Nikil Ravi
@nikilravi
Joined September 2021
4.3K Following 644 Followers
True, and it seems like much more of the govt/policy world will soon be driven by evals as well
It’s funny that a large chunk of the industry is driven by evals now. Many modeling efforts across the industry are pursuing SoTA eval numbers as their primary goal, well done eval teams! Well done artificial analysis and swebench etc.!
Show more
