News for hackers. Stuff that matters.

A comment on GulliBench: Measuring Skepticism in Frontier Models.

Re:GulliBench: Measuring Skepticism in Frontier Models by dvaplima on Wednesday August 12, 2026 @10:58AM (#49273445)
I liked approach to evaluating AI behavior, the fact that additional reasoning doesn’t improve performance is quite interesting!
[ Parent | on HN ]

There are no comments on this comment yet.