reinforcement learning

“Because when something really big happens with, say, reinforcement learning, which is an area mostly attributed to research today, it's going to happen really quickly.”

“The whole market is shifting to reinforcement learning, right? You're already seeing this with O-one, O-three, the deep seek models. And as a result, I think we're going to see really, really powerful models in specific domains that can reason extremely well.”

“You know, it's RL, for example, is I would say the biggest breakthrough of the last year and a half call it.”

“RL, to shape the behavior of models, to get them to be social creatures, that we have no idea how to do. I mean, I don't know if you have children, but like shaping their behaviors, you know, the number of times you can repeat the same thing, and still they do…”

“Now, you know, where we're maybe getting a little bit ahead is thinking that just RL out of the box is gonna give us AGI. That part, a lot less so. You know, if you look at the curve of progress, RL is terribly inefficient, and so the amount of signal you need…”

“Oh, I'm still super bullish on RL in that, like, the concept itself is so fundamental. You know, this idea of training through a system of rewards, of indicating what's valuable and what's not valuable through numerical values, like, that is so fundamental. It…”

“It's coming down, especially in domains where we have good reward functions.”

“Today, the dominant paradigm is reinforcement learning.”