←back to thread

469 points samuelstros | 1 comments | | HN request time: 0s | source
Show context
diego_sandoval ◴[] No.44998676[source]
It shocks me when people say that LLMs don't make them more productive, because my experience has been the complete opposite, especially with Claude Code.

Either I'm worse than then at programming, to the point that I find an LLM useful and they don't, or they don't know how to use LLMs for coding.

replies(17): >>44998684 #>>44998692 #>>44998700 #>>44998702 #>>44998714 #>>44998723 #>>44998787 #>>44998796 #>>44998808 #>>44998811 #>>44998815 #>>44998918 #>>44998938 #>>44999026 #>>44999031 #>>45000201 #>>45001208 #
1. breuleux ◴[] No.45000201[source]
Speaking for myself, LLMs are reasonably good at writing tests or adapting existing structures, but they are not very good at doing what I actually want to do (design, novelty, trying to figure out the very best way to do a thing). I gain some productivity from the reduction of drudgery, but that's never been much of a bottleneck to begin with.

The thing is, a lot of the code that people write is cookie-cutter stuff. Possibly the entirety of frontend development. It's not copy-paste per se, but it is porting and adapting common patterns on differently-shaped data. It's pseudo-copy-paste, and of course AI's going to be good at it, this is its whole schtick. But it's not, like, interesting coding.