News for hackers. Stuff that matters.

A comment on A $500 RL fine-tune of a 9B open model beat frontier models on catalog review. Parent comment

Re:A $500 RL fine-tune of a 9B open model beat frontier mode... by dineshdb on Tuesday July 28, 2026 @09:57AM (#49083981)
I took a look at the codebase and found that this is just pattern matching. There is no any novelty here. It looks good for knowledge-base retrieval system, but other than that, this is just nothing more than a pattern-matcher.

Would love to be proven wrong with future updates.

[ Parent | on HN ]
Re:A $500 RL fine-tune of a 9B open model beat frontier mode... by vkaku on Tuesday July 28, 2026 @10:08PM (#49092649)
Sure. Like throwing money at problems is novel.

Why don't you go and actually build something novel? People need to understand better how current models work, and if retrieval indeed solves 99% of the problems people care about, then those other models aren't doing anything super novel either.

I'm not arguing here: The code is out there, data is out there. Do better if you know something actually better. Thanks!

[ Parent | on HN ]