News for hackers. Stuff that matters.
Re:In 27,280 coding agent runs, 64% of inference spend went ... by krawczstef on Tuesday November 17, 2026 @10:48PM (#50541623)
There's no IP in a harness, and they don't matter that much.

Harnesses simply make different choices around certain context engineering things, what they name tools, how they compact, their system prompt, etc.

So it's not surprising that they work "better" for some models than others, but I'd bet that if you made each harness have same system prompt and tool names, the variance would shrink further...

So I would say know what you're optimizing for and construct the harness you need for it instead (it's just a while loop with an llm call and function calling after all) ...

There are no comments on this comment yet.