Canaletto

Karma: 349

Canaletto 22 Jun 2026 12:35 UTC
11 points
10
in reply to: Wei Dai’s comment on: Wei Dai’s Shortform
I would prefer hearing the actual conversation, something something subliminal learning. I’d rather also hear how you say that stuff, not just the text TTS-ed.

Canaletto 22 Jun 2026 12:31 UTC
1 point
0
in reply to: Buck’s comment on: Buck’s Shortform
I mean, they are mostly the same “take over the world, tile it with something” agents? I guess minimizer would be motivated to work on blowing up the world e.g. by searching for vacuum decay triggers—but that’s also a sort of take over / tiling.

EDIT Okay, I guess, they have opposite preferences on [human civ vanishes without a trace, humans get to have glorious transhumanist future], but I don’t think it’s all that relevant, as it’s in low utility corner for both of them? Well, maybe it’s relevant for not that powerful / scalable such agents.

Canaletto 21 Jun 2026 18:30 UTC
1 point
0
in reply to: snarles’s comment on: leogao’s Shortform

(1) because the God of Christianity truly exist

But what reasons you have to think so? It seems to me you think Bible is the same kind of “cool story” as Greek myths, Norse myths, Aztec myths, etc. You agree with atheists on facts.

So, what privileges that God? Your wishful thinking?

Some (most) religious people think there are ironclad reasons to privilege those particular Myths. And I somewhat agree with their epistemic, let’s say, approach, even if I disagree on facts with them. (even if yes, those conclusions are too heavily oiled with wishful thinking)

Canaletto 19 Jun 2026 14:48 UTC
1 point
0
in reply to: snarles’s comment on: leogao’s Shortform
I think your whole approach is unsound. You have no beliefs about state of the world. Many religious people do have actual beliefs, they expect to find evidence of the flood or Jews in Egypt, or of miracles of Jesus, of all the figures mentioned in bible. As God is Truth, and would not egregiously lie, and stuff.

And by that authority they think the principles that the Bible and Church recommend are good and righteous. Why have principle of “being joyful”? Because God says so.

They think, why not principle of “being brave” that Thor commends? Because Thor does not exist, and holds no authority, as opposed to how Christian God exists, actually, verifiably.

But you, you have no disagreements about facts with atheists. You just think the Christian principles are great for some reason? Why not Neo-Pagan principles?

Canaletto 18 Jun 2026 19:03 UTC
2 points
1
on: AI that represents you can’t be neutral.

Take an autobiography. Split it in half. The first half is training data; second half is held out text

Well, autobiography is written at the late time wholesale, so there would be a lot of leaks. Diary would be better, being written chronologically would help. But still there would be a lot of selection, like you do not include diaries from people who wrote two entries and gave up, and general propensity to write them in the first place.

Canaletto 15 Jun 2026 10:14 UTC
1 point
0
in reply to: kbear’s comment on: The Power to Punish
Well, it certainly would be more cruel to be cruel in situation where you could as well be kind.

Canaletto 14 Jun 2026 17:50 UTC
7 points
0
on: The Hidden Structures of Problems
67. Floating Definition

The problem which is stated abstractly enough that it’s unclear what exactly it entails or in what concrete situations it happens.

Canaletto 13 Jun 2026 21:43 UTC
9 points
1
on: Not telling is lying
There is a term for egregious version of this, “lie by omission”, when you omit critical information with intent to form false impression in recipient.

Interesting examples from here:

You break an item, then report to its owner that the item is broken. Which it is.

“Imagine you had a work meeting at noon, and plans to go see a concert at night. You don’t feel like going to the concert, so you tell the person you’re going with ‘I can’t make it tonight, I have a big work meeting.’ You’re not missing the concert because of the meeting, but you’ve made it sound like you are. That is a lie of omission.”

When someone is selling a car and they say that it is serviced regularly, but do not say that there was a problem found when it was serviced.

A great lie by omission I once gave was that I missed class in college because I was in the hospital. But I was in the hospital because I got injured while skipping class to play football.

From here:

Mom asks son if he did sneak out of the house at night. Son answers that he did not sneak out of the house through the door.

Kinda awkward, but it’s nice example of a person adding details to their answer that excludes some pathways for the question to be fulfilled and hope that questioner does not notice a hole.

Canaletto 13 Jun 2026 20:13 UTC
2 points
0
in reply to: Kai בראונר’s comment on: Kai בראונר′s Shortform
https://en.wikipedia.org/wiki/Ultimatum_game

Canaletto 12 Jun 2026 18:31 UTC
1 point
3
in reply to: Brendan Long’s comment on: Brendan Long’s Shortform
More like “caved in”.

Canaletto 12 Jun 2026 14:01 UTC
4 points
2
on: If you, a human, can imagine red and green being swapped, you are probably conscious
I’m not sure what’s the thing you argue with? Like, yes, you can modify my retina which is actually part of my brain, if you look at embryology, or my specialized neural pathways that shuffle info, like LGN.

If you meddle with higher regions, then uhh how do I know that the guy on the other end of this is me actually? You can meddle in such ways that I definitely would not think he is me, like reshaping my brain to match someone else’s and ways that would probably preserve it, like deleting 10 random neurons? It’s kinda question begging.

Thus, people’s values are in fact pointing to the context of their experiences, to their qualia, not to actual world states

Uhh, they are part of the world, and as you just pointed to, they have brain states that can be modified, so they dislike their brains being in some states, right?

Canaletto 11 Jun 2026 19:42 UTC
2 points
1
in reply to: snarles’s comment on: leogao’s Shortform
There are some books of the Bible, such as the books of Samuel and Chronicles, which are harder to interpret as metaphor—it seems there must have literally existed a King David.
So, hypothetically, if there were no King David or anything close at all, would you say “oh no, the bible lied to me!” or “it’s all more weirdly and misleadingly metaphorical than I thought!”—I think some people got that moment with Jews in Egypt or with flood.
The best example I can give of a domain where I might tend to disagree with scientific consensus is with regards to the placebo effect in medicine
That’s kinda funny. I don’t think you are religious in the traditional sense, you are kinda into spirituality with faint Christian flavor. Which is not that surprising with Protestantism tbh.

Canaletto 11 Jun 2026 8:50 UTC
−1 points
−7
in reply to: Vanessa Kosoy’s comment on: Vanessa Kosoy’s Shortform
And those who hindered it, would be punished?

Canaletto 10 Jun 2026 20:14 UTC
1 point
0
in reply to: avturchin’s comment on: The Three Filters: Why Almost Every Plan to Survive ASI Fails Miserably
Well, capabilities are more about having large effects, and alignment is about having effects that are desirable to the principal. You can imagine a 2x2 matrix with aligned/unaligned, highly capable / slightly capable. Aligned + highly capable is the best, unaligned + highly capable is the worst.

Canaletto 10 Jun 2026 7:39 UTC
2 points
0
in reply to: snarles’s comment on: leogao’s Shortform
Do you actually have any uhh factual disagreements with atheists? Did all the stuff from Old Testament happened, or is it all weird and misleading metaphor? Was Jesus a spellcaster or just an inspired guy with awesome ideas? Did God micromanage the creation of humans or did he outsource it to a meatgrinder of evolution?

Canaletto 8 Jun 2026 15:36 UTC
24 points
15
in reply to: Kaarel’s comment on: leogao’s Shortform
“The real Magic was friends we made along the way!”

“Wrong. FIREBALLLL *explosion* ”

People really believe there is a God, it’s not fair to redefine it to point to some Leviathan-like thing which arises from people acting like it breathes down their necks. For one thing, the religious people would say that you are wrong in general and about their position in particular.

Canaletto 3 Jun 2026 21:43 UTC
13 points
5
on: My favorite depiction of utopia
What do I feel about this world? About this state of affairs?

I think, mostly annoyance. It’s annoying way for it to turn out. Like, omg whatever, let’s go have an orgy with a hundred ’spians or something. Then it gets boring, then that me decides to learn all that there is available to learn by directly modifying my brains, then he gets extra bored, and speeds up time subjectively, waiting for something to happen, but it never does. The End.

I think annoyance comes mostly from there being this entity, instead of just humans getting some power and negotiating some deal among themselves, or at least the entity approximating that process. Or something.

Well, also the observable universe probably contains some aliens, what’s up with them? Do chimps get their own ’spians? What’s the status of other MWI branches and stuff? Many other questions.

Canaletto 3 Jun 2026 19:34 UTC
1 point
2
in reply to: Matthew Khoriaty’s comment on: Taking the Training Wheels Off: Aligning LLMs without Personas
So, you plan to experiment with MuZero type stuff, where you train an agent with no human imitation learning whatsoever?

Canaletto 2 Jun 2026 11:00 UTC
1 point
0
on: Taking the Training Wheels Off: Aligning LLMs without Personas
Okay, let’s try to classify non apples here.

You either deal with an agent, and then the easiest things around to imitation learn are humans. Those do have personas. Maybe you need to shift this into non-human-like reasoning mode? E.g. some kind of neuralise or constructed language? But that sounds difficult for alignment, and it might still get seeded with human imitation, just non transparently. And all the problems with neuralise.

Or maybe you need more power-armor design? E.g. edit prediction. This also might give rise to an agent in background. And be less powerful in the first place.

Something other?

And to be fair all of this sounds like a pretty high capability externality line of thinking.

Canaletto 1 Jun 2026 7:26 UTC
1 point
−2
in reply to: Zack_M_Davis’s comment on: Comment on “Banning Said Achmiz”
Well, good point. But there are clearly situations where this fails, like suppose a user with a lot of karma starts unambiguously insulting someone, e.g. throwing slurs. They should be warned/banned for this one act! Karma mechanisms would not react appropriately, as only a small number of people would see this comment and react to it.