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 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 distillation happened, why some models occasionally introduce themselves as "Claude," and a surprisingly old idea: a 2015 paper by Geoffrey Hinton, Jeff Dean, and Oriol Vinyals on distilling knowledge using the full probability distribution over a model's outputs — not just its single most likely answer — and what that "soft label" approach captures about how a model relates concepts to each other.

Denne episoden er hentet fra en åpen RSS-feed og er ikke publisert av Podme. Den kan derfor inneholde annonser.

Episoder(320)

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 Aug 23min

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* ac...

10 Aug 33min

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 Aug 25min

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 Jul 41min

Still summer break: back next week

Still summer break: back next week by Katie Malone

13 Jul 25s

Summer break: back soon

Summer break: back soon by Katie Malone

6 Jul 36s

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 Jun 37min