Simon Willison: preference

Transcript context

…I was gonna say, I think the Post is really focused on how do we get the best model, but it's not focused on like, how do we build the best product around it. A lot of these models are limited by how many GPUs you can get to run them and we've seen on traditional open source, like everybody can use some of these projects like Kafka and like Alaska for free. But the reality is that not everybody can afford to run the infrastructure needed for it. So I, I think like the main takeaway that I have from this is like, A lot of the moats are probably around just getting the, the sand, so to speak, and having the GPUs to actually serve these models. Because even if the best model is open source, like running it at large scale for an end is not easy and like, it's not super convenient to get a lot, a lot of the infrastructure. And we've seen that model work in open source where you have. The opensource project, and then you have a enterprise cloud hosted version for it. I think that's gonna look really different in opensource models because just hosting a model doesn't have a lot of value. So I'm curious to hear how people end up getting rewarded to do opensource. You know, it's, we figured that out in infrastructure, but we haven't figured it out in in Alans yet. I mean, one thing I'll say is that the the models that you can run on your own devices are so far ahead of what I ever dreamed they would be at this point. Like Vicuna 13 b i i, I, I think is the current best available open mo model that I've played with. It's derived from Facebook Lama, so you can't use it for commercial purposes yet. But the point about MCK 13 B is it runs in the browser directly on web gpu. There's this amazing web l l M project where you literally, your browser downloaded a two gigabyte file. And it fires up a chat g D style interface and it's quite good. It can do rap battles between different animals and all of the kind of fun stuff that you'd expect to be able to do the language model running entirely in Chrome canary. It's shocking to me that that's even possible, but that kind of shows that once, once you get to inference, if you can shrink the model down and the techniques for shrinking these models, the, the first one was the the quantization. Which the Lama CPP project really sort of popularized Matt can by using four bits instead of 16 bit floating point numbers, you can shrink it down quite a lot. And then there was a paper that came out days ago suggesting that you can prune the models and ditch half the model and maintain the same level of quality. So with, with things like that, with all of these tricks coming together, it's really astonishing how much you can get done on hardware that people actually have in their pockets even. Just for completion I've been following all of your posts. Oh, sorry. Yes. I just wanna follow up, Simon. You're, you said you're running a model on your phone. Which model is it? And I don't think you've written it up.…

Stored transcript either side of the excerpt. The highlighted words are the published quote; the surrounding text is unedited source, never generated.