Linear Digressions

00:29:21

Mechanistic Interpretability: How Researchers Try To...

Linear Digressions ·

2026/10/05

As AI systems grow more powerful, they grow harder to understand — and that tradeoff has never mattered more. Most interpretability tricks give us approximations from the outside, but mechanistic interpretability takes a different approach: cracking open the model itself to trace *why* it behaves the way it does. This episode digs into what makes mechanistic interpretability fundamentally different from other explainability methods, and why it might be the most promising path toward actually

en

00:30:12

LLM As A Judge

Linear Digressions ·

2026/09/28

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 what you want, the problem gets even messier. How do you judge whether a chatbot response was helpful, honest, or hallucination-free at scale? This episode digs into using LLMs as judges: letting the models themselves evaluate the quality of AI outputs, from simple chat exchanges all the way to complex multi-step agent behavior.

en

00:31:57

Constitutional AI

Linear Digressions ·

2026/09/07

How do you teach a model the difference between helpful and harmful when it has no inherent sense of either? This episode dives into Constitutional AI, Anthropic's framework for training AI systems to be both useful and safe by giving them an explicit set of principles to reason from. It's a fascinating look at how alignment research is evolving beyond simple human feedback — and what it means to give an AI something like a conscience.Links: Anthropic, "Constitutional AI: Harmlessness from AI

en

00:23:21

Better Know a Benchmark: Humanity's Last Exam

Linear Digressions ·

2026/08/17

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 collaboration — hundreds of contributors, thousands of fiendishly hard questions spanning a wild range of domains. In this Better Know a Benchmark installment, we unpack what HLE is actually testing, how it was built, and what it means when a model finally starts cracking it.

en

00:23:38

Distillation, or, How to Steal a Model

Linear Digressions ·

2026/07/27

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

en

00:24:24

Agent Economics (The Agents Season, Episode 10)

Linear Digressions ·

2026/06/22

What if building more highways made your commute *slower*? That's the paradox at the heart of AI agent economics: even as per-token inference costs have plummeted dramatically over the past two years, total LLM spending keeps climbing. Drawing on a surprising lesson from Robert Moses's mid-century New York infrastructure projects, this episode unpacks why cheaper compute doesn't necessarily mean cheaper AI — and what's really driving the economics of running agents at scale.

en

00:31:45

How Do You Evaluate An AI Agent? (The Agents Season,...

Linear Digressions ·

2026/06/01

Knowing when an AI agent has failed sounds straightforward — until it isn't. Agents have a frustrating habit of finishing confidently while quietly doing the wrong thing, or looping endlessly without ever crashing in an obvious way. This episode tackles one of the thorniest problems in the agentic world: evaluation. If failure is hard to see, how do you measure it systematically? And how do you know when your agent is actually working?

en

00:24:00

Agentic Planning (The Agents Season, Episode 5)

Linear Digressions ·

2026/05/18

When tackling a complex, multi-step task, even the smartest AI agent can fail without a solid game plan. This episode dives into the research around agentic planning — how agents move beyond simply reacting to what's in front of them and instead model a path forward, explore different routes, and course-correct when things go sideways. It's a subtler problem than memory, and a fascinating one: can an agent actually *think ahead*? Tune in to find out what the research says.

en

00:24:41

Memory Management for AI Agents (The Agents Season,...

Linear Digressions ·

2026/05/10

Context windows are powerful — but finite, and surprisingly easy to overwhelm. When an AI agent is tackling a long, complex task, the information it needs has to fit inside that limited real estate, and research shows that anything buried in the middle tends to quietly disappear. So how do you design a system that actually *remembers* what matters? This episode digs into memory management for AI agents, from foundational computing concepts to practical lessons from tools like Claude

en

00:19:44

Lost in the Middle (The Agents Season, Episode 3)

Linear Digressions ·

2026/05/04

Just like a memorable talk lives or dies by its opening and closing, LLMs have a surprisingly similar quirk: they pay close attention to what's at the beginning and end of their context window — and kind of zone out in the middle. This "lost in the middle" phenomenon has real consequences for anyone building AI agents that rely on long-context reasoning. In this episode we dig into the research behind how (and how poorly) models actually use the information you feed them, and what it means for the

en

00:23:41

ReAct and Tool Usage (The Agents Season, Episode 2)

Linear Digressions ·

2026/04/27

Before 2022, there was a wall between AI and the real world — models could reason impressively, but couldn't look anything up, run code, or check whether anything they said was actually true. This episode traces the moment that wall came down, through two landmark papers: ReAct, which showed what happens when you interleave reasoning and action in a loop, and Toolformer, which taught models to decide *for themselves* when to reach for a tool. Plus: what MCP actually is, and why a hobbyist project

en

00:29:55

Benchmarking AI Models

Linear Digressions ·

2026/03/30

How do you know if a new AI model is actually better than the last one? It turns out answering that question is a lot messier than it sounds. This week we dig into the world of LLM benchmarks — the standardized tests used to compare models — exploring two canonical examples: MMLU, a 14,000-question multiple choice gauntlet spanning medicine, law, and philosophy, and SWE-bench, which throws real GitHub bugs at models to see if they can fix them. Along the way: Goodhart's Law, data contamination,

en

00:22:32

The Hot Mess of AI (Mis-)Alignment

Linear Digressions ·

2026/03/23

The paperclip maximizer — the classic AI doom scenario where a hyper-competent machine single-mindedly converts the universe into office supplies — might not be the AI risk we should actually lose sleep over. New research from Anthropic's AI safety division suggests misaligned AI looks less like an evil genius and more like a distracted wanderer who gets sidetracked reading French poetry instead of, say, managing a nuclear power plant. This week we dig into a fascinating paper reframing AI

en

00:19:17

The Bitter Lesson

Linear Digressions ·

2026/03/15

Every AI builder knows the anxiety: you spend months engineering prompts, tuning pipelines, and chaining calls together — then a new model drops and half your work evaporates overnight. It turns out researchers have been wrestling with this exact dynamic for 30 years, and they keep arriving at the same uncomfortable answer. That answer is called the Bitter Lesson — and understanding it might be the most important thing you can do for whatever you're building right now. From Deep Blue to AlexNet to

en

00:17:14

It's RAG time: Retrieval-Augmented Generation

Linear Digressions ·

2026/03/02

Today we are going to talk about the feature with the worst acronym in generative AI: RAG, or Retrieval Augmented Generation. If you've ever used something like "Chat with My Docs," if you have an internal AI chatbot that has access to your company's documents, or you've created one yourself on some kind of personal project and uploaded a bunch of documents for the AI to use — you have encountered RAG, whether you know it or not.It's an extremely effective technique. Works super well for taking

en

All Episodes

Similar Podcasts

Lead With AI

Tamara Nall

Tech Guide

Stephen Fenech

The ITSPmagazine Podcast

ITSPmagazine, Sean Martin, Marco Ciappelli

The Good Tech Companies

HackerNoon

ev.news

Martyn Lee