Canaletto

Karma: 319

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
1 point
0
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
12 points
4
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.

Canaletto 28 May 2026 20:44 UTC
1 point
0
in reply to: Arjun Panickssery’s comment on: Arjun Panickssery’s Shortform
Well, you can consider some situations and think, does it give good recommendation in them? If not, maybe it’s a motivation to start the search for other principles?

Here is one, even more exaggerated:

Imagine even stronger predictor. It offers you 20 Newcomb’s games in a row. And the predictor is already gone, dead etc. For simplicity boxes you didn’t take burst into flames or something. CDT agent will not experiment with this and just straight up two box 20 times in a row. Where as normal humans would pick one box some of the time, see it gives them more money and switch their strategy.

Like, what percent of humans would two box 20 times in a row you think? Like, 0.1%? Some philosophy professors among them apparently.

Canaletto 28 May 2026 20:32 UTC
2 points
0
in reply to: Arjun Panickssery’s comment on: Arjun Panickssery’s Shortform
1. Maybe principle of dominance gives wrong action recommendations in some situations? How do you evaluate your principles?
2. That’s not the point? The point is, you would commit to “check on what date hour and minute Omega looked at me and one box if after, two box if before”, with whatever method you have you can constrain your future actions. Which is kinda crazy, like, just commit to one boxing if you are into commitments.

Canaletto 28 May 2026 20:11 UTC
1 point
0
in reply to: Arjun Panickssery’s comment on: Arjun Panickssery’s Shortform
Yeah, the most interesting Newcomb’s problem is the one where you learn about it for the first time after encountering it. And you obviously should one box, duh.

Also note, that committing to one boxing, under causal point of view, makes sense not for the Newcomb’s problems you encounter later, but only for Newcomb’s problems where Omega inspected you after the date of commitment, which becomes a magic number. Kinda weird? If you work by commitments, why not commit to one boxing in general?

Canaletto 28 May 2026 9:36 UTC
1 point
0
in reply to: J Bostock’s comment on: Jemist’s Shortform

It would be really good if someone could solve agent foundations

Do you think it would have no capabilities relevance? What if it’s like “Here is an embedded version of AIXI that actually works” and everyone is like great, let’s run in on this super duper computer for 10k hours, with NNs as heuristics / glue. And you are like, oh no

Canaletto 25 May 2026 21:07 UTC
4 points
0
in reply to: nesiacel’s comment on: nesiacel’s Shortform
d) Expansion is at near c, and so it’s unlikely that Earth would be in a thin rim where it can see the expansion, but no vN probes arrived yet.

Also, those considerations do not depend on this being some misaligned AI as opposed to just aliens, you know, who want to expand. Or at least some fraction of aliens who do.

Canaletto 25 May 2026 19:06 UTC
2 points
0
in reply to: ChristianKl’s comment on: Samuel Ratnam’s Shortform
That’s an interesting question in isolation. I guess the lowest selection would be when the whole tree is un-pruned, e.g. when bacteria split, but no bacteria die. But there would be still selection for speed of reproduction? Or, in opposite case, when you have only 1 bacterium, and it splits and you invariably kill one of its descendants, and repeat. That also has low selection I guess? So, something in between?

There are probably better answers if you know actual biology.

EDIT after consulting with some LLMs there is actually pretty standard terminology about this. Basically large heritable fitness differences and large population where variation can translate into frequency change.

https://en.wikipedia.org/wiki/Selection_coefficient

https://en.wikipedia.org/wiki/Effective_population_size

https://en.wikipedia.org/wiki/Mutation–selection_balance

Canaletto 25 May 2026 10:55 UTC
1 point
0
in reply to: Ape in the coat’s comment on: A relatively brief explanation of Boltzmann Brains
Well, then you take that consistent universe at face value and notice it should (maybe) produce shitton of BBs. That’s the point of discussion of this post, I guess.

Canaletto 25 May 2026 10:43 UTC
1 point
0
in reply to: Ape in the coat’s comment on: A relatively brief explanation of Boltzmann Brains
Yeah, it doesn’t, but not through your argument.

Canaletto 25 May 2026 10:02 UTC
1 point
0
in reply to: Ape in the coat’s comment on: A relatively brief explanation of Boltzmann Brains
That’s not how evidence works, you have two theories, and you have some observation. Is this observation expected on H1? Yes. On H2? Yes. So, it’s not evidence either way.

The point that Eliezer (cited from Feynman) makes, is that given Boltzman brains, you would expect partially unordered instantiations to be more frequent. Partially unordered as a part of momentary experience.

Not, “first me, then Bezos”, this point still uses reliable history as a primitive.