Prime Intellect

“Using more tool calls, searching the web more, gives you a nice scaling curve where you get better answers by putting in more effort, by, like, spending more time browsing the internet, essentially.”

“And the most, one of the most promising ways, I think, towards doing this is having the reward models also be able to answer harder questions by themselves being reasoning models.”

“I never really got to the point where I found it was helpful for a thing that was like a large existing code base. But if it's like, hey, I want to like cook something up in a few hours for fun. Pretty good at that. But these become messy and they become hard …”

“So it seems like artificially truncating the thought is actually like fine. Like the model can, even if like it got cut off mid-sentence with an injected like think token, these are smart enough models that they can kind of finish with the best that they got f…”

“The thing that's going to make the next wave of stuff be powerful is just, like, everyone wants better agents. Everyone wants models that can, like, go off and do stuff. And, like, reasoning was kind of, like, a precursor to that a little bit.”