Skip to content
PodSubs
ShowsPeopleGuestsJobsNewsEvents
More
BlogPodCred
Menu
ShowsPeopleGuestsJobsNewsEventsBlogPodCredNetworksSign in
Join nowSign in
  • Shows
  • People
  • Jobs
  • News
  • More
    • Guests
    • Events
    • Blog
    • PodCred
    • Networks
    Join nowSign in

Linear Digressions

Linear Digressions artwork

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

Aug 10, 202634 minAudio
ShareXLinkedInFacebookWhatsAppEmail

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.

Audio and video play straight from the show's own hosting. PodSubs stores and serves no media.

Hosts and Guests

Nobody is credited on this episode yet.

Credit the people on this episode

Be the first to rate this episode

More episodes

All episodes
  1. How to Stay Relevant as a Data Scientist in the Age of AI | Interview with Dr. Jon Krohn

    Nov 16, 202644 minAudio

    Staying relevant as a data scientist when AI is reshaping the field isn't just a career question - it's an existential one. Dr. Jon Krohn, neuroscientist-turned-data-science-educator, podcaster, and consultant, sits...

    Credit the people on this episode

  2. GPU Architecture for LLM Inference: Memory, Bandwidth and Hardware Explained

    Nov 9, 202620 minAudio

    GPUs are the engines powering every AI conversation you've ever had - but what's actually happening inside those chips when an LLM generates a response? Understanding GPU fundamentals turns out to be surprisingly useful...

    Credit the people on this episode

  3. KV Cache Fundamentals

    Nov 2, 202624 minAudio

    The unsung hero of every LLM conversation you've ever had? A clever optimization called the KV cache. Self-attention is computationally brutal - every token attending to every other token means costs that scale as N²,...

    Credit the people on this episode

  4. AI Inference 101

    Oct 26, 202628 minAudio

    Everyone talks about training the model - the data, the compute, the alignment magic. But what happens after the weights are frozen and millions of users start hammering it with prompts? That's inference, and it's a...

    Credit the people on this episode

  5. Back Next Week

    Oct 19, 202618 secAudio

    Back Next Week by Katie Malone

    Credit the people on this episode