The Dystopian Future of AI

Are we that far from being able to run these models? Like, for example, the llama model locally on, say, an urban or at least on, like, I don't know, maybe an iPhone. You can run the llama, like llama dot CPP, or packet of CPP, you know, very efficiently on your Mac right now and it won't even be that slow. It's just that the model isn't as good as VPT for. So what you want is you want the hardware to get a little bit more accelerated and you want the models to be optimized.

Play episode from 54:35

Transcript

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!

Get the app