You have to learn to use your tools, not try whatever intuitively made sense to you at first (expecting the tool to do all the work) and then whining on Hacker News when it doesn’t work out for you.
I'm thinking the issue is probably that LLMs/harnesses are too easy to use? It crossed the thin line between magic and tooling and blur the mental model. If Claude Code were as hard to use as, say, ComfyUI, perhaps there would be less programmers having absurd expectation of it.
The parent commenter was trying to learn how to use the tool. Perhaps he could've used it better, but like you said, what may have worked was not necessarily the intuitive approach.
The parent comment also changed his approach, and AI worked for him to test out changes. That's not expecting the tool to do all the work, he's actually agreeing with you that "expecting the tool to do all the work" is a misstep.
> others dumping their raw AI output at me
Sheesh.