Загрузка видео...

Не удалось загрузить видео

На главную

Help shape the future of Android Bench. Android Bench provides you with transparency into AI coding assistance. You now have an opportunity to contribute your own tasks, or submit locally run evaluations. Read more to learn how →

19,483 просмотров • 14 дней назад •via X (Twitter)

Комментарии: 2

Фото профиля MD ADIL
MD ADIL14 дней назад

Update it with latest model, 3.8 Flash specifically.

Фото профиля PuneetSingh⚡️
PuneetSingh⚡️14 дней назад

locally run evals is the useful bit. once people submit their own tasks, how do you stop the set from overfitting — versioned harness + held-out tasks?

Похожие видео