t55
Joined 3 years ago
Karma
896
Submissions
167
Member since
Aug 18
ML researcher
View on Hacker NewsRecent submissions
Comment · 3 months ago
what timelines do you have in mind
Comment · 1 year ago
that's a standard feature in cursor, windsurf, etc.
Comment · 1 year ago
this is what deepmind did 10 years ago lol
Comment · 1 year ago
For a 100k token context window; all those models are comparable though
gemini 2.5 pro shines for 200k+ tokens
Comment · 1 year ago
i didn't say they invented everything; in science you always stand on the shoulders of giants
i still think my original statement is fair
Comment · 1 year ago
yeah, RLVR is still nascent and hence there's lots of noise.
> How can these spurious rewards possibly work? Can we get similar gains on other models with broken rewards?
it's because in those cases, RLVR merely elicits the reasoning strategies already contained in the model through pre-training
this paper, which uses Reasoning gym, shows that you need to train for way longer than those papers you mentioned to actually uncover novel reasoning strategies: https://arxiv.org/abs/2505.24864