Investors are chasing a company that achieves some kind of AI singularity. Let's set aside the fact that there's no reason to believe there is anything but diminishing marginal returns by making marginal refinements to current frontier models. Let's imagine someone hits the jackpot and gets, not even AGI, but a system that's as far ahead of today's frontier model are ahead of 2020's GPT 2.0 in performance.

Globally AI revenues are 150 billion, against a cumulative burn rate of 450 billion. A model that is a generation ahead of others would almost certainly capture the lion's share of that revenue.

If AGI magically appears as a Sam Altman has promised investors it will, a hundred million is way too low. Add, maybe, another zero to the revenues.

Conservatively, a safer assumption is that frontier models will get marginally better based on refinements in training and reinforcement and the other bits and bobs that go into these systems. The nobody is winning the lion's share of anything, at least overnight. But you have to define "safe". By "safe" I mean unlikely to lose money. But some investors are clearly defining "safe" as "having the greatest chance of owning a piece of the biggest thing ever."

I'm not following this super-closely, but if Anthropic is pursuing adding multi-step model based reasoning to their system, that could be the basis of a generational leap in capability. But if that is an approach that looks like it has a chance of working, then their competitors are no doubt pursuing the same thing. In that case you'd expect the revenue pie to grow as the scope of model utilty increases, but that growth to be split among several competitors. This could credibly result in a revenue stream for some of them that is as big as the entire industry's revenue stream today. But there's going to be hell to pay on the data center impacts end of things.

But that *does* require that you believe that they are honest to you about their future actions...and that they won't change their mind later.

Pirates were often hanged by the same countries that issued them letters of marque.

Why do you believe what they say when they continually misrepresent things. I'd say "lie", but that implies they know what they're doing.

I would imagine they decay into something else in like 10e-15 seconds.

If I read that summary correctly, this will only ever be usable to clean small amounts of stuff in a closed container. It's not going to work for, say, the Great Pacific Garbage Patch.

That's what it meant ever since RUR. I'll grant that PR people keep spinning different meanings for it though.

Please modify this to:
"""Whenever a "discovery" is announced it's best to wait for verification before popping champagne corks."""

If there isn't independent verification then it's poor policy to believe. It may also be poor policy to disbelieve.

Actually, I had measles twice before there was a vaccine. There are two different kinds of measles, but presumably the vaccine covers both.

Not necessarily. If they're designed to achieve maximum penetration, then you're probably correct, but if they're designed as networks of friends, and you can't invite whole networks, then it's a lot more manageable. Say that no group can have more than, O, 254 members, and you don't have the problem you posit. Of course, everyone would have trouble finding the groups they wanted to be a member of that also had room for them, but there are problems with every approach.

How do you prove they represent the company they claim to represent without giving them a credit card number?

I generally assume that they DON'T represent such a company, but occasionally one will claim that they represent a company which forwards positive sales to another company. I've never tried to find out if that's true, but it's believable. But such a company is probably off-shore and with no local assets.

A couple of things to worry about, if you want to.
1) How reliable is that test for measles antibodies?
2) How quickly do those antibodies decay after a vaccination?

I strongly suspect that the answers to both of those questions is variable. Also, at least some diseases with do a reset on your immune system beta cells. (Actually IIRC measles is one of the diseases that will do that.)

Since he's talking about an individual decision, I assume he's talking about that same individual deciding whether it's worth paying for his extended life (in the future).

Well, unless you're arguing that everyone should invest an infinite amount of money in prolonging everyone's life no matter what their condition is.

That's not a "could be". They *did* report that. And adjusted the statistics to handle that effect. There's a reasonable argument that "10 years earlier" is hard to adjust for", though.

From TFOriginalScientificArticle: "Additionally, death certificates included a field for reported usual occupation (the occupation in which the decedent spent most of their working life), generally completed by a funeral director with help from the decedent’s informant."

Looking at Figure 1 from the paper, taxi drivers and ambulance drivers are clear lower-bound outliers in terms of risk from Alzheimer's. But they also die a full decade before the eyeballed mean of the population. There are a couple of data points in the middle plot from that figure that have just slightly higher adjusted risk of Alzheimer's, but have lifespans at ca. 80 years that are well *above* the mean. Regrettably, the paper does not discuss those data points -- me, I'd want to have those occupations since they trade a very slightly increased risk of Alzheimer's for 15 more years of life.

And, then, the bit that's also not in the headline and TFS is that taxi drivers and ambulance drivers have *increased* risk of other forms of dementia, especially taxi drivers.

Also, disappointingly, the paper does not show the full ranked list of occupations (even in the supplementary data), highlighting only a small handful (taxi drivers, ambulance drivers, bus drivers, airline pilots, ship captains, and CEOs).