Linear Digressions

Better Know a Benchmark: Humanity's Last Exam 17/08/2026

A Scientific Deep Dive into Overconfident LLMs: Interview with Kaitlyn Zhou (Cornell) 10/08/2026

Reasoning Models: When LLMs Went Beyond Fancy Autocomplete 03/08/2026

Distillation, or, How to Steal a Model 27/07/2026

Invisible LLM Failures and AI Fluency with Chris Potts (Stanford) 21/07/2026

Interviewing the Linear Digressions Agents (The Agents Season, Episode 11) 28/06/2026

Agent Economics (The Agents Season, Episode 10) 22/06/2026

Agent Trust, Oversight and Control (The Agents Season, Episode 9) 15/06/2026

Many Agents, Many Problems (The Agents Season, Episode 8) 08/06/2026

How Do You Evaluate An AI Agent? (The Agents Season, Episode 7) 01/06/2026

AI Agent Failure Modes (The Agents Season, Episode 6) 26/05/2026

Agentic Planning (The Agents Season, Episode 5) 18/05/2026

Memory Management for AI Agents (The Agents Season, Episode 4) 11/05/2026

Lost in the Middle (The Agents Season, Episode 3) 04/05/2026

ReAct and Tool Usage (The Agents Season, Episode 2) 27/04/2026

What's an AI Agent? And Why Is that Hard to Define? (The Agents Season, Episode 1) 20/04/2026

Unfaithful Chains of Thought 13/04/2026

Benchmark Bank Heist 06/04/2026

Benchmarking AI Models 30/03/2026

The Hot Mess of AI (Mis-)Alignment 23/03/2026

Latest episodes of the podcast Linear Digressions