Viliam

Karma: 24,270

Viliam Mar 19, 2025, 9:30 AM
19 points
9
on: Do What the Mammals Do
I agree that something being “natural” doesn’t make it “right”. But “natural” is still a force of nature that you have to include in your predictions… unless you are okay with getting your predictions systematically wrong.
Applying this to the examples you mentioned:
Males are more aggressive in most animals; therefore, male humans should be expected to be more aggressive.
Yes, 100% agree. Notice that this doesn’t say anything about aggression being good or otherwise desirable; the statement is positive, not normative.
Do you have an alternative explanation for gender ratios in violent crime statistics?
Females are the natural caregivers in most mammals; therefore, human mothers should primarily raise children.
Okay, we have a “should” here; that is a mistake. But we could make a positive statement out of it, something like “on average, females will be more successful caregivers than males”, especially if they are randomly selected from the population (rather than self-selected).
Of course, “more successful” does not automatically translate to “should”; we need to balance it against other interests.
Hierarchies exist in many animal groups; therefore, human social hierarchies and inequality are natural and acceptable.
Here, I would make a statement like “human social hierarchies are a natural attractor, so if you want to avoid them, you need to think really carefully about how to design your group, because it is very unlikely to happen automatically”.
Alpha males dominate in many mammal groups; therefore, dominant, assertive men should naturally be leaders.
Similarly, something like “there are many dominant men, so you either need to accept that you will have a leader like this (and maybe focus on figuring out how to choose the best one out of multiple candidates) or you need to think really carefully about how to avoid this outcome”.
Animals eat meat; therefore, human meat consumption is natural and morally acceptable.
The positive statement would be something like: “you need to think really carefully about designing a vegetarian diet that will be healthy in long term, because the most likely outcome of ‘just don’t eat meat, duh’ is some kind of nutritional deficiency”.
Metaphorically speaking, opposing the nature is like opposing gravity. Yes, you can build airplanes and tall buildings. But you need to design them carefully, otherwise a disaster will happen. Just saying “I hate gravity, it is such an oppressive concept that it should not be allowed to mention in a polite society” is not going to do it.

Viliam Mar 17, 2025, 11:21 AM
2 points
0
in reply to: Ape in the coat’s comment on: Counting Objections to Housing
The people outside the town who buy houses here either expect to rent them expensively, or to use them as an investment because they expect the costs of housing to grow. (Or a combination of both.)
Refusing to build more houses means doing exactly the thing they want—it keeps the rents high, and it keeps the costs growing.
If you have 500 000 people in the town, and 100 000 houses are owned by people outside the town, you should build more houses until there are 600 000 of them (i.e. not only 500 000). Then the people outside the town will find it difficult to rent their houses expensively, and may start worrying that the costs will not grow sufficiently to justify their investments.

Viliam Mar 17, 2025, 11:12 AM
2 points
0
on: LLMs may enable direct democracy at scale
My problem with democracy is that most people are stupid. More precisely, they are relatively good at saying whether they are happy or unhappy, starving or fed, etc. They can give a relatively reliable “thumb up” or “thumb down” feedback to the government. But if you ask them about the specific steps that should be taken to make them better fed, etc., many of the popular suggestions will be quite insane.
For example, people can have a legitimate complaint about healthcare being inaccessible for them, and yet the suggestion many would propose will be something like “government should spend more money on homeopathy and spiritual healing, and should definitely stop vaccination and other evil unnatural things”.
This seems inevitable to some degree. We can’t realistically expect that everyone will be an expert on everything. And we want to allow feedback such as “the experts are hurting us, and we want that to stop”, but we don’t really want the non-experts to micro-manage the experts.
The traditional solution is to give people only the “thumb up/down” kind of feedback. For example, in capitalism, you can choose to buy or not to buy a certain kind of product or service, but you can’t e.g. go to a restaurant and demand that they start cooking meals according to your recipe, no matter how good that recipe sounds to you. But you can start your own restaurant that will cook according to your recipes, and then the customers will vote on the result.
Even this approach has many problems, because some things seem good in short term, but are harmful in long term, and these often get a “thumb up” from the non-experts. The more tasty food can be less healthy. The economic problems or successes of today may be a consequence of things that the previous government did.
The problem with democracy is externalities. People who vote for stupid things don’t only hurt themselves; they equally hurt their neighbors. It would be better to set up things in a way that when people insist on doing the wrong thing, they hurt themselves more than they hurt the others. But this itself is a subject to voting, and many people oppose it.
...shortly, I am worried that this would allow democratic micro-management, i.e. the rule of stupid.
That said, I am not sure what is the optimal level of democracy, but I am suspicious of the assumption that more is necessarily better.

Viliam Mar 17, 2025, 8:56 AM
2 points
0
in reply to: TsviBT’s comment on: TsviBT’s Shortform
Ah, then I believe the answer is “no”.
On the time scale of current human lifespan, I guess I could point out that some old people are unkind, or that some criminals keep re-offending a lot, so it doesn’t seem like time automatically translates to more kindness.
But an obvious objection is “well, maybe they need 200 years of time, or 1000”, and I can’t provide empirical evidence against that. So I am not sure how to settle this question.
On average, people get less criminal as they get older, so that would point towards human kindness increasing in time. On the other hand, they also get less idealistic, on average, so maybe a simpler explanation is that as people get older, they get less active in general. (Also, some reduction in crime is caused by the criminals getting killed as a result of their lifestyle.)
There is probably a significant impact of hormone levels, which means that we need to make an assumption about how the God-emperor would regulate their own hormones. For example, if he decides to keep a 25 years old human male body, maybe his propensity to violence will match the body?
tl;dr—what kinds of arguments should even be used in this debate?

Viliam Mar 17, 2025, 8:39 AM
2 points
0
in reply to: TsviBT’s comment on: TsviBT’s Shortform
Well, if we assume that humans are fundamentally good / inevitably converging to kindness if given enough time… then, yeah, giving someone God-emperor powers is probably going to be good in long term. (If they don’t accidentally make an irreparable mistake.)
I just strongly disagree with this assumption.

Viliam Mar 17, 2025, 8:20 AM
8 points
12
in reply to: TsviBT’s comment on: TsviBT’s Shortform
Sounds to me like wishful thinking. You basically assume that in 1 000 000 years people will get bored of doing the wrong thing, and start doing the right thing. My perspective is that “good” is a narrow target in the possibility space, and if someone already keeps missing it now, if we expand their possibility space by making them a God-emperor, the chance of converging to that narrow target only decreases.
Basically, for your model to work, kindness would need to be the only attractor in the space of human (actually, post-human) psychology.
A simple example of how things could go wrong is for Genghis Khan to set up an AI to keep everyone else in horrible conditions forever, and then (on purpose, or accidentally) wirehead himself.
Another example is the God-emperor editing their own brain to remove all empathy, e.g. because they consider it a weakness at the moment. Once all empathy is uninstalled, there is no incentive to reinstall it.
EDIT: I see that Thane Ruthenis already made this argument, and didn’t convince you.

Viliam Mar 17, 2025, 8:00 AM
2 points
0
in reply to: Jiro’s comment on: Counting Objections to Housing
Yes, if you have 500 000 people in town, you need to produce food for 500 000 people all the time. While if you have 500 000 people in town, you only need to build houses for 500 000 once.
But the logic of “there is a shortage of X, therefore the proper solution is to ban the production of X and hope that the problem will magically go away” is insane either way.

Viliam Mar 16, 2025, 11:18 PM
2 points
0
on: Counting Objections to Housing
“I’m tired of this simplified idea that building more buildings here will solve the affordable housing problem”
I am tired of this simplified idea that giving people more food will solve the hunger problem. (Insert sophisticated arguments about how supermarkets throw away lots of perfectly okay food, etc.) Therefore, making more food should remain banned.

Viliam Mar 16, 2025, 11:04 PM
5 points
0
in reply to: TsviBT’s comment on: TsviBT’s Shortform
Are people fundamentally good?
Maybe some people are, and some people are not?
Are they practically good?
Not sure if we are talking about the same thing, but I think that there are many people who just “play it safe”, and in a civilized society that generally means following the rules and avoiding unnecessary conflicts. The same people can behave differently if you give them power (even on a small scale, e.g. when they have children).
But I think there are also people who try to do good even when the incentives point the other way round. And also people who can’t resist hurting others even when that predictably gets them punished.
Given more information about someone, your capacity for having {commune, love, compassion, kindness, cooperation} for/with them increases more than your capacity for {hatred, adversariality} towards them increases.
Knowing more about people allows you to have a better model of them. So if you started with the assumption e.g. that people who don’t seem sufficiently similar to you are bad, then knowing them better will improve your attitude towards them. On the other hand, if you started from some kind of Pollyanna perspective, knowing people better can make you disappointed and bitter. Finally, if you are a psychopath, knowing people better just gives you more efficient ways to exploit them.

Viliam Mar 16, 2025, 10:40 PM
10 points
2
in reply to: danielechlin’s comment on: Any-Benefit Mindset and Any-Reason Reasoning
I’d like to know how you handle arguing for something like “usability” in the face of a morally urgent argument like “don’t be eurocentric.”
I would probably start with rejecting the premise that I have to listen to other people’s arguments.
(This makes even more sense when we know that the people who loudly express their opinions are often just a tiny minority of users. However, it is perfectly possible to ignore the majority, too.)
I think this is a mistake that many intelligent people make, to believe that you need to win verbal fights. Perhaps identifying as a rationalist can make it even worse, if you conflate “being rational” with “winning verbal fights”. The trick is to realize that it is perfectly possible to hear a verbal argument against doing X, and then do X anyway (without having to win the verbal fight first, or at all).

Viliam Mar 16, 2025, 9:44 PM
5 points
0
in reply to: jbash’s comment on: Davey Morse’s Shortform
Similar here. I wouldn’t want to constrain my 100 years older self too much, but that doesn’t mean that I identify with something very vague like “existence itself”. There is a difference between “I am not sure about the details” and “anything goes”.
Just like my current self is not the same as my 20 years old self, but that doesn’t mean that you could choose any 50 years old guy and say that all of them have the same right to call themselves a future version of my 20 years old self. I extrapolate the same to the future: there are some hypothetical 1000 years old humans who could be called future versions of myself, and there are many more who couldn’t.
Just because people change in time, that doesn’t mean it is a random drift. I don’t think that the distribution of possible 1000 years old versions of me is very similar to a distribution of possible 1000 years old versions of someone else. Hypothetically, for a sufficiently large number this might be possible—I don’t know—but 1000 years seems not enough for that.
Seems to me that there are some things that do not change much as people grow older. Even people who claim that their lives have dramatically changed, have often only changed in one out of many traits, or maybe they just found a different strategy how to follow the same fundamental values.
At least as an approximation: people’s knowledge and skills change, their values don’t.

Viliam Mar 15, 2025, 1:14 PM
6 points
0
on: Whether governments will control AGI is important and neglected
Notice how Elon Musk has positioned himself so that he has a chance to win both if the governments will control the AIs and if they won’t.

Viliam Mar 13, 2025, 9:12 AM
4 points
0
on: Social Media: How to fix them before they become the biggest news platform
I like the concept of Community Notes on Xitter, as a pushback against spreading misinformation. But now it seems that Musk will “fix” it, because his own tweets get often contradicted. Are there similar features on other social networks? How do they compare?

Viliam Mar 13, 2025, 8:39 AM
19 points
8
in reply to: mishka’s comment on: The Most Forbidden Technique
And this part is what Robin Hanson predicted about a decade ago. If I remember it correctly, he wrote that AI Safety was a low-status thing, therefore everyone associated with it was low-status. And if AI Safety ever becomes a high-status thing, then the people in the field will not want to be associated with their low-status predecessors. So instead of referencing them, an alternative history will be established, where someone high-status will be credited for creating the field from scratch (maybe using some inspiration from high-status people in adjacent fields).

Viliam Mar 12, 2025, 3:22 PM
18 points
4
on: The Most Forbidden Technique
I believe it is a clear demonstration that misalignment likely does not stem from the model being “evil.” It simply found a better way to achieve its goal using unintended means.
It is fascinating to see that the official science has finally discovered what Yudkowsky wrote about a decade ago. Better late than never, I guess.

Viliam Mar 12, 2025, 2:51 PM
2 points
0
on: You don’t actually need a physical multiverse to explain anthropic fine-tuning.
As I see it, there are two possible explanations for a fine-tuned universe:
- an insane amount of luck (or something other than luck, such as a supernatural force)
- multiverse
The argument for multiverse is precisely that it does not require the insane amount of luck.
Your argument is that with the insane amount of luck, the multiverse is not necessary.
That is correct, but then we are back to the original question: why did we get so extremely lucky?

Viliam Mar 10, 2025, 6:47 PM
5 points
−1
on: Have you actually tried raising the birth rate?
I agree with the spirit of your suggestion—often “it is known” that something couldn’t possibly work, based only on armchair reasoning, or one half-assed attempt made a few decades ago, in a different country, with N=20.
That said, literally cash for babies feels somewhat dysgenic (though, maybe if we actually did the experiment, the results might surprise us). It seems like it would appeal most to people with short-term thinking, the most poor people (which is probably correlated with various dysfunctions), and psychopaths who only want cash and don’t care about what happens to the baby afterwards. I don’t insist that a good policy needs to appeal to the elites, but it would be nice if it appealed to the average people more than to those at the bottom.
I would prefer financial support in a form of free kindergartens, free school lunches, free health insurance for children (if there are countries that don’t already have that), even free babysitting in the afternoons and weekends. Make it a few thousand dollars a year, but with vouchers instead of cash.
I could also imagine various kinds of non-financial support (on top of the financial support, not as an alternative), such as more libraries specialized for children, cheap tutoring, coordinating second-hand selling and buying things for children, etc.
Also, build more playgrounds, and buildings that can only be used for activities for kids (clubs, etc.).

Viliam Mar 10, 2025, 6:22 PM
2 points
0
in reply to: Canaletto’s comment on: when will LLMs become human-level bloggers?
Okay, that pretty much ruins the idea.
Makes me think, what about humans who would do the same thing? But probably the difference is that humans can build their credibility over time, and if someone new posted an unlikely comment, they would be called out on that.

Viliam Mar 10, 2025, 8:50 AM
6 points
0
in reply to: johnswentworth’s comment on: johnswentworth’s Shortform
build a social circle which can maintain its own attention, as a group, without just reflecting the memetic currents of the world around it.
Note that it is not necessary for the social circle to share your beliefs, only to have a social norm that people express interest in each other’s work. Could be something like: once or twice in a week the people will come to a room and everyone will give a presentation about what they have achieved recently, and maybe the other people will provide some feedback (not in the form of “why don’t you do Y instead”, but with the assumption that X is a thing worth doing).

Viliam Mar 10, 2025, 8:18 AM
5 points
3
in reply to: Michael Roe’s comment on: when will LLMs become human-level bloggers?
I think you don’t need a lot of agency to write comments on Less Wrong. I imagine an algorithm like this:
- After an article is written, wait a random time interval between 15 minutes and 24 hours.
- Read the article and the existing comments.
- Prepare a comment that you believe would get most karma (you can learn from existing LW comments and their karma).
- Think again how much karma would your prepared comment probably get. In your estimation, include the fact that LW readers do not like comments that seem like written by an LLM.
- If you conclude that the expected karma is 5 or more, post the comment. Otherwise, do not comment on this article.
I imagine that the “learn from existing LW comments and their karma” would be the difficult part, because the more comments you need to process, the more work it is. But otherwise, this seems relatively simple; I am curious how well would such algorithm be received.