Daniel Wilson: recommendation

Transcript context

…I'll proxy, you know, actually does that automatically. Like sometimes when I'm trying, I, I like to try and get it to build Python command line tools. Cause I build lots of Python and command online tools and it will just straight up say, I can't execute this, but copy and paste this into terminal and, and run this yourself and see what happens. Yep. Yeah. Yeah. Totally without any prompting, like it just threw it out there. No, you need, you gotta use the jailbreaking prompts. Okay. It's best if we don't tell them to the open AI folks because they'll just add them as more instructions to the moderation engine and change the model soon. So, yeah, have fun while we can, guys, before we update the moderation model. Actually I should keep track of that now. We, we will reach AGI when code interpreter can jailbreak itself. Yeah. Okay. So, so maybe I'll, I'll talk about one more limitation, which I seriously ran into. And then maybe you can just like, talk a bit more about, just use cases cuz I, I really want to spell it out for people. Because everyone, like I, I, I guess I consider myself relatively embedded in the SF AI space. It's at like a 5%. Market recognition right now. Like people don't know what it is, what they can use it for. Like as much as, as loud as Simon and Ethan have been about code interpreter. No, everyone is seriously underestimate underestimating this thing. So okay, one more, one more thing that I tried to do was I tried to use it to do data augmentation, right? Like I have a list of tables like superhero names and I want to augment it with things that I know it knows. I know the model knows this, right? But the model wants to write code rather than to fill in the blanks with its existing world knowledge. And it cannot call itself, right? Because there's no network access. So it cannot write code to call open AI to fill in the blanks on existing models. And I wanted it to, for example, embed texts that I sent it in and it couldn't do that, right? So so there's just some, some limitations there, which I observed like if you were using regular GC four, switching, the code interpreter is a regression on that element on that front. That's really interesting. I have to admit I've not tried it for augmentation because when I'm doing stuff like augmentation, I'll generally do that directly in g just regular GPT4, like print out a Python dictionary look, providing a name and bio for each of these superheroes, that kind of thing. And then I can copy and paste that back into, well actually not copy and paste. You want to upload that J s o n file into code interpreter cuz uploading files doesn't take up tokens. Whereas copy and paste and code does. Yeah, yeah,…

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