, MATS) — UK AI Forum
Saturday, October 11, 2025Webinar · Lightfoot Room, Old Divinity School, St John's College, 2 All Saints Passage England, CB2 3LS United Kingdom
About this event
As AI systems become increasingly agentic, understanding how they make decisions becomes crucial for safety and control. This talk presents novel mechanistic interpretability methods for decomposing chain-of-thought reasoning in LLM agents to identify "thought anchors" - critical reasoning
Chain-of-thought interpretability for AI Agents (Uzay Macar, MATS) — UK AI Forum is a webinar from UK AI Forum focused on AI and Data. The event is scheduled for Saturday, October 11, 2025. UPCOMING provides an independent event listing and directs attendees to UK AI Forum's website to complete registration or viewing.
