News for hackers. Stuff that matters.

A comment on Gemini 3.5 Flash. Parent comment

Re:Gemini 3.5 Flash by throawayonthe on Tuesday May 19, 2026 @02:32PM (#48197329)
well there is https://artificialanalysis.ai/evaluations/omniscience
[ Parent | on HN ]
Re:Gemini 3.5 Flash by goldenarm on Tuesday May 19, 2026 @03:03PM (#48197826)
It's a gibberish input detection benchmark, and does not measure output hallucinations.
[ Parent | on HN ]