logoalt Hacker News

theshrike79yesterday at 5:01 PM5 repliesview on HN

Should be possible with optimised models, just drop all "generic" stuff and focus on coding performance.

There's no reason for a coding model to contain all of ao3 and wikipedia =)


Replies

jstummbilligyesterday at 6:31 PM

There is: It works (even if we can't explain why right now).

If we knew how to create a SOTA coding model by just putting coding stuff in there, that is how we would build SOTA coding models.

noveltyaccountyesterday at 5:29 PM

I think I like coding models that know a lot about the world. They can disambiguate my requirements and build better products.

show 1 reply
moffkalastyesterday at 6:22 PM

That's what Meta thought initially too, training codellama and chat llama separately, and then they realized they're idiots and that adding the other half of data vastly improves both models. As long as it's quality data, more of it doesn't do harm.

Besides, programming is far from just knowing how to autocomplete syntax, you need a model that's proficient in the fields that the automation is placed in, otherwise they'll be no help in actually automating it.

show 1 reply
MarsIronPIyesterday at 5:34 PM

But... but... I need my coding model to be able to write fanfiction in the comments...

wongarsuyesterday at 10:25 PM

Now I wonder how strong the correlation between coding performance and ao3 knowledge is in human programmers. Maybe we are on to something here /s