Maybe-Mathematical Musings — nostalgebraist: lostpuntinentofalantis: ...

1.5M ratings
277k ratings

See, that’s what the app is perfect for.

Sounds perfect Wahhhh, I don’t wanna
nostalgebraist
lostpuntinentofalantis

[reblog chain snipped]

Last year, when considering where to donate and knowing that I hadn’t really talked to 1) smart people who were 2) aware of the arguments for MIRI and 3) considered themselves EA/EA adjacent put a lot of weight on the fact that there were three independent confirmations (Frink, Lie group and Frobenius) that MIRI was incompetent re: math.

The fact that they were a sockpuppet is really concerning to me, because I already dislike su3 a lot on other (irrelevant to the issue at hand) grounds. I had already changed my mind based on evidence presented by all THREE separate, independent people and finding out they are all sockpuppets makes it very hard for me to undo my previous mind changing without the previous bias filtering in again.

Ordinarily I wouldn’t have paid much attention to people online for a decision as important as this, but it’s hard to talk to people about this subject when the social circles I hang out in either are unabashedly for MIRI or just not qualified to talk about the mathematical impressiveness. Lesson learned.

nostalgebraist

If this is useful, @jadagul is a mathematician and has also written about MIRI’s preprints.  (See this tag.)

On the other hand, I’m not sure you should really be putting much weight on these perspectives?  I don’t think anyone thinks MIRI’s available preprints are very impressive, and on the other hand I don’t think anyone’s found any explicit mistakes in them.  Judging from their output MIRI looks very unproductive (this is not controversial), and the explanation I’ve heard is that they’re working on a very hard problem and don’t have usual academic pressures to publish, so they just try out ideas and most of them don’t work (bc the problem is hard).

This is not generally how hard problems get solved – usually a large research community works on many semi-related (or even seemingly unrelated) issues until eventually it turns out they’ve built the tools to tackle the problem without exactly intending to.  (It’s sort of like: if you wanted brighter lighting in 1600, it would be good if you could invent electric lights, but the road to get there runs through playing around with magnets and stuff, and is unlikely to be found by a hard-working Royal Committee To Make Brighter Lights.)

So even if you believe MIRI’s team is competent (which they probably are), you’re still giving money to a Royal Committee To Make Brighter Lights than has spent years thinking about the problem all day and saying “hmm, this sure is hard.”  Consider whether that is a good use of your charity budget.

jadagul

So I was rereading SMBC comics the other day and ran across this comic

SMBC 2698

This doesn’t prove the claim is correct, but it does encapsulate the extent to which basically everyone believes it. It’s really hard to come up with an example of anyone, ever, solving a hard problem by deciding just to think about that one problem really hard, without going through a lot of more tractable problems and intermediate results.

miri science smbc

See more posts like this on Tumblr

#miri #science #smbc

More you might like

While I’m getting myself in trouble over gender:

I matched with someone on OKCupid yesterday. By which I mean she liked my profile and messaged me to tell me how much she liked it, and I agreed to the match and responded.

And her first followup message was to quote my list of movies and books I like and “gently ask me my fave women/POC creators”.

And like there are various ways I could answer that question. (I just enjoyed Gideon the Ninth. I subscribe to KB Spangler’s patreon at like ten dollars a month. I love Unpretty’s fanfic here on tumblr. Ursula LeGuin is amazing. Etc.)

But my real answer is, I think that’s kind of a poisonous way of engaging with media; I mostly don’t care about the demographics of the author, and I mostly don’t think you should either. I find the question, and the tone in which it was asked (“"gently”“), so offputting that my interest is now at zero.

from a place of privilege gender okcupid dating

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.

ai gpt ml

More generally, Yudkowsky has long been

  1. Correct that a powerful optimization agent that we don’t understand the inner workings of would be extremely scary, and
  2. Wrong in his belief that creating such a thing would be easy.

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.

ai ml gpt yudkowsky

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.)

ai ml gpt
jaydaigle.net

A Fictional History of Numbers, Part 2: Measurement, Estimation, Completeness, and Reality

This week we continue our exploration of what numbers are, and where mathematicians keep finding weird ones. We start by asking for the area of a circle, get exhausted by Archimedes's method for finding the answer, and take a tour through the idea of limits to construct the complete field of real numbers. We resolve one of the oldest mathematical flame war topics on the internet, and finish by worrying the real numbers are just too weird to actually use.
Jay Daigle

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.

blog math number theory calculus analysis
jaydaigle.net

Evaluating Students is Important, Too

Adam Mastroianni wrote a very interesting essay on his substack about how the difference between teaching and grading, and how much he dislikes the latter and all the problems with it. And I don't really disagree, but I don't agree either. So here's my response. Grading sucks, but it's important.
Jay Daigle

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.

blog I profess grading
loki-zen
transgenderer

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.

max1461

Mario does this also. Nintendo thing. Very interesting I actually like it a lot.

jadagul

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.

video games
See this in the app Show more