R-one
3 statements across 3 episodes · 2 bullish · 1 bearish · 3 people on the record · first statement Feb 13, 2025 by Aymeric (Emmerich) · across every show →
Everything said about R-one, oldest first
Feb 13, 2025 positive
Apr 29, 2025 bullish
Jin: RL enables models to surpass expert labelers and develop self-direction
“The model outperforming expert labelers is, is possible. The model learning, like, self-direction is, like, expected. And yeah, we've seen, like, kind of cool emergent behaviors with, like, you know, like, O-one, O-three, R-one, kind of, like, these, like, thi…”
May 9, 2025 negative
No open-source model currently matches OpenAI's general agent capabilities
“There really isn't currently an open source model that behaves in the way that these models do. We have things like R-one, which are great at kind of the single-term math and code reasoning problems. But they are not in the general purpose agents world yet.”