Man there is a lot of activity going on about my stories lately. Was it the Slate Star Codex link? I’d figure it was that, but it seemed delayed by 24+ hours from when the post went up.
Maybe everyone needed a day or so to read them before they started responding?
I’m totally going to read them soon, I expect. Been trying not to get into new fiction until the school year ended. But all I have left now is grading!
I had to share this absolute banger of a meme that Matt Yglesias put on Twitter.
I really liked this Sarah Constantin article on why current AI approaches fundamentally aren’t going to lead to AGI.
Her discussion of ontological robustness reminded me of the point I was making the other day, about how GPT on a deep level can’t learn.
And for the agent to be able to conceive of [the possibility that its fundamental model might be wrong] and count it as something to avoid, for it to be able to say I don’t want my loss function to be spoofed by something that kills me, it needs to have a “goal” or a “value” that goes beyond its loss function.
AKA, not a static terminal goal. A way to distinguish the “true real-world goal” from one’s mere current specification of it, and update the specification as necessary.
AKA, cross-ontological transfer of goals.
GPT-like systems just…can’t do this. They have their training weights, and that’s what they have; nothing ever updates.
And of course there are ways to retrain them and fine-tune them, but that’s awkward, and manual, and not feeding off of any of the AI capabilities that GPT has. There’s no iterative improvement; and there’s no obvious or even really suggested path for how to get there.
Sarah says no one is even really working on this, and I believe her. I haven’t encountered anyone genuinely working on this; and it doesn’t seem terribly commercially useful, while it does seem super hard. And this is part of why I’m just not terribly worried about the AI apocalypse.
I am now a homeowner.
More generally, Yudkowsky has long been
If you grant that a super-powerful uncontrolled optimization process is about to be launched, you should in fact worry quite a lot. But it’s not.
In particular, the successes of GPT and the Transformer should reduce the credibility of Yudkowskian arguments, not raise it. Yudkowsky was arguing from a premise that any recognizable AI would necessarily have a certain collection of capabilities. GPT either does, or probably will soon, satisfy the conditions of a “recognizable AI”, but it doesn’t have those capabilities.
And the Yudkowskian conclusion is basically, therefore it must have those capabilities somewhere.
bulbous-oar
We don’t know that no possible large neural network implements an optimizer. If one does, we could stumble into it via gradient descent, just as we’ve stumbled into large neural networks that have world models.
Sure, we don’t know that no possible neural network implements an optimizer. In fact, I’ll go farther: it seems like if it’s possible to write one, which it probably is, we should probably be able to encode one in a large neural network. It’s just a very flexible framework for a model.
(Of course that flexibility is also the weakness: if it could be anything it has no strong pressure to be a specific thing.)
But I can say something stronger and also dumber than that, right? If an optimizer exists, then it’s possible that if I have my computer spit out 10TB of random bits and then interpret that as the source code to a C program, it will compile to that optimizer. It’s just…unlikely.
Large neural networks like GPT are not attempting to create optimizing agents. The training process is (outer-)optimizing for something, and the thing it’s optimizing for is very much not an (inner-)optimizer.
So this argument is something like, maybe writing an extremely powerful optimizer is so easy that we’ll do it by accident. And then not only will we create one, but it will be so powerful that it can out-optimize us, even if we’re trying to stop it, even though that’s if anything counterproductive to what we were training the model to do. That’s not impossible but it seems extremely unlikely.
(In contrast, I don’t think we “stumbled into” world models exactly; they are something we were more or less explicitly trying to get for the past couple years. This is part of Sarah’s point: people are trying to get world models, but they aren’t trying to get ontological stability or train inner optimizing loops basically at all.)
A new post up on my blog! Last time we talked about the algebraic numbers, and how just wanting to solve simple equations can create a ton of different numbers. But they don’t get us everything.
So this time we start off with the idea of measurement, and wind up inventing the real numbers. The real numbers are weird. Real weird. But they show up when we start asking questions about size or measurement. And in part 3, we’ll see they’re exactly the right way to do calculus.
ok this is dumb and not important BUT neural networks are not piles of linear algebra, they're piles of matrix multiplications. Linear algebra is the name of the mathematical theory we use to prove theorems about matrix multiplications.
This is the same pedantic losing battle as me objecting to the use of "biology" to mean "life", "chemistry" to mean "chemical reactions", etc
My main complaint with this phrase is that they are not linear. Like, that's exactly what makes them more powerful than the linear regression models and factor analysis models that people were using in the 20th century, right? That's a pretty significant thing that happened...
Well, unless you’re using floating point operations.
But yeah, it’s a pile of linear operations with mildly nonlinear buffers in between.
I have a new post up on my blog. Trying to experiment with writing faster and shorter so I can get more regular content out—which in this case means it’s only two thousand words and only took me a week to publish.
Do you find it risible when I say the name…Bigolas…Dickolas?
You do? Good. That is why I chose it.
its an interesting choice that link is mute from the players perspective but clearly conveying ifnromation, seemingly verbally, to other characters. i think the implicaiton is that link is speaking, we just dnt know what hes saying. i guess to make him more of a "blank slate". im not sure.
Mario does this also. Nintendo thing. Very interesting I actually like it a lot.
It’s a pretty common video game thing! Especially in earlier games. Link and Mario are always mute. But like Crono is also mute. In the Golden Sun games, whichever character is the protagonist at the time is mute. (And the Pokemon protagonists are mute, but that’s Nintendo again.)
In general if you want one character to be a standin for the player, it can be helpful for them to have no literal dialogue; the menu selections the player makes are “your dialogue”. That’s why modern pokemon games give you a bunch of dialog prompts where you can choose between “yes” and “of course” or some shit—the point is not to give you a choice, it’s to give you a line.
That doesn’t work well with modern voice-acted games, so it’s died out of those. But with a purely text-based interface it’s often the most reasonable choice.
