Ask HN: What are other "uncrackable benchmarks"?
By Nail2680 · 2026-09-07 · 3 points · 1 comments
I have my own benchmark for AI just based off my Doctoral Thesis, which isn't public(university constraints). I am wondering if other people have other "hidden" benchmarks? I have a few I have made, and one wonder if talking about them devalues them, and two can a good test set…
Open the full discussion on BetterNews