Comment by avianlyric
5 hours ago
If you’ve validated the Jev scores, then it means you’ve built and run the evals. The exact thing the author is arguing needs to be done if you’re using Jev.
So they’re not dunking on that, they’re dunking on the idea that you can just trust Jev confidence scores without actually doing any validation.
No comments yet
Contribute on Hacker News ↗