Comment by d_sem
3 days ago
This article left me wishing it was "How I'm using coding agents to do <x> task better"
I've been exploring AI for two years now. It's certainly upgraded itself from the toy classification to a basic utility. However, I increasingly run into its limitations and find reverting to pre-LLM ways of working more robust, faster, and more mentally sustainable.
Does someone have concrete examples of integrating LLM in a workflow that pushes state-of-the-art development practices & value creation further?
Mitchell's post from this morning: https://mitchellh.com/writing/non-trivial-vibing
My impression is we're still in the tinkering phase. The metrics are coming.
What metrics? We could never objectively measure productivity except in the macro economic sense, so what makes you think we'll be able to now?
There are best practices of a kind, and well known org structures that work for building software, at least as much as anything can. We'll have some best practice experience with LLM agents soon enough.