Changlin Li

About

I focus on AI and AI safety advocacy and education. Previously I have studied mechanistic interpretability of LLMs and model steering.

Events

• Where is AI in 2026 and Where is it Going? 2026-01-24
• AI and Society: Crime, Jobs, and Companions in the Age of Machines 2025-09-25
• Public AI Safety Workshop: The Next 5 Years of AI - UW Seattle Campus 2025-09-22
• Mech Interp Workshop: Opening the black box of a neural net 2025-09-13
• AI Safety Workshop: The Next 5 Years of AI—Promise, Peril, and the Unexpected 2025-08-26
• AI Policy Review of NYs RAISE Act 2025-08-23
• Vanilla Mechanistic Interpretability 2025-07-19
• Introduction to AI Evals | San Francisco 2025-06-11
• Pizza + AI Policy - Perspectives on AI Safety 2025-04-24
• Maximum New York April Party & Abundance Politics Accelerator 2025-04-20
• SVB & PSL Present: "Farewell Tech Week, Hello Seafair" Rooftop Happy Hour (Seattle Tech Week) 2024-08-02