Do they go away or do they use the weak but good enough (for many) Google LLM response instead?

What if the CEO isn't just telling the company how much to invest, but also has influence on how that money is used? Google's relative success, if it exists, I'd rather not judge, isn't from investing more than everybody else. Because the money just keeps pouring into these things, for all contenders.

> investing more than everybody else

If that's going to decide who wins, Zuckerberg will be the winner. He's been hiring researchers for $100 Million a piece. We'll see soon.

So how much is the American household spending on Waymo, in average? It's totally insignificant.

The value of Waymo isn't current revenue, it's whether it works reliably and whether it can be scaled.

Valuable in what metric? I'm very much in the brownfield-has-the-lessons camp, but one of the lessons is that this experience has a very low market value. In fact it's so impossible to downgrade from "senior in $outdated" to "junior in $whateverisconsideredhotrightnow" that any brownfield experience could easily be considered to have negative market value.

Give it time: at some point nobody will be consumer except for the equity lords. Savings will reach them.

In analogy to suspension of disbelief I'd like to postulate suspension of genericity:

when I sink countless hours skimming text content in some The Elder Scrolls I'm not really convinced that much of it is a story worth consuming (my opinion of TES is lower than my number of gameplay hours might suggest), but I'm at least open to the idea that it might be. Thousands of players have paid good money for consuming those stories, do who knows, I might actually find something meaningful, perhaps something I'll one day connect with a real person about, so it's not necessarily a given that it's all just filler.

But when it's an LLM generating the story for me and only for me, there's no other possibility. It's a hamster wheel time sink and I can't even pretend that it's not.

Procedural generation has always had this problem where over reliance on it feels cheap and not meaningful - see Starfield from the same developer.

I would argue the exact same effect can be seen with AI images or videos - no one is watching those for hours every day on purpose

And yet there were a lot of games with procedural generation as their centrepiece that did not suffer from this at all. The original X-Com games come to mind. I guess we can somehow "feel" where it's simulation, where it's "honest diceroll" (also very much ok when the rules appear tuned well).

But when it's too much it's too much, and an LLM game (where either the LLM remains in the loop, or it just spewed out a seemingly infinite heap of static filler) can't not be too much.

Yeah, let's look at it through the national lense. For every researcher who defects to the US to make their PhD there and most likely stay, taxpayers of the country they came from have paid for the education of hundreds of students. Because they don't come from America where graduating essentially means a life of indentured servancy for all but the dynastically wealthy.

It's called brain drain, and doing the rest of the world the favor of putting on the brakes is something that would be quite far out on the spectrum you'd call "woke" if it was done for the reasons one would arrive at when really thinking it through (which clearly has not happened)

Imagine if it were the other way around, and all the top American university graduates left to do their PhDs and postdocs in Chinese labs.

Americans would throw a fit and say it was a grave threat to American technological superiority, national security, etc.

It's obviously good for a country when it can attract the top talent from around the world.

I guess the idea would have to be to look at it in the reverse: have some domestic capacity for those usual strategic supply independence reasons, even if it operates at a loss. And hope that occasionally, one of those demand surge waves will swipe through and make the cost not quite so bad. Outlier waves like the current one might even create a net positive, but that bet would not be the primary purpose, that honor would go to hedging against getting cut off.

Reads a bit like the Paperclip Maximizer appearing way ahead of schedule? Implemented not as AI, but as emergent behavior in the ways of the financial class (that happens to be about AI, singularity and all that).

Given the level of totally bonkers I feel tempted to suggest that it's a hit piece indirectly commissioned by palantir themselves so that they can for once appear as the good guys in a news story