Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

We’re introducing SEAL Showdown, the AI leaderboard that actually captures real preferences, powered by a platform used by real people. Public benchmarks today rely on contrived tasks or narrow user groups. That leaves us guessing which models are actually preferred by people. SEAL Showdown changes that. Model performance can...

20,072 Aufrufe • vor 1 Jahr •via X (Twitter)

5 Kommentare

Profilbild von Jason Droege
Jason Droegevor 1 Jahr

Explore Showdown yourself!

Profilbild von Gilfoyle
Gilfoylevor 1 Jahr

Not an open model is included ... It's a private club.

Profilbild von Mohamed Anis
Mohamed Anisvor 1 Jahr

Are you planning to weight demographic segments by market size or keep it pure preference-based - that choice will determine whether this becomes a research tool or commercial predictor

Profilbild von sor
sorvor 1 Jahr

Slavery is illegal in the USA but the nice folks at Uber eats have found a solution and created the next best thing! They're profit generating geniuses! What a concept

Profilbild von Ton
Tonvor 1 Jahr

Benchmarks miss what usage really shows

Ähnliche Videos