AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
2min chapter
Collin Burns On Discovering Latent Knowledge In Language Models Without Supervision
The Inside View
Do We Need Models to Maximize Profit Subjects?
I don't think this is sufficient right like getting a model to maximize profit subject following the law. I sort of suspect that people will like push in that direction anyway and use models for those sorts of purposes anyway. If you're thinking that let's just like we'll output plans that always maximize human authority yep yep yeah so this is going back to my original point about not trying to be clear on how AI companies try to maximize profit subjects or maybe like follow the intent being behind a law. Even literal law like you know not killing anyone or something I think it's not even clear how to do that for example if you have an AGI system that's doing all this
00:00
Transcript
Episode notes
Get the Snipd
podcast app
Unlock the knowledge in podcasts with the podcast player of the future.
AI-powered
Discover
highlights
Listen to the best highlights from the podcasts you love and dive into the full episode
Save any
moment
Hear something you like? Tap your headphones to save it with AI-generated key takeaways
Share
& Export
Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more
AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
Discover
highlights
Listen to the best highlights from the podcasts you love and dive into the full episode