This is not just PR and is very interesting. However, in my view, (and from a quick read of the paper) this is actually a very classical method in applied math work: - Build a complex intractable mathematical model…
No examples of before/after? Maybe I missed something.
What does this add to the conversation?
Some info that may be missing: - v2/v3 (not r1) seem to be cloned from o1/4o output, and perform worse (this cost the oft-repeated 5ish mm USD) - r1 is specifically a reasoning step (using RL) _on top of_ v2/v3 and…
Two months without a commit could still be quite active and useful software, especially for a personal project. Where would you draw the line?
This is not just PR and is very interesting. However, in my view, (and from a quick read of the paper) this is actually a very classical method in applied math work: - Build a complex intractable mathematical model…
No examples of before/after? Maybe I missed something.
What does this add to the conversation?
Some info that may be missing: - v2/v3 (not r1) seem to be cloned from o1/4o output, and perform worse (this cost the oft-repeated 5ish mm USD) - r1 is specifically a reasoning step (using RL) _on top of_ v2/v3 and…
Two months without a commit could still be quite active and useful software, especially for a personal project. Where would you draw the line?