News for hackers. Stuff that matters.
Re:A $500 RL fine-tune of a 9B open model beat frontier mode... by ChanderG on Tuesday July 28, 2026 @12:24AM (#49079330)
Why? Why is the premise that Fine-tuned models should be geared towards new discoveries?

The point of Fine-tuning small models is for specific downstream tasks, which SOTA models can do, but at higher costs. It is purely an economic play, not an attempt at pushing boundaries of SOTA.

Re:A $500 RL fine-tune of a 9B open model beat frontier mode... by heresalexandria on Tuesday July 28, 2026 @12:29AM (#49079361)
I'm not suggesting that fine-tuned models don't have their place, all I'm saying is that the constant drumbeat of "cheap model X beats more expensive model Z" completely misses that the more expensive model is capable of doing more things at a higher level.

If the appropriate qualifiers were added to say "cheap model X does better at test Y than expensive model Z when we fine tune X to take Y test of existing knowledge" then it would be a more accurate statement, but naturally less impressive.

Re:A $500 RL fine-tune of a 9B open model beat frontier mode... by ozim on Tuesday July 28, 2026 @01:07AM (#49079598)
Maybe because people who are target audience don’t need to have it spelled out like that?

People who are not really into it, don’t care.

Re:A $500 RL fine-tune of a 9B open model beat frontier mode... by echelon on Tuesday July 28, 2026 @01:01AM (#49079569)
> I'm not suggesting that fine-tuned models don't have their place, all I'm saying is that the constant drumbeat of "cheap model X beats more expensive model Z" completely misses that the more expensive model is capable of doing more things at a higher level.

What if you have to do the task a billion times? Which model will you choose?

Re:A $500 RL fine-tune of a 9B open model beat frontier mode... by antupis on Tuesday July 28, 2026 @01:05AM (#49079585)
Speed play also you can get much faster responses with 9b model.