News for hackers. Stuff that matters.
Re:Show HN: Claude Code workflow: PRDs → GitHub Issues → par... by afro88 on Wednesday August 20, 2025 @06:51PM (#44967337)
No one mentioned anything about "people who can't program at all" until your comment. Up until then the discussion was about using LLMs for production ready code. It's a given that people working on production systems know how to program.
Re:Show HN: Claude Code workflow: PRDs → GitHub Issues → par... by stavros on Wednesday August 20, 2025 @06:54PM (#44967359)
That is what "auto-edits" (in the first comment) and "vibe coding" (in the second comment) mean.
Re:Show HN: Claude Code workflow: PRDs → GitHub Issues → par... by afro88 on Saturday August 23, 2025 @06:06AM (#44994796)
The bit you're missing is that people who can program also use "auto edits" and "vibe coding" when it fits the problem at hand
Re:Show HN: Claude Code workflow: PRDs → GitHub Issues → par... by stavros on Saturday August 23, 2025 @06:25AM (#44994882)
As someone who can program and used vibe coding, when they use vibe coding and don't look at the output, how do they ensure errors don't compound?
Re:Show HN: Claude Code workflow: PRDs → GitHub Issues → par... by afro88 on Saturday August 23, 2025 @11:55PM (#45001237)
I'll give you that - you can't vibe code, not look at the output, and push to main of a production codebase. Same as writing code normally.

But you can vibe code and auto-edit your way to a good PR. But you're reviewing the code being output when the agent finishes each task. Maybe that's not pure vibe coding?

Re:Show HN: Claude Code workflow: PRDs → GitHub Issues → par... by stavros on Sunday August 24, 2025 @04:07AM (#45002320)
The definition of vibe coding is that you aren't looking at the code. That's what's never worked for me.