All Episodes

Why Models Over-Edit Your Code, Meta Keystroke Surveillance, Interviewing Engineers in the AI Age

Is Claude Opus 4.7 Mythos Distilled, Running Qwen 3.6 Locally, and the AI-On-AI Arena

Anthropic Mythos & Project Glasswing, Recursive Improving Agents, and Your Parallel Agent Limit

Ep 20: Claude Code Source Leak, Emotion Concepts in LLMs, and Surprising Facts AIs Know About Us.

Ep 19: Thinking Fast Slow and Artificial, Meta's Trouble with Rogue Agents, and FOMO in the Age of AI

Ep 18: 8 Levels of AI Engineering, Meta AI Delays, and LLM Neuroanatomy

Ep 17: Slop Garbage Collection, Cleanroom Rewrites, and Will Claude Ruin our Teams?

Pentagon Anthropic Drama, Verified Spec-Driven Development, and Interview with Martin Alderson!

Convincing AI the Earth is Flat, Inference at 17k tokens/sec, and an Agile Manifesto for the Agentic Age?

Crabby Rathbun, Model Councils & Why You Want More Tech Debt

Episode 13: Pi Coding Agent, Dark Factories & the Furniture Makers of Carolina

Episode 12: The OpenClaw Saga, How AI Affects Programming Skills, and How Vibe Coding is Addictive like Gambling

Episode 11: AI Fluency Pyramid, Unrolling the Codex Agent Loop, and Claude Code's Secret Swarm Mode

Episode 10: There's a New Sherif in the Gas Town of AI Software Development

Episode 9: Chinese Models 7 Months Behind US Labs, Token Efficient Languages, and LLM Problems Observed in Humans

Episode 8: AI Acquisitions, Everyone's a Staff Engineer Now, and Building a Technical Writing Agent

Episode 7: Project Vend Update, Hallucinating Neurons, and Year End Reflections

Episode 6: GPT 5.2, Claude Skills, and Hacker Hall of Fame

Episode 5: How Anthropic Engineers use AI, Spec Driven Development, and LLM Psychological Profiles

Episode 4: Open AI Code Red, TPU vs GPU and More Autonomous Coding Agents

Claude Opus 4.5, Olmo 3, and a Paper on Diffusion + Auto Regression

It's Gemini 3 Week! And How to Persuade an LLM to Call You a Jerk

AI Benchmarks, Tech Radar, and Limits of Current LLM Architectures