logoalt Hacker News

jacquesm • yesterday at 10:05 PM • 1 reply • view on HN

You can hill climb but you will (or at least, I think you will!) lose generality.

And no, that won't get you to AGI, that is a completely different goal.


Replies

banghua13 • yesterday at 10:25 PM

If you carefully curate the data, plus the original model isn't saturated for RL post-training, it's possible to improve targeted benchmarks without regression on other metrics. This experiment is done with terminal bench 4.1 as a target, and the regression on other benchmarks has been carefully controlled through data + infra design.

➕ show 1 reply