{"type":"rich","version":"1.0","provider_name":"Transistor","provider_url":"https://transistor.fm","author_name":"The AI Cookbook Show by Malcolm Werchota","title":"#133 - The Harness Is The Work: Why The Chef Isn't The Point","html":"","width":"100%","height":180,"duration":1905,"description":"Title: #133 - The Harness Is The Work: Why The Chef Isn't The Point\n\nThere is a GitHub repository that was released a few days ago that is, right now, the fastest-growing repo on GitHub by velocity. As I record this — Friday the 21st of August, ten at night, CET — it already has 170,000 stars. It's called DeepSeek Harness. And two days after DeepSeek released theirs, OpenAI released one too.\n\nHere's the question I asked myself before I understood any of this: if I already have Claude Code or Codex, and I can already tell it \"read these files, make a plan, run the tests, fix what's broken\" — why the hell do I need a harness? Isn't a harness just a very long prompt with a fancy name?\n\nThen it clicked. The model is not the company. The model is the brilliant chef. Claude can be an incredible chef. GPT can be an incredible chef. DeepSeek can be an incredible chef. Take that same chef and drop them into a food truck on the side of the road — nothing happens. Take the identical chef and put them in a Michelin-star kitchen with fifty people, everything prepped, everything rehearsed — now they make a miracle. The harness is the kitchen.\n\n📍 What this episode covers: what a harness actually is (chef, kitchen, hygiene rules); why it suddenly matters (DeepSeek and OpenAI shipping theirs two days apart); exactly how to prompt Claude Code or Codex to build you one; three real patterns where harnesses work (and where they don't); the honest answer on whether a harness costs you more tokens; and the harness that built this very episode — including the two places it caught its own builder being wrong.\n\n🍳 Same brain, different kitchen. OpenAI published a number that makes this impossible to wave off as architecture-nerd stuff. Same model — GPT-5.6 Sol. Standard harness on ARC-AGI-3: 13.3%. Turn on OpenAI's harness — retained reasoning, compaction: 38.3%. Nearly three times better. And it used roughly six times fewer tokens doing it. The chef didn't change. The kitchen did.\n\n🔧 How...","thumbnail_url":"https://img.transistorcdn.com/K89WOul5lFP6eyTkepgc48DwnmOLDjvzPf-VdoMUwqc/rs:fill:0:0:1/w:400/h:400/q:60/mb:500000/aHR0cHM6Ly9pbWct/dXBsb2FkLXByb2R1/Y3Rpb24udHJhbnNp/c3Rvci5mbS84Y2I2/YTZiNWNmNGE5NmYy/NzE4ZTAyMTYxYjNh/ZmM5Zi5qcGc.webp","thumbnail_width":300,"thumbnail_height":300}