Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

Open models can come from anywhere. Securing them shouldn’t depend on where you get them. Today we're launching Project Beacon to make safety a default for open intelligence. We're partnering with Goodfire to bring inference and in-line monitoring together for the first time, so safety signals are caught proactively....

22,103 görüntüleme • 3 gün önce •via X (Twitter)

4 Yorum

Mark Attar profil fotoğrafı
Mark Attar3 gün önce

@GoodfireAI Yo @oneill_c you lost the beard

Amelia | AI & Tech profil fotoğrafı
Amelia | AI & Tech3 gün önce

@GoodfireAI In-line monitoring making safety the default for open models is a solid step enough

Sonup Bhuyaan profil fotoğrafı
Sonup Bhuyaan3 gün önce

@GoodfireAI Safety by default at the inference layer makes sense. Most teams pulling open models never add monitoring on their own.

Sam profil fotoğrafı
Sam3 gün önce

@GoodfireAI "Safety as a default" is doing a lot of work in that sentence. What does the default actually block, and can a customer turn it off?

Benzer Videolar