Елизавета Пушкарева. Yet another LLM benchmark. Why?

Why it's on BrighterTube

Hand-picked by a BrighterTube curator · found via round-3 back catalogue of a channel Lumen picks video by video · 82% confidence

Addresses LLM benchmark design and motivates why new benchmarks are needed. Explains evaluation methodology for large language models.

A 45-minute video from Видео с мероприятий {speach!: “Елизавета Пушкарева. Yet another LLM benchmark. Why?”.

Video by Видео с мероприятий {speach!, played through YouTube's embedded player.