AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
Structured Access to AI Models
The framing of this too is kind of interesting because they explicitly differentiate between the idea of malicious use or kind of weaponization and just the idea of an AI that develops enough context awareness to engage in power seeking behaviors. So I thought this was really interesting. It's another data point in favor of the idea of external audits of these models. Yeah, I think this is awesome work. We mentioned this briefly last week from Yoshua Benjio, a blog post called How Rogue AI May Arise. And yeah, it's a more analytical look into how could bad AI that's misaligned happen,. building on some of the existing theories.