Linear Digressions

Publicly listed emails

hello@lineardigressions.com

Looking for the right person? Join Podseeker to find direct host and producer contacts and manage your podcast outreach.

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

August 10, 2026

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 lov...

Reasoning Models: When LLMs Went Beyond Fancy Autocomplete

August 03, 2026

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 final answer, exploring how the internal reasoning process works. Are these models genuinely "thinking," or is something else going on under the hood?

Distillation, or, How to Steal a Model

July 27, 2026

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 this — making lighter, faster, more focused models for specific tasks, and the more contentious use case of effectively copying a rival's flagship model by hammering its API with questions (with a callback to the old Bing/Google search controversy). They also get into why it's so hard to prove d...