Gå til indhold
Global sound
Linear Digressions

Linear Digressions

A Scientific Deep Dive into Overconfident LLMs: Interview with Kaitlyn Zhou (Cornell)

· 34 min.

Episodebeskrivelse

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.

Website: soundcloud.com

Live, seneste time: 8.228 sange på 3.401 stationer i 127 lande

Opdag verden gennem radioen

Flere måder at opdage på (7)

Hørt noget godt? Gem det, eller åbn det direkte i Spotify.

★ Artist of the week The fastest riser on the radio this week
Your song here? From € 9 per week →
Blur FM Online RadioFortsæt med at lytte