Загрузка видео...
Не удалось загрузить видео
SITUATION EXPLAINED: Someone is finally building AI benchmarks for blue-collar work. • Lenny Bogdonoff, former investor at NFDG (Nat Friedman Daniel Gross), is building a multimodal eval for blue-collar tasks • Covers electricians, ironworkers, technicians, assembly line workers, mechanics, and more • Almost every AI benchmark tracks knowledge work,... show more
32,729 просмотров • 3 месяцев назад •via X (Twitter)
Комментарии: 2

Max Mona 🇺🇸3 месяцев назад
It’s not far off in the future… It’s happening now! We’re going to be releasing our AI benchmarks soon across almost a dozen trades.

Ofek Shaked | AI Engineer3 месяцев назад
Knowledge work benchmarks became table stakes years ago. The harder measurement problem is whether an agent can propose a safe torque sequence or diagnose a control panel without hallucinating the interlock logic.
