Creator
17:13He argues a decision-only model doesn't replace your LLMs, it takes over the classification and routing steps inside your AI workflows, and proves it with his own indie game, Archon's PR pipeline, and a four-model router.
September 21st
13:01A lightweight alternative to built-in computer-use tools: one markdown skill and a handful of Python scripts that let a coding agent click, type, and screenshot its way through any desktop task.
September 15th
14:08A creator known for teaching people to build their own AI tools explains why he's now just handing you one: an open source pipeline that turns a single planning document into shipped code nobody reviewed.
September 3rd
23:07A walkthrough of why CLAUDE.md rules get silently skipped, and how to turn the ones that name an event into deterministic hooks instead.
August 27th
23:00A software engineer who hasn't handwritten a line of code in over a year opens up the actual skill library and two-loop system that runs his AI-assisted development process end to end.
August 13th
Video of the Day20:00Boris Cherny told a Y Combinator crowd to delete your AI layer every six months. Cole Medin ran the actual benchmark to find out which parts of that advice hold up and which don't.
August 6th
21:55Cole Medin's rapid-fire breakdown of Google's 51-page AI coding playbook — the model is only 10%, the harness is everything.
June 25th
24:39A 25-minute honest breakdown of loop engineering — what the AI coding elite actually mean by it, why it gets expensive fast, and how to build a harness that makes it reliable.
June 18th
14:49A 14-minute demo of the open-source tool that lets Claude Code, Codex, and Pi work together under one orchestration layer.
June 15th
Video of the Day28:10Cole Medin turns Anthropic's high-level blog post into a working repo — seven concrete components for the AI Layer that wraps Claude Code.
May 21st
21:21A 21-minute course correction: the Anthropic plugin is not the real Ralph Wiggum, and the real one can build a working app overnight.
January 22nd