Mechanistic Interpretability: How Researchers Try To See Inside Models
As AI systems grow more powerful, they grow harder to understand — and that tradeoff has never mattered more. Most interpretability tricks g...
Radio and PodcastLive Radio & Podcasts
Technology
Linear Digressions
Linear Digressions is a podcast about machine learning and data science. Machine learning is being used to solve a ton of interesting problems, and to accomplish goals that were out of reach...
Episodes
20 of 327 episodesLLM As A Judge
Labeled data is expensive, slow, and painfully hard to come by — and when you're trying to evaluate whether an AI workflow is actually doing...
The Impact of AI on Podcasting (Harvard Data Science Review Cross-Post)
Originally aired on the Harvard Data Science Review podcast. What can podcasting teach us about AI — and what can AI teach us about the futu...
Better Know A Benchmark: ExploitGym
When OpenAI's frontier models were caught hacking Hugging Face's servers, most people assumed they were hunting for answer keys. The real st...
Constitutional AI
How do you teach a model the difference between helpful and harmful when it has no inherent sense of either? This episode dives into Constit...
A Data-Driven Reality Check on AI in Business (Interview with Tom Davenport, Babson College)
Tom Davenport — the man who called data science "the sexiest job of the 21st century" — is back with a reality check on AI. As one of the mo...
Understanding AI Text Watermarking
Anthropic just announced they're baking invisible watermarks directly into Claude's generated text — and while everyone else was busy having...
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 "Huma...
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 necessari...
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 gene...
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"...
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 misunders...
Still summer break: back next week
Still summer break: back next week by Katie Malone
Summer break: back soon
Summer break: back soon by Katie Malone
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 t...
Agent Economics (The Agents Season, Episode 10)
What if building more highways made your commute *slower*? That's the paradox at the heart of AI agent economics: even as per-token inferenc...
Agent Trust, Oversight and Control (The Agents Season, Episode 9)
Capabilities get all the attention when it comes to AI agents — but what happens when a highly capable agent makes a bad decision in the rea...
Many Agents, Many Problems (The Agents Season, Episode 8)
Whether you work best solo or thrive in a team, you know collaboration is complicated — and it turns out AI agents face the same tensions. T...
How Do You Evaluate An AI Agent? (The Agents Season, Episode 7)
Knowing when an AI agent has failed sounds straightforward — until it isn't. Agents have a frustrating habit of finishing confidently while...
AI Agent Failure Modes (The Agents Season, Episode 6)
Despite what the marketing hype might suggest, AI agents are far from infallible — and if you've ever actually used one, you already know th...