News for hackers. Stuff that matters.

A comment on Supervised fine tuning on curated data is reinforcement learning.

Re:Supervised fine tuning on curated data is reinforcement l... by stolencode on Tuesday July 29, 2025 @09:40PM (#44730207)
> For example achieving 66.7% on the AIME 2024 dataset.

We worked _really_ hard, burned _tons_ of cash, and we're proud of our D- output. No wonder there are more papers published than actual work being done.

[ Parent | on HN ]
Re:Supervised fine tuning on curated data is reinforcement l... by supermdguy on Tuesday July 29, 2025 @10:03PM (#44730310)
That corresponds to a 10/15, which is actually really good (median is around 6)

https://artofproblemsolving.com/wiki/index.php/AMC_historica...

[ Parent | on HN ]
Re:Supervised fine tuning on curated data is reinforcement l... by stolencode on Wednesday July 30, 2025 @02:14AM (#44731296)
Isn't the test taken only by students under the age of 12?

Meanwhile the model is trained on these specific types of problems, does not have an apparent time or resource limit, and does not have to take the test in a proctored environment.

It's D- work. Compared to a 12 year old, okay, maybe it's B+. Is this really the point you wanted to make?

[ Parent | on HN ]
Re:Supervised fine tuning on curated data is reinforcement l... by jpcompartir on Wednesday July 30, 2025 @04:39AM (#44732039)
This is a nonsense critique.

Modest results are worth publishing, as are bad results.

[ Parent | on HN ]