swlabr @ swlabr @awful.systems

Only Bayes Can Judge Me

---

Read more

Posts

37

Comments

1,898

Joined

2 yr. ago

YaaS: Yubitsume as a Service

He got up at 5:30 a.m. to show the sunrise to his microphone

No doubt inspired by my favourite holistic wellness woo/Soundgarden song, butthole sun(ning)

Grue? Is this Zork?

Zit crit!

Agree: I don’t have much of an opinion on him either way. If this community is gonna hold him up as a voice of note then it should be able to critically engage with his work.

If saltman knew what quantum gravity was and why LLMs won’t solve it first, maybe he’d have general intelligence

maybe 2, for good measure

This paragraph caught my interest. It used some terms I wasn’t familiar with, so I dove in.

Ego gratification as a de facto supergoal (if I may be permitted to describe the flaw in CFAImorphic terms)

TL note: “CFAI” is this “book-length document” titled “Creating Friendly AI 1.0: The Analysis and Design of Benevolent Goal Architectures”, in case you forgot. It’s a little difficult to quickly distill what a supergoal is, despite it being defined in the appendix. It’s one of two things:

1. A big picture type of goal that might require making “smaller” goals to achieve. In the literature this is also known as a “parent goal” (vs. a “child goal”)
2. An “intrinsically desirable” world (end) state, which probably requires reaching other “world states” to bring about. (The other “world states” are known as “subgoals”, which are in turn “child goals”)

Yes, these two things look pretty much the same. I’d say the second definition is different because it implies some kind of high-minded “desirability”. It’s hard to quickly figure out if Yud actually ever uses the second definition instead of the first because that would require me reading more of the paper.

is a normal emotion, leaves a normal subjective trace, and is fairly easy to learn to identify throughout the mind if you can manage to deliberately "catch" yourself doing it even once.

So Yud isn’t using “supergoal” on the scale of a world state here. Why bother with the cruft of this redundant terminology? Perhaps the rest of the paragraph will tell us.

Anyway this first sentence is basically the whole email. “My brain was able to delete ego gratification as a supergoal”.

Once you have the basic ability to notice the emotion,

Ah, are we weaponising CBT? (cognitive behavioral therapy, not cock-and-ball torture)

you confront the emotion directly whenever you notice it in action, and you go through your behavior routines to check if there are any cases where altruism is behaving as a de facto child goal of ego gratification; i.e., avoidance of altruistic behavior where it would conflict with ego gratification, or a bias towards a particular form of altruistic behavior that results in ego gratification.

Yup we are weaponising CBT.

All that being said, here’s what I think. We know that Yud believes that “aligning AI” is the most altruistic thing in the world. Earlier I said that “ego gratification” isn’t something on the “world state” scale, but for Yud, it is. See, his brain is big enough to change the world, so an impure motive like ego gratification is a “supergoal” in his brain. But at the same time, his certainty in AI-doomsaying is rooted in belief of his own super-intelligence. I’d say that the ethos of ego-gratification has far transcended what can be considered normal.

I hear GPT-8 will broadcast a dyson sphere circumnavigation race

Opening the sack with this shit that spawned in front of me:

OpenAI CEO Sam Altman says GPT-8 will be true AGI if it solves quantum gravity — the father of quantum computing agrees

Guess it won’t be true AGI!

Kind of a fluff story (archive) where salty’s douchiness is on full display.

I referenced it because fake book titles are throwaway jokes, you can reference something hyperspecific and not have to worry about whether or not someone will get it, because they might not even notice it at all.

The spectre of Marx nods in approval

Ah, gotcha. fwiw I wasn’t saying that to say “joyless people are bad”; burnout also tends to look like joylessness.

Man, knowing nothing else about your coworker, they sound like a completely joyless person. Coming up with fake titles for things is like, such a high fun-to-effort ratio. “Creativity and the essence of Human Experience” by Chat GPT. Boom, there’s one. “Cooking With Olive Oil” by Sam Altman. “IQ184” by Harukiezer Murakowsky. This is so fun and easy that it’s basically hack outside of situations where it is solicited.

Putting cream in my carbonara to see how my 8K 120Hz Nonna reacts

Well unfortunately it’s not diluted enough to be homeopathic, so it’s just off³ broadway

My current iteration of the etymology is that "dath ilani" anagrams to "HD Italian". As in, the dath ilani are an idealised version of Italians, making dath ilan a utopian version of Italy.

there's No Such Feasible Way for that imo

FWIW my understanding is the "Off"-ness is just decreasing theatre size, but gets (mis)construed as less prestige/fame/quality etc. Fame is probably fine for construing, but prestige/quality is orthogonal. Like you could conceivably have absolute theatre mega stars do an epoch-defining production in an intimate 50-seat theatre or something, and that would still be "Off-off-broadway".

OH that Jack Thompson. Yeah I remember now. Man, on one hand, his actions were at best misguided and at worst totally insane. On the other hand, IMO we wouldn’t know about him if video game people were by any measure calm or reasonable.

I don’t know who Jack Thompson is, so just pretend that I came up with some incredible, witty interleaving of references to waiting for godot, the torment nexus meme, and Jack Thompson