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 buyucu on Tuesday February 11, 2025 @04:37PM (#43018683)

'Count the letter Rs in the word strawberry' is probably in all training sets by now.

[ Parent | on HN ]

Re:DeepScaleR: Surpassing O1-Preview with a 1.5B Model by Sc... by swiftcoder on Tuesday February 11, 2025 @04:46PM (#43018759)

And yet many models still stumble with it

[ Parent | on HN ]

Re:DeepScaleR: Surpassing O1-Preview with a 1.5B Model by Sc... by notjulianjaynes on Wednesday February 12, 2025 @05:47PM (#43030611)

I sometimes do the strawberry question immediately followed by "How many Rs in "bookkeeper?"

[ Parent | on HN ]