Hacker News new | ask | show | jobs
by gck1 106 days ago
Yeah, people seem to forget one of the L's in LLM stands for Language, and human language is likely the largest chunk in training data.

A cli that is well designed for humans is well designed for agents too. The only difference is that you shouldn't dump pages of content that can pollute context needlessly. But then again, you probably shouldn't be dumping pages of content for humans either.
2 comments
Smaug123 105 days ago
It's not obvious that human language is or should be the largest amount of training data. It's much easier to generate training data from computers than from humans, and having more training data is very valuable. In paticular, for example, one could imagine creating a vast number of debugging problems, with logs and associated command outputs, and training on them.
link
rkagerer 105 days ago
I also feel like it's just a matter of time until someone cracks the nut of making agents better understand GUI's and more adept at using them.

Is there progress happening in that trajectory?

link
Imustaskforhelp 105 days ago
> Is there progress happening in that trajectory?

There was a recent Hackernews post which had a novel approach about making agents interact with GUI/computer-use

https://news.ycombinator.com/item?id=47125014: The First Fully General Computer Action Model : https://si.inc/posts/fdm1/

Hope this helps

link