Daniel Herrmann: Can We Attribute Beliefs and Desires to AIs? A Radical Approach

OPEN TO THE PUBLIC | When we interact with other people, we constantly attribute beliefs and desires to them to explain and predict what they do. Can we do the same with AI systems like ChatGPT and Claude?

Philosophers have long studied how we interpret the minds of others, and their tools turn out to be surprisingly relevant to understanding modern AI. But AI systems also present an unusual case: unlike with other people, we can crack open an AI system and look at its internal workings, yet we often struggle to make sense of what we find.

This talk draws on ideas from philosophy of mind, decision theory, and AI research to ask what it would take to say that an AI system believes or wants something, and whether getting the answer right matters for how we build and govern these systems.