Systems engineer Yacine argues developers should train RL from scratch as Nemotron 3 Ultra steps cost $1,000 each

@yacineMTB @giffmana It’s like asking Claude to control cart pole directly. Like bro no

@giffmana there is always money in the gpu stand tho

I mean, it's one RL step, Michael. What could it cost?

@giffmana The rare scenario where Arrested Development's 'What could it cost?' is completely sincere.

@giffmana this is the Arrested Development reference i was looking for today

@shakoistsLog @giffmana the tasks that really matter don't benefit from language priors!

@yacineMTB @giffmana You can do a lot more, a lot faster with a 3-4 layer NN.

@giffmana My take: post-training cost is the next real filter, not model access. When a meaningful RL run is hundreds of $1K steps, only teams with a tight reward signal can afford to iterate. The bottleneck stops being compute. It becomes knowing exactly what to reward.