. It received 119 points and 20 comments.

Cool study, we definitely need more principled studies on the role of harnesses. I'd also say that there aren't too many benchmarks where the more complicated harnesses consistently outperform extremely simple agents. But I'm also biased, because I wrote 

 , which is probably the most minimal agent out there (it started as just 100 lines, all included), and it's used in a lot of benchmarks like DeepSWE, terminalbench, programbench (seems like it's still top of the ranking for TB3, but wasn't evaluated with the best models on TB4).

tech

This link was posted by [wek](https://news.ycombinator.com/user?id=wek) 2 hours ago on [HN](https://news.ycombinator.com/item?id=49753878). It received 119 points and 20 comments.

[Top comment](https://news.ycombinator.com/item?id=49755993) by [lieret](https://news.ycombinator.com/user?id=lieret):

> Cool study, we definitely need more principled studies on the role of harnesses. I'd also say that there aren't too many benchmarks where the more complicated harnesses consistently outperform extremely simple agents. But I'm also biased, because I wrote [https://github.com/swe-agent/mini-swe-agent/](https://github.com/swe-agent/mini-swe-agent/) , which is probably the most minimal agent out there (it started as just 100 lines, all included), and it's used in a lot of benchmarks like DeepSWE, terminalbench, programbench (seems like it's still top of the ranking for TB3, but wasn't evaluated with the best models on TB4).