OMG, I'm so stealing that ;)

"Woke" simply means "I'm conservative, and the thing I'm calling 'Woke' is something that I hate". It has no well-defined meaning beyond that. I've heard things as diverse as "the concept of the Metaverse" and "removing copyrighted content so you don't get sued" described as "woke".

No call by push value or P vs NP or complexity theory etc.

So a different set of things that are also useless to the vast majority of people?

Even when Chrome adds support, we'll have to wait ages before we can actually reliably use the format without having to implement fallback logic and fallback formats for legacy browsers.

AVIF is also painfully slow. And if I recall correctly, is outperformed by JPEG XL at moderate and low compression (but - again, if I recall correctly - AVIF wins at highly compressed images). Also, AVIF faces some patent threats. And misses a lot of JPEG XL's interesting features.

A practical issue with a circle is that it is not a circle until it is finished,

That's not the reason at all, AFAIK. The reasoning is, okay, we want people to be able to move from one place to some distance place in the city at the maximum comfortable speed, which is limited by G-forces. You have some guaranteed G-forces from first accelerating and then decelerating. But if it's linear, that's your only G forces. If it's curved, however, you also have radial G-forces.

The Line's train going from one end to the other (170km) nonstop is supposed to do it in 20 minutes, aka with a mean speed of ~510 kph. Let's say a peak of 800 kph. Now if we shape that 170km into a circle, that's 54km diameter, 27km radius. From the centripetal force formula a=v^2/r, that's 222,22...^2 / 27000 ~= 1,83 m/s^2, or a constant ~0,2g to the side. This is on top of the G-forces from your acceleration and deceleration. You can probably deal with ~0,2g in a train if everyone is seated without much discomfort, though it's double what's acceptable for standing passengers. But you can eliminate that if the city is linear (at the cost of increasing the mean distance that the average person has to travel to go from one arbitrary point in the city to another)

That's not to defend this concept. Because the city doesn't need to be 170km long; you can just made it more 2d and have the distances be vastly shorter (at the cost of just needing some extra lateral travel within the city). Honestly, if I were building a "designer" city from the ground up, I'd use a PRT (Personal Rapid Transit) system rather than trying to make it super-elongated.

What got me is that I don't see why this isn't readily resolved by active damping, the same systems that many tall towers now use to resist earthquakes or resonant wind forces. Big heavy weight at the top (or in this case the bottom) hooked up to actuators that make it move in an inverse direction to the sway.

Again, this is not to defend this colossal waste of money. I just don't see why there aren't ready solutions for this specific problem.

Agreed - but that said, there are space elevator alternatives, like the Lofstrom Loop / Launch Loop, which at least theoretically can be built with modern materials (and have far better properties anyway - not latitude-constrained, provides dV, vastly higher throughput, far more efficient, stores energy / can add cheap energy at off-peak times, etc). One could always "waste" money on them trying something new :)

No; it's absolutely a terrible idea. It may be great for the businesses; but, it's absolutely fucking terrible for the consumer.

This is absolutely fucking insanity. Imagine having to carry 6 different cards and wondering which one a particular store is going to take.

there are 5 billion Roblox accounts created

5 billion more accounts than you have brain cells, apparently

SAS has been dead for 15y; it started with R and then Python absolutely destroyed it. No one teaches SAS in universities any longer, why would they? It's terribly expensive and absolutely fucking dead.

We migrated away from SAS back in 2017 and never looked back. The only verticals still using it are heavily regulated and running long-standing legacy code that they're slowly migrating to Python.

I remember absolutely dying when they tried to renegotiate our contract UP back in 2015. I flat out told them they were dead and we were moving away from them and they told me, "good luck managing your data without us!"

Two companies and 10 years later, we're doing just fine and they are not.

No. Like any software, AI requires maintenance, and that maintenance costs money, lots of money.

It does not. Models need nothing more than the storage of some gigs of weights, and a GPU capable of running them.

If you mean "the information goes stale", one, that doesn't happen at all with RAG. And two, updating information with a finetune or even LORA is not a resource-intense task. It's making new foundations that is immensely resource intensive.

Can you integrate it into your products and work flow?

Yes, with precisely the difficulty level of any other API.

Can you train it on your own data?

With much less difficulty than trying to do that with a closed model.

And my point is that AI wouldn't just stop being used even if the bubble imploded so heavily that all of the major AI providers of today went under. It's just too easy to run today. The average person who wants something free would on average use a worse-quality model, but they're not going to just stop using models. And inference costs for higher-end models would crash if the big AI companies were no longer monopolozing the giant datacentres (which will not simply vanish just because their owners lose their shirts; power is only about a third the cost of a datacentre, and it gets even cheaper if you idle datacentres during their local electricity peak-demand times).

Your scenario is impossible, so try again.

Because we're discussing a scenario where the big AI companies have gone out of business, remember? And the question is whether people just stop using the thing that they found useful, or whether they merely switch to whatever alternative still works.

It's like saying that if Amazon went out of business, people would just stop buying things online because "going to a different website is too hard". It's nonsensical.