A Scientific Deep Dive into Overconfident LLMs: Interview with Kaitlyn Zhou (Cornell)
Linear Digressions10 Elo

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

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.

Tämä jakso on lisätty Podme-palveluun avoimen RSS-syötteen kautta eikä se ole Podmen omaa tuotantoa. Siksi jakso saattaa sisältää mainontaa.

Jaksot(320)

Better Know a Benchmark: Humanity's Last Exam

Better Know a Benchmark: Humanity's Last Exam

Humanity's Last Exam was designed with a bold premise: questions that human experts can answer, but AI models can't. Originally dubbed "Humanity's Last Stand," this benchmark is a massive academic col...

17 Elo 23min

Reasoning Models: When LLMs Went Beyond Fancy Autocomplete

Reasoning Models: When LLMs Went Beyond Fancy Autocomplete

Reasoning models don't just answer your question — they *think out loud* first. In this episode we dig into the class of AI models that generate intermediate chains of thought before arriving at a fin...

3 Elo 25min

Distillation, or, How to Steal a Model

Distillation, or, How to Steal a Model

This week we’re covering model distillation: the technique of using a large "teacher" model's outputs to train a smaller, cheaper "student" model that mimics it. They cover the two big reasons labs do...

27 Heinä 23min

Invisible LLM Failures and AI Fluency with Chris Potts (Stanford)

Invisible LLM Failures and AI Fluency with Chris Potts (Stanford)

What happens when a Stanford linguistics professor turns his attention to AI chatbots — and the surprisingly invisible ways humans misunderstand them? Chris Potts joins the show to unpack the hidden f...

20 Heinä 41min

Still summer break: back next week

Still summer break: back next week

Still summer break: back next week by Katie Malone

13 Heinä 25s

Summer break: back soon

Summer break: back soon

Summer break: back soon by Katie Malone

6 Heinä 36s

Interviewing the Linear Digressions Agents (The Agents Season, Episode 11)

Interviewing the Linear Digressions Agents (The Agents Season, Episode 11)

After a five-year hiatus, the podcast that burned out partly over the tedium of writing episode descriptions is back — and using AI agents to handle exactly that task. The season-11 finale turns the l...

28 Kesä 37min