Ideas & society2025 · shared on Hacker News
Digital Agent outperforms o1 by 15% – trained with new RL-variant similar to R1
Explore Digital Agent outperforms o1 by 15% – trained with new RL-variant similar to R1, its original source and Hacker News discussions. Discover community perspectives and save it to your reading list.
GO BEYOND THE ABSTRACT
The conversation around the idea.
Original Hacker News threads. Different perspectives, questions, and things worth thinking about.
Showing up to 100 related threads. A paper may appear in a comment rather than the original submission.
Ylet_tim_cook_ ·
Digital Agent outperforms o1 by 15% – trained with new RL-variant similar to R1
11 points0 comments