Not addressed raw tape
D 1 · C 4 · P 4 · Cm 3 2.95
Q Yeah. And I'm sure we're going to talk about it, but obviously the question is, uh, to which extent can AI review AI?
A Unfortunately, for those people that are viewing the podcast that, uh, that are engineers or practitioners, uh, all of the problems that I'm talking about are very much our opportunities as investors, um, and founders and founders, uh, and we see a ton of them across All of these spaces. So I, I won't go into every single one, but I'll, I'll call out a few on the security side. So there's a, there's a lot of companies, older companies, Fortune, a thousand companies that use, uh, EOL software. So maybe they're on like a very old version of CentOS, or, um, you know, maybe they're using a old package, old version of an open source library. Um, and the notion that they could just upgrade is actually quite, uh, it's a difficult thing to do. And so we're seeing a handful of companies that have actually, uh, pioneered what's called auto patching. And so the ability just to, uh, instead of like forcing folks to make a potentially breaking change, just patch a project and, and let things stay status quo and smooth. That's a capability that, um, you'd be shocked. There are thousands of engineers that have spent days, weeks, months trying to just keep something afloat.
AI assessment note: “all of the problems that I'm talking about are very much our opportunities as investors”
Redirected raw tape
D 1 · C 3 · P 3 · Cm 3 2.40
Q bit in part to figure out what to do, uh, as we alluded to earlier, then the question becomes, uh, you know, how do you become a great editor, uh, or QA person if you don't write the code and, and build, uh, Fundamental knowledge and habits around the core. How do you build the taste that you need to be able to review those things? It's a complicated topic.
A The idea of prompting, too, is just fascinating. So, um, I was having an interesting conversation with an engineer the other day who was talking about, you know, the ability to one-shot Salesforce. And by one-shot they mean, like, could I recreate Salesforce With, uh, in, in just one sitting with one of these tools. I mean, obviously the answer is no. Uh, but, but if you ask why it's mostly because actually like if you're trying to recreate something through a series of prompts, you actually have to really understand what it is that you're creating. And most of us, when we, when we do that, we're starting visually. We think we understand, uh, you know, maybe the database logic sitting underneath an app, but I mean, Salesforce is a, a fantastic example of a very, very complex, deep app with a ton of different use cases and integrations and reporting structures. And so, You know, it's not just the reviewing side, I think that will evolve, but it's also just how we think about prompting and, and that being a skill set. Um, so that, that is fascinating. I think on the architecture side too, we're seeing a similarly sized shift where, um, you know, we used to sort of define these systems via design docs and then a bunch of human enforced conventions that might've sat in a confluence doc somewhere, uh, to follow. Um, whereas today we're seeing just this huge push to define systems in…
AI assessment note: “The idea of prompting, too, is just fascinating.”
