DeepScaleR: Surpassing O1-Preview with a 1.5B Model by Scaling RL

Re:DeepScaleR: Surpassing O1-Preview with a 1.5B Model by Sc... by numba888 on Tuesday February 11, 2025 @07:10PM (#43020055)

o1 is more than just math solver. And you cannot possibly train that much in a small model.

However smaller specialized models looks to be the right way to handle world's complexity. Sort of mixture of experts on one level above. Orchestrating them will be another problem. Possible solution is generalists model "to rule them all".

[ Parent | on HN ]

Re:DeepScaleR: Surpassing O1-Preview with a 1.5B Model by Sc... by mdp2021 on Tuesday February 11, 2025 @07:29PM (#43020237)

Have you considered the very practical importance of running specialized models for specialized tasks on common hardware (maybe a couple of CPU cores in a couple GB of RAM)?

[ Parent | on HN ]

Re:DeepScaleR: Surpassing O1-Preview with a 1.5B Model by Sc... by numba888 on Wednesday February 12, 2025 @03:00AM (#43022989)

Small models are just tools. Even many of them will make only a toolset. They don't evolve in AGI by themselves. But putting them together in a structure (brain) may result in something close. Like big smart calculator. It takes more to create a 'character' similar to, say, terminator.

[ Parent | on HN ]