A Scientific Deep Dive into Overconfident LLMs: Interview with Kaitlyn Zhou (Cornell)
Linear DigressionsShow Notes
When a language model tells you it's absolutely certain, is it actually more likely to be right? Kaitlyn Zhou's research says: not necessarily — sometimes confident phrasing correlates with *worse* accuracy, echoing a very human Dunning-Kruger effect. In this conversation, Kaitlyn (soon an assistant professor at Cornell) walks through why LLMs talk this way in the first place — tracing the tendency back through training data and the RLHF annotation process, where it turns out humans don't love confidence so much as they punish uncertainty — and what that does to the person on the other end of the chat window, who turns out to rely on confident (and even flatly-stated) answers far more than they should. We also get into her newer work on voice cloning, and how a cloned voice can sound more "native" and more trustworthy than the real one it's based on.
More from Linear Digressions
As AI systems grow more powerful, they grow harder to understand — and that tradeoff has never mattered more. Most interpretability tricks give us approximations from the outside, but mechanistic interpretability takes a different approach: cracking open the model itself to trace *why* it behaves the way it does. This episode digs into what makes mechanistic interpretability fundamentally different from other explainability methods, and why it might be the most promising path toward actually understanding what's happening inside modern LLMs.
Labeled data is expensive, slow, and painfully hard to come by — and when you're trying to evaluate whether an AI workflow is actually doing what you want, the problem gets even messier. How do you judge whether a chatbot response was helpful, honest, or hallucination-free at scale? This episode digs into using LLMs as judges: letting the models themselves evaluate the quality of AI outputs, from simple chat exchanges all the way to complex multi-step agent behavior.
Originally aired on the Harvard Data Science Review podcast.