←back to thread

413 points martinald | 1 comments | | HN request time: 0.2s | source
Show context
jdmoreira ◴[] No.46197142[source]
I must be holding wrong then because I do use Claude Code all the time and I do think its quite impressive… still I cant see where the productivity gains go nor am I even sure they exist (they might, I just cant tell for sure!)
replies(1): >>46198489 #
hurturue ◴[] No.46198489[source]
if you back and forth with the model, and discuss/approve every change it does, that's the problem.

you need to give it a bigish thing so it can work 15 min on it. and in those 15 min you prepare the next one(s)

replies(1): >>46198517 #
jdmoreira ◴[] No.46198517[source]
Sure. But am I supposed to still understand that code at some point? Am I supposed to ask other team members to review and approve that code as if I had written it?

I'm still trying to ship quality work by the same standards I had 3 or 5 years ago.

replies(1): >>46199125 #
hurturue ◴[] No.46199125[source]
when compiler appeared assembly programmers would complain all day how ugly and inneficient the generated code was

if you want to get the productivity gain you need to figure out how to solve the code review problem

replies(3): >>46201414 #>>46202286 #>>46204539 #
1. christophilus ◴[] No.46204539[source]
But did the generated code do what you told it to do and was it deterministic? LLMs aren’t the same at all. That metaphor doesn’t work.