Voice prompting vs typing

`2:15:17`

When I build something like Omarchy, I, I do look at the code. I look at the shape. And I look at the proportions. Like, I don't have to chisel everything myself anymore. This is, again, when I'm flattering myself for... Not one moment I'm a McLaren audio, uh auto engineer, and the next moment I'm a da Vinci, working with his whole studio of students-... who are doing all the chiseling on the, the fine marble, right? And he goes like, "Ah, no, the proportions are not quite right." That's how it feels working with agents now. That I can give feedback like an editor. That, do you know what? I'm not gonna write everything myself, but I can tell you when the argument doesn't land. I can tell you when the shape isn't proportional to the problem, or when it just feels like it's too complicated. And shockingly often, it just works. It's like the early days, where the jokes was, "Don't make mistakes." I don't think you have to tell the agents that anymore, because now the harnesses are so good, they run automated testing. They get that feedback. But you actually do have to tell them, "Make it simpler."

`2:16:23`

I type the whole thing. I actually, in Omarchy's built-in Voxtype-... Audio transcription, and it's actually really good. I just find that I don't think that way, and it surprised myself that I don't like to talk to the computer. Uh, I like when I'm in the car, but when I'm in front of the keyboard, I just wanna type. I also just love typing. Are you using the voice?

`2:18:52`

... I haven't, yeah, I haven't used it that, and maybe that's how I'm using it wrong. I try to just type or speak two sentences, and then I get a little frustrated that I could've typed that just as fast maybe. But I have not tried this whole thing of just talking continuously for 20 minutes.

`2:19:12`

Yeah. No, I could see it. I think because the reason I've been, I've been trying to do it for things like replying to emails, and it got to a point where I thought it could help. And it sort of did, but then it would make a small mistake, and I'd have to correct the mistake. But if you're doing stream of conscious to an LLM who doesn't care about all this other stuff anyway-... that probably works way better.

`2:20:22`

Correct. Then I can't use it for dictating an email.

`2:20:43`

You gotta vibe code this into an app that does all of this such that-... it just works.

`2:20:59`

It seems like you've gotten much closer to the best of what's possible by putting all these things together.