think again they're going aggressive enough. Imod that, you know, like you said, they they trained this on 10,500 Nvidia GB300s and they said it was the largest publicly documented RL run and they said quote with no sign of a plateau. So, you know, it it seems like this is just the beginning. Um Dave, you >> Yeah, please. >> Yeah, just quick on that. Yeah, pre-training has now become like a quarter of compute and RL is like two a third um half of compute. So, it will
Imod that, you know, like you said, they they trained this on 10,500 Nvidia GB300s and they said it was the largest publicly documented RL run and they said quote with no sign of a plateau.