←back to thread

469 points samuelstros | 3 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 #
socalgal2 ◴[] No.44998808[source]
I’m trying to learn jj. Both Gemini and ChatGPT gave me incorrect instructions 4 of 5 times

https://jj-vcs.github.io/jj/

replies(1): >>44999351 #
1. BeetleB ◴[] No.44999351[source]
That's because jj is relatively new, and constantly changing. The official tutorial is (by their own admission), out of date. People's blog posts are fairly different in what commands/usage they recommend, as well.

I know it, because I recently learned jj, with a lot of struggling.

If a human struggles learning it, I wouldn't expect LLMs to be much better.

replies(1): >>45001035 #
2. esafak ◴[] No.45001035[source]
That's ironic considering jj is supposed to make version control easier.
replies(1): >>45001613 #
3. BeetleB ◴[] No.45001613[source]
It does make it easier. Don't conflate documentation with the tool itself.