Generative AI coding tools and agents do not work for me

The author makes the excellent point that LLM-coding still has a human bottleneck at the code review point - regardless of whether the issue at hand is fixed or not.

Leaving aside the fact that this isn't an LLM problem; we've always had tech debt due to cowboy devs and weak management or "commercial imperatives":

I'd be interested to know if any of the existing LLM ELO style leaderboards mark for code quality in addition to issue fixing?

The former seems a particularly useful benchmark as they become more powerful in surface abilities.

> Leaving aside the fact that this isn't an LLM problem; we've always had tech debt due to cowboy devs and weak management or "commercial imperatives":

But this is one of the core problems with LLM coding, right? It accelerates an already broken model of software development (worse is better) rather than trying to help fix it.

Possibly so - which is why I think research towards quality rather than just test-passing would be a significant benefit.