[sejje]

That one does sound like hyperbole, or maybe he just works slowly as a human? People are different.

Likewise, I think they're having wildly different results. Look at how differently humans drive vehicles, and realize they're doing the same with compute. Some people probably are working at light speed, and some people are actually slower like in the study.

[latexr]

> Look at how differently humans drive vehicles, and realize they're doing the same with compute.

I’m not sure that comparison is evoking the image you intended. Hands down the best driver I know—the one I’m sure won’t get me car sick, won’t ever have me worrying for my safety, the most fuel efficient, the smoothest rider—is by no means the fastest but the most thoughtful and methodical.

I don’t care how fast you develop your software. Is it good? Is it carefully considered? Will it not bite me in the ass? Those are the things that matter.

[sejje]

Sure, I agree. And I get that result--slow and steady--out of the LLM when I use it.

[theultdev]

I'm talking about the scale. This was a large app with 60+ screens, 400+ component ui kit, and very rich features.

And had to work on ios/android/web.

I'd consider myself a pretty fast programmer, and I grind 12 hours at a time, everyday until it's done.

But between all humans it's a rounding error compared to the output of an agent swarm.

For personal projects, I pick and choose how much to use AI. But for work, agents go brrrr.