News for hackers. Stuff that matters.
Re:An Empirical Study of Harness Design for Coding Agents by 0xbadcafebee on Friday September 18, 2026 @10:33AM (#49754983)
It might be 'duh' but it means we need a formal list of what each model is good at, and to pick or change harnesses to closer fit the model. Like an llm recipe book. Not just for remote models, but also local ones where how you run the model is critical too.

There are no comments on this comment yet.