Simon Willison: commitment

Transcript context

…possible. Yeah, but it, it, it definitely feels possible cuz I literally just as you guys were talking, dumped some and yeah. Wait, wait. So, okay, I, I, I don't understand your assertion. You, you ran code, but the code has nothing to do with the model. No, no. I think Alex hit it on the head. Okay. All right. Cool. Alright. Right. And then Yam also nist and then Surya. Hi. Yeah. I just wanna say that I did some sniffing around of the protocol of the client side, and it goes to a completely different endpoint. I mean, it's nearly sure that it's not the same model. There are also other parameters that I've never seen on the client side when running this. So I'm pretty, it's nearly sure that it's not the same model. And sorry, what do, what do you mean? What do be other parameters? Can you, can you elaborate? I don't have it in front of me, but when you go on the client side and just, you know, write and, and talk to the model if you go to the inspect of Chrome and just look at the network, it's different than the, the normal . It goes first, it goes to a different model. And usually the endpoint is an actual name of a model, like something that, you know 3.5 Turbo or something, or four. This is a different one. It's four dash interpreter. So that's, that's a first. And I also saw some parameters that are sent that are, I'm, I'm not sure what they're said or what, what are they saying, but it, it is, it is different. This is what I'm, I wanna say it's different. So it's nearly for sure not the same model. And I just wanna ask, I just wanna ask all of you, all of you're talking about uploading code and then letting it use the code. I mean, it needs to know about the code somehow, if I'm correct. So I mean, mostly I copy and paste code straight into it. I find that for the kind of stuff I'm doing, normally what I'll do is I'll take the code I'm working on, I will reduce it to the shortest sort of example that, that shows what I'm trying to do to use less tokens, copy and paste that in. And then I'll tell it, try running this against this data, then refactor it so it supports this feature and, and that just tends to work. But, but you still need to pay the tokens. That's what I'm asking. It's not, there is no work around, like you can upload a full GitHub repository and somehow not model. No, there is,…

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