HackerTrans
TopNewTrendsCommentsPastAskShowJobs

axod

no profile record

Submissions

Rewriting stale OSS projects using LLM

loopholelabs.io
3 points·by axod·mês passado·0 comments

comments

axod
·mês passado·discuss
That's exactly how it was in the 90s really.
axod
·mês passado·discuss
Maybe you want to byte align some data, or pack to a certain size but keep compat. I think they're going to be rare cases, but I can see it being used.
axod
·mês passado·discuss
I don't think you can ignore it. It's the biggest change to tech in 30 years I'd say.

"I'm tired of all this internet talk" in 1990s?
axod
·mês passado·discuss
> ...are poor design choices that humans wouldn’t write.

They certainly do in my experience. Maybe you've been lucky and haven't worked with really messy programmers.
axod
·mês passado·discuss
I don't think this approach is wise.

Concentrate on code quality, and whether it does what it needs to do. Not whether it was written by AI or not.
axod
·mês passado·discuss
That's like saying ban IDEs. Or ban search engines. LLM is just a tool that humans use to create things.
axod
·mês passado·discuss
Fun little game, but I think the questions jump context so much it's a little unrepresentative. It might be better to group things into "packs", which have more real-world representative structure to them. For example, lots of "editing something.js" file permission requests, and then an "npm publish" is far more normal, and it's more of a risk, if you're used to pressing Y lots and then suddenly out of the blue...
axod
·mês passado·discuss
And so the cycle will continue. Always a shame when languages cave like this and add extra unnecessary complexity and error prone hard to parse syntax.

It'll be interesting to see the next language that comes along rejecting bloat in favor of simplicity, and then we can all start again.