Halvar Flake(@halvarflake):Random note: I’ve been squinting at the statistical validity of published AI benchmarks in the last few days, and while I vaguely believe the mean, I pretty much believe none of the confidence intervals. Everybody is playing very fast and loose with stats.

Halvar Flake

@halvarflake

Choose disfavour where obedience does not bring honour. I do math. And was once asked by R. Morris Sr. : "For whom?" @halvarflake @mastodon.social

가입 June 2008

2.9K 팔로잉 중 47.7K 팬

Halvar Flake@halvarflake

2026.09.13 21:54

Random note: I’ve been squinting at the statistical validity of published AI benchmarks in the last few days, and while I vaguely believe the mean, I pretty much believe none of the confidence intervals. Everybody is playing very fast and loose with stats.