Tailwind is so pervasive it's 100% in pretraining _and_ RLHF.

I've done several Tailwind projects and rarely did models from various providers need to reference Tailwind documentation.

> go after profitable niches and avoid unwinnable fights

If you know Apple's history, this should stand out to you.

I desperately miss their old XULRunner app. No longer worked through the API as of ~3 years ago and was a sad day for me.

He didn't say 90% of the coding jobs. He said LLMs would write 90% of the code. As in be LLM generated.

If you've ever been confused about which turn is which with top down navigation, then this is for you. While driving a car, being able to at a glance know exactly what turn is what would have saved me countless wrong turns, my parents probably doubly so.

One classic: there's a fork in the road on the way to my parents. One side is "straight", the other side is an exit. I took the wrong, exit side of that several times while my app said to go straight before I just knew the route and didn't need GPS at all. Top-down isn't as good in these cases because of densely packed roads and back to back exits.

That said, it's "good enough" and I doubt this takes off.

For me, confusion in top-down navigation happens either because there's no bitmapped imagery being displayed, forcing me to guess where the turn is by mentally wrapping vague 2D geometry over the scene viewed through my windshield, or because the trace isn't drawn precisely enough over the imagery that is available.

I don't see much added value with this particular nausea-inducing approach. It falls into the category of "You should've thought less about whether you could and more about whether you should."

while I think that the widgets telling you which lane to put yourself in largely solve this kind of intersection confusion, I understand the problem you are describing

but this seems to me just a topdown and "third person" at the same time through the distortion, I don't see how it helps with knowing exactly where to turn, is it because it shows the way further down the turn (like, sideways after the turn in the demo) ?

I had to login the other day to use it. Probably getting slowly rolled out.

If you just want it to generate UI out of nothing, the benchmarks aren't really for that.

If you want to generate a UI based on specific user input of some kind, then they are.

I'd suggest using one model for UI and another model for tacking onto that UI. LLMs are great at pattern matching, and benchmarks don't really capture one-shotting desirable UI.

That said, benchmaxxing is a thing and your experience with models is a thing. Benchmarks are fuzzy and should be taken with a grain of salt.

> designed

What?

"By the early 1960s, however, Philip Morris scientists had discovered that ammonia could also be used to increase the free nicotine in cigarette smoke, providing a more powerful nicotine kick than the milder low-pH tobaccos traditionally used in American-blend cigarettes."

They referred to it as 'crack nicotine' internally. It was an entire, giant scandal. They made a movie about it.

This product that kills the users of it with remarkably high rates and has effectively no positive use is fundamentally different from light and sound.

While that is terrible, it's still nowhere near proving your original assertion.

That's an insane take. Anything?!?

Can you name a single thing in the JavaScript ecosystem which has been stable for 10 years?

Express, Lodash, jQuery, require still works, the language itself.

Lots of CSS stuff are still virtually the same, as it only gets additions.

Vue.js API from 10 years ago still works fine in newer versions.

React class components still work. Even Hooks themselves are pushing 7-8 years now.

Express

Can you name a major Java framework or library (that's not abandonware)?

That's solely so that you burn more money. It's totally unnecessary to assume the parent model. Sure, it could be upgraded from Haiku if there was a solid reason to, but...