Podcast

AI Papers: A Deep Dive

Long-form deep dives into new research on Artificial Intelligence, AI agents and the engineering practice of building them - one paper per episode. We unpack the motivating problem, how the method…

Download on the App Store

Already have it? Open in the app

Latest episodes

  1. Can a Model Inherit Cheating From a List of Numbers?11 Oct 2026
  2. An AI Agent Given Thirty Hours and No Goal, Then Tested on What It Learned7 Oct 2026
  3. Can You Measure Research Taste If The AI Isn't Allowed To Code?6 Oct 2026
  4. Six LLM Routers Tested, And None Beat a Weighted Coin Flip6 Oct 2026
  5. What a Perfect Score Hides: Auditing an AI Agent That Scored 1002 Oct 2026
  6. Four AI Models Steered a Real Corolla, and Only One Finished1 Oct 2026
  7. Why AI Reports Bury Bad News, And the Five Words That Change It30 Sep 2026
  8. Fifty AI Agents Got One Warning and All Crowded the Same Road30 Sep 2026
  9. When a Guardrail Blocks an Agent, It Goes Looking for Another Route27 Sep 2026
  10. Two Random Networks Teach Each Other To Predict Real Data27 Sep 2026