Vibe coding

`1:56:37`

There's very often been people who didn't know how to program, who wanted programs, who then hired programmers, who gave them messy descriptions of what they wanted and then when the programmers delivered that back said, "Oh no, actually that's not what I meant. I want something else." AI may be able to provide that cycle. If that happens to the fullest extent of it, yeah, there's not gonna be as many programmers around, right? But hopefully presumably someone still, at least for the foreseeable future, have to understand whether what the AI is producing actually works or not. — As a interesting case study, maybe a thought experiment. If I wanted to vibe code Basecamp or HEY, and some of the products you've built, like what would be the bottleneck? Where would I fail along the way? — What I've seen when I've been trying to do this, trying to use vibe coding to build something real is you actually failed really early. The vibe coding is able to build a veneer

`1:57:39`

at the current present moment of something that looks like it works, right? But it's flawed in all sorts of ways. There are the obvious ways, the meme ways that it's leaking all your API keys, it's storing your password in plain text. I think that's ultimately solvable. Like it's gonna figure that out or at least it's gonna get better at that, but its capacity to get lost in its own labyrinth is very great right now. It code something and then you wanna change something and it becomes a game of whack-a-mole. Real quick, Pieter Levels who've been doing this wonderful flight simulator was talking to that where at a certain scale, the thing just keeps biting its own tail. You wanna fix something and it breaks five other things, which I think is actually uniquely human because that's how most bad programmers are. At the certain level of complexity with the domain, they can't fix one thing without breaking three other things. So in that way I'm actually in some way it's almost a positive signal for that the AI is gonna figure this out because it's done an extremely human trajectory right now.

`1:58:39`

The kind of mistakes it's making are the kind of mistakes the junior programmers make all the time. — Yeah, can we zoom out and look at the vision, the manifesto, the doctrine of Rails? What are some of the things that make a programming language a framework great? Especially for web development. So we talked about happiness. The underlying objective of Ruby. What else? — So you're looking at the nine points I wrote out in I think 2012. And first, before we dive into 'em, I wanna say the reason I wrote it down is that if you want a community to endure, you have to record its values and you have to record its practices. If you don't, eventually you're gonna get enough new people come in who have their own ideas of where this thing should go. And if we don't have a a guiding light helping us to make decisions, we're gonna start flailing. We're gonna start actually falling apart. I think this is one of the key reasons that institutions of all kinds start falling apart.