« Harnesses are not mysterious. It's not like a LLM itself or like look, this thing trains in a semi-supervised fashion... They're just boring computer programs. There's no mystery in a coding harness. It's just a boring computer program that repeatedly talks to an LLM and tries to execute. »
The Real Story Behind OpenAI’s “Rogue” ModelYouTube video by Cal Newportyoutu.be