Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

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 görüntüleme • 14 gün önce •via X (Twitter)

2 Yorum

MD ADIL profil fotoğrafı
MD ADIL14 gün önce

Update it with latest model, 3.8 Flash specifically.

PuneetSingh⚡️ profil fotoğrafı
PuneetSingh⚡️14 gün önce

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?

Benzer Videolar