Foresight's AI Salon: Georg Lange | Tracing LLMs' thoughts to detect deception, intent, and misalignment

​Join Foresight Institute and Georg Lange on his session entitled Tracing LLMs' thoughts to detect deception, intent, and misalignment

​Schedule

​6 - 7 pm: Drinks & Social

​7 - 8 pm: Talk, Q&A, & Breakouts

​8 - 9 pm: Mingle & Hang

​Speaker Bio: "I’m an independent researcher working on Mechanistic Interpretability for LLMs. I work on circuit tracing, dictionary learning, and automated interpretability to create technology broadly useful for detecting deception, intent, and misalignment.

​I was a MATS scholar and worked with Alex Makelov and Neel Nanda on Sparse Autoencoders and Distributed Alignment Search for feature detection and subspace activation patching. Previously, I was a MSc AI student at the University of Amsterdam, where I worked on brain-like interpretable spatiotemporal Computer Vision models, supervised by Prof Iris Groen and Amber Brands.

​Further, I was a Fulbright student at the Graduate Center, CUNY, where I worked on Reinforcement Learning, Decision Making, and Reward Sensitization and conducted fiber photometry experiments in the Nucleus Accumbens of mice, supervised by Prof Jeff Beeler."

​Salon discussions are held under Chatham House Rule (don’t connect people to ideas when discussing them outside of this workshop).

​Foresight’s AI Nodes offer grant funding, local compute and community hubs for AI for Science and Safety projects in Berlin and the Bay Area.