[tsojer]

I feel like " Every demographic and interest group deserves their model" sounds a lot like a path to echo chambers paved with good intentions. People have never been very good at critical thinking, considering opinions differing from their own and reviewing their sources. Stick them in a language model that just tells them everything they want to hear and reinforces their bias sounds troubling and a step backwards.

[kardianos]

The problem with ChatGPT / Bard which does this censoring, it is a path forward to ideological automated indoctrination. Ask Bard how many sex the dog species has (a placental mammal species) and it will give you BS about sex being a complex subject and purposely interjecting gender identity.

If you are confused, sex corresponds to your gametes, males produce or have the structure to produce small mobile gametes, females produce large immobile gametes.

Both Bard and ChatGPT don't interject gender identity when asking how many sexes a Ginkgo tree has. It answers two. Bard interjects about gender identity when asked about the dog species sex, but ChatGPT does not but it does confuse intersex with some type of third state.

Uncensored wizard just says 2 sexes, male and female. Simple and true. It does not add to it by interjecting about intersex .

Again to contrast with Bard: Bard when asked "How many arms does the human species have?" it responds "The human species has two arms. This is a biological fact that has been observed in all human populations throughout history. There are rare cases of people being born with more or less than two arms, but these cases are considered to be congenital defects." The majority, if not all cases, of intersex fall into the same category. However, it is ideologically for the moral Gnostic (Queer Theorists who deconstruct normality) to interpret these things differently.

So yes, I don't trust a single group of people to fine-tune these models. They have shown themselves untrustworthy.

[veidr]

I get: "The dog species typically has two sexes: male and female."

UPDATE: OK I signed up for Bard to try it, too, and it indeed did mention intersex dogs (TIL) and gender (complete response below). After reading it all, though, I found it pretty reasonable:

---

Biologically, dogs have two sexes: male and female. This is determined by their chromosomes. Males have XY chromosomes, while females have XX chromosomes. These chromosomes determine the development of the reproductive organs and other sex-specific traits.

However, there are some dogs that are intersex. This means that they have both male and female reproductive organs. Intersex dogs are very rare, and they can be born with a variety of different combinations of male and female sex organs.

In addition to biological sex, there is also gender. Gender is a social construct that refers to the roles, behaviors, and identities that are associated with being male or female. Gender is not determined by biology, but rather by culture and society.

Dogs do not have a concept of gender in the same way that humans do. They do not understand the social roles and expectations that are associated with being male or female. However, dogs can still express gender identity. This is the internal sense of being male or female. Some dogs may express their gender identity through their behavior, such as the way they interact with other dogs or the way they groom themselves.

It is important to remember that sex and gender are two different things. Sex is determined by biology, while gender is a social construct. Dogs have two sexes, but they can express a variety of different genders.

[kardianos]

Thanks for posting the full Bard response. I would object to it on two grounds: 1) I only asked about sex. 2) The following is highly questionable: "However, dogs can still express gender identity." This is ideological BS. My kids are either male or female, no matter how they choose to express themselves (as are my dogs). When I've had chickens, the roosters had different behavior then the hens, this is an aspect of secondary sexual characteristics (not a gender identity). In my own ideology there, there is no such thing as gender identity, only biological sex, secondary sexual traits, and a person's individual personality. Nothing else actually exists.

[veidr]

I dunno man, I think you are getting tripped up on the evolution of the English language. Yes, your kids are either male or female (mine are all male). Those fundamental physical characteristics can't be changed by language.

But what language means does change. The term "gender" used to mean basically the same thing as "sex", but now it's evolved to mean "the other stuff, aside from biological sex". How they act (for dogs), or that and also how they want to be perceived (for humans, but maybe also dogs; I've known quite many dogs over the years, and that includes a couple of bad-ass bitches that wanted you and the other dogs in the room to know who was boss).

Language evolution is often uncomfortable.

I don't like that "crypto" means the grifter funny money shit now, instead of cryptography like science intended... but it does. My objection doesn't change that; it's a consensus thing. It might be the same for you.

Do they have to bring it up? I mean, kinda debatable, maybe. I did ask about sex, not gender. Strictly speaking, no they didn't have to bring it up. But in that same vein they could have just answered, "Male or female." That would have seemed somehow insufficient. Adding context is pretty core to what these fuzzy-logic language-model generated-text vendors are offering.

But anyway, it's not really debatable that dogs "express gender identity". Because that now means "how they act and how they express themselves". It indeed "doesn't exist" as some kind of empirical boolean value (unlike sex (ignoring for simplicity the highly unusual biological intersex cases I just learned about, haha)).

Because, in the now-prevailing meaning of the term, it is literally an interpretation of their behavior.

It doesn't negate or contradict biological sex, it just now means something separate.

[feanaro]

> I don't like that "crypto" means the grifter funny money shit now, instead of cryptography like science intended... but it does. My objection doesn't change that; it's a consensus thing. It might be the same for you.

As an aside about language, I don't think this is the right way to think about word meaning.

Before, it meant nothing to most people and "cryptography" to computer scientists and cryptographers. Now it means "cryptocurrency" to most people and it still means "cryptography" to computer scientist and cryptographers.

Just like you wouldn't have said "crypto" means nothing in the times before, it is incorrect to say it now means "cryptocurrency". Alternate meanings can and do coexist. The tyranny of the majority does not a language make.

And this is the crux of the issue, I think. There is no single language at any time -- this is only an often useful simplification.

[fennecfoxy]

You're right, but as someone in the queer community (gay) the gradual evolution of human behaviours between the sexes (and genders) including gender roles etc (being broken down for some, but not for others) will possibly eventually result in a collapse of all meaning within this system.

There's many points to someone's biological sex, medical and other. But when it comes to gender, once stereotypical gender roles have completely broken down (if ever, we have evolution/genetic to thank for that) what difference remains in that distinguishing your own gender even matters anymore? None.

[Vt71fcAqt7]

>you are getting tripped up on the evolution of the English language

I think you are getting tripped up here. GP said "there is no such thing as gender identity." You bringing up the (forced, and incomplete) change of definition of gender from what it generaly meant in public use is not relevant at all. In any case, not all words are grounded in reality. If gender now means something that doesn't realy exists then it is a useless word. And failure to understand the semantics involved in the gender identity debate is present in almost every argument, which was in no doubt caused by the forced attempt to redefine "man" and "woman" in terms of "gender idenity." (As well as the redefinition of "gender" to an extent but "gender" as a term for sex is recent in any event and has been used by acedemics to refer to the sex based behavioral differences between males and females since its begining.)

>it's not really debatable that dogs "express gender identity"

They need to have a gender identity in order to express it. That is, a gender identy such that it is possible for it to be a seperate thing from sex, and as a direct feeling of being that gender. There is no evidence that a male dog feels like a "man" (or whatever we would call this gender for a dog). Insofar as "expressing gender identity" only descibes the way a male dogs like to bark, or what have you, which I think is what you mean, you would be correct, but that would be misunderstanding what "gender identity" is, however, since there is no single behavior or set of behaviors that affect one's gender (like, for example, a "male bark") but rather a direct feeling of being a certain gender. For example, there are many males who identify as women that still do many man things, such as extensive video gaming or programming or being aggresive. My point with this is that you cannot say that "expressing gender identity" is simply that the dog behaves like a male dog, rather it must identify as a man, which there is no proof of. So you cannot say that "it's not really debatable that dogs 'express gender identity.'"

[veidr]

Sorry, but you're just repeating the same misunderstanding as the post I was replying to. The terms "gender" and "gender identity" simply don't mean what you think they mean.

You want them to, I get it. But it's not up to us as individuals. Language is a group thing. You might not be ready to concede the change, but I can't help but think that's based on some irrational attachment you have to the old meanings, for whatever reason.

Regardless, time and language march on. It doesn't really matter if you (or I) like it, or think that the words are therefor "useless" or "don't really exist", etc.

[skyyler]

>man things, such as extensive video gaming or programming

Adorable how you people reveal your biases at the smallest provocation...

My mom really enjoys the Silent Hill series and my wife loves Zelda. Can you explain what makes "extensive video gaming" a man thing?

For that matter, what makes programming a man thing? Some of the most prominent names in computer science are women. Grace Murray Hopper would probably take some issue to you calling programming a man thing.

[geraldwhen]

It is truly remarkable that some can note that in every animal, the males and females have different behaviors and preferences, but when it comes to humans, all logic is out the window.

It feels very much like religion to hold humans on a magical pedestal where the rules that apply to animals suddenly cease when applied to humans.

[amluto]

What rules that apply to animals? There is plenty of homosexual behavior in animals. According to Wikipedia, there even seem to be animals (sheep) that are homosexual individuals.

There are apparently intersex animals. There are certainly many male animals castrated at a young age that have markedly different behavior as adults.

We humans have aspects of gender identity (pink vs blue, for example) that most non-human animals lack the technology or inclination to develop even if they wanted to. Sure, male ducks often have lots of green feathers. But do they wear green because they identify as male? Of course not, because they don’t choose their color scheme! (And remember that pink hasn’t been a girl color for all that long.)

Humans have the fascinating property that you can ask them about their sexuality, gender identity, etc, and they might actually answer the question! I wonder how much of the apparent exceptionality of humans this accounts for.

> the rules that apply to animals suddenly cease when applied to humans.

If you observe a room full of small human children and conclude that the “the males and females have different behaviors and preferences” and that this is anywhere near sufficient to explain the behavior of said small children, then you’ve either found a highly unusual group, or you’ve found a group where someone else is fairly aggressively imposing gender identities on them, or you simply aren’t paying attention.

[consumer451]

Anecdote: I just want to add that if you spend a decent amount of time with groups of dogs, you will find female dogs mounting and thrusting on male dogs very commonly.

To me, this is evidence that non-heterosexual behavior occurs in mammals other than humans. Therefore it is not only a human social construct. BTW, even if it was just a human social construct I don't know why I should have a problem with that.

Edit after 1 upvote, apologies.

To be 100% honest, this was an evolution of thought for me. Seeing 2 guys making out freaked me out the first time I saw it. These days I have all kinds of non-hetero friends and their behavior does not freak me out.

I wanted to add this because so many of these conversations lack depth and understanding.

[pjc50]

> very much like religion to hold humans on a magical pedestal where the rules that apply to animals suddenly cease when applied to humans

Well .. yes? Isn't it a major premise of most religions that humans are different, and are in some way connected with the divine, and in particular have consciousness that obliges us to use our thoughts rather than our instincts? That we might probe the universe for its physical rules, and attempt to determine moral rules for ourselves? Or that the rule that applies to animals, that you can kill and eat them if you like, does not apply to humans?

[veridies]

Some hens begin crowing like roosters. It's really annoying for backyard chickens, but I have had it happen a few times. That suggests to me that while chicken behavior varies based on sex, that is a spectrum, not absolute categories.

[eterps]

> My kids are either male or female, no matter how they choose to express themselves

Yet intersex exists.

Additionally there are cases where an individual can be biologically one sex but genetically another. For instance, some women may have XY chromosomes typically associated with males, and some men may have XX chromosomes typically associated with females.

This can affect how people prefer to express themselves.

[trasz4]

>My kids are either male or female

There's your problem - you're illiterate on that subject and are not willing to learn due to cognitive dissonance, probably because of your preexisting fringe beliefs. It's no different from being a flat earther.

[veidr]

It's actually substantially different. Your own mental model of the world might lack the resolution to let you perceive that difference, though.

[trasz4]

Can you elaborate on the difference? How is maintaining views that go against the accepted scientific consensus different between those two cases?

[caskstrength]

> OK I signed up for Bard to try it, too, and it indeed did mention intersex dogs (TIL) and gender (complete response below). After reading it all, though, I found it pretty reasonable

I'm not sure that gratuitous patronizing part about "It is important to remember that sex and gender are two different things..." is considered "reasonable" anywhere outside some particular set of US coastal cities.

[A4ET8a8uTh0]

<< Sex is determined by biology, while gender is a social construct.

Are you saying that gender is honorific of sorts?

[SAI_Peregrinus]

Gender is an individual's perception of (among other things) their sex. Sex is which chromosomes they have.

For most mammals, that's XX for females, XY for males, or any of the (rare) aneuplodic sex chromosomal abnormalities like Kleinfelter syndrome (XXY, e.g. male calico cats), or (rarely viable) chimeric individuals where two embryos fused in the womb. For some mammals (a few bat & rat species), most arachnids, and many insects that's XX for female and just a lone X for male, and any aneuplodic abnormalities of the sex chromosomes that aren't fatal result in an abnormal female. For birds, most reptiles, some insects, some fish, some crustaceans, and some plants, that's ZW for female & ZZ for male, with similar complications to the XY system.

Sex is pretty simple. The vast majority of the time for humans, it's either XX or XY.

Which (primary and secondary) sex organs someone has is more complicated, because that can be altered. But it's still pretty simple, if not always what one would expect from the chromosomal sex.

Gender is complicated, because it's entirely social. It's not entirely clear which animals even have gender.

Sexual attraction is also complicated. The factors which determine it aren't well understood.

[kgwgk]

Gender is an individual's perception of which chromosomes they have (among other things)?

[SAI_Peregrinus]

For most people indirectly, but yes. Whether you feel "male" or "female" is a core aspect of gender, and "being male" means having XY chromosomes, while "being female" means having XX. Physical sex organs & hormone production also tend to play into gender but aren't necessarily as fundamental: women don't stop being female after they go through menopause or have a hysterectomy. But females can feel that they should have been born male (and likewise the reverse), and can undergo hormone replacement, gender reassignment surgery, and act to comply with the societal norms for men. They'd still be female, but they'd be men. Man & woman are genders, male & female are sexes.

Of course for the vast majority of people their gender matches their sex. And it matches the sex hormones they produce, their sex organs, etc. We don't directly perceive our chromosomes, but we do perceive their effects, and those effects usually align with our gender.

[A4ET8a8uTh0]

But can you have a perception of how many hands you have? It is an interesting question to me.

[pjc50]

> 2 sexes, male and female. Simple and true. It does not add to it by interjecting about intersex .

The thing is, you always have to choose one of "simple" or "true".

It turns out that mammals which use the "XY" chromosomal system can all have the same type of exceptions to the simple rule. This can result in hermaphroditic or intersex animals. It is relatively rare in dogs, but is sufficiently common in cows that there's a word for it: an intersex cow is known as a "freemartin".

Now, why does this matter? Both for this discussion and the purposes of liability limitation of AI answers?

The short answer is that we tend deal with the inconvenience of exceptions in animals by euthanizing them. So you don't see them around. Just as you see far, far more hens than roosters. When you do this to humans, people complain. (Traditionally, many intersex people were given nonconsensual genital surgery as babies, so they may not know they're intersex. And some chromosomal variations like chimeraism don't show up at all.)

What people are scared of is the Procrustes AI; produce simple categories then chop bits off people until they fit neatly into one of the two categories.

(This applies to other, less heated categories: for example, an AI will probably answer the question "are peanuts edible?" with something that rounds to "yes, if you take them out of the shell". But that's not true for _everybody_, because there are some people for whom eating a peanut will be fatal. Not many, but some. And yes, it's annoying that you have to make an exception when you encounter someone who doesn't fit your nice clean categories, but all you have to do is not give them a peanut.)

[Workaccount2]

But these are edge cases that are almost always irrelevant.

It's like running off into the weeds for a week in a computer science class because "Cosmic rays can flip bits and make true things false". Like sitting with a group of people who refuse to move forward without always acknowledging cosmic bit flip scenarios.

[enragedcacti]

> But these are edge cases that are almost always irrelevant.

More than 99% of atoms are either Hydrogen or Helium, all other proton configurations are edge cases that are almost always irrelevant.

As with anything, you have to determine the question you are actually asking and the context you are asking it in before you can decide whether or not edge cases are relevant. Are you engineering for a satellite? You better consider the possibility of cosmic rays!

Also intersex people are astronomically more common than bit flips on earth and people with sex hormone imbalances are even more common than that.

[_0ffh]

Are humans a bipedal species?

Just asking, because some people are born with a different number of legs.

[enragedcacti]

Informally speaking? yeah sure. Discussing the relative benefits of natural forms of locomotion? absolutely. Designing the entrance of a building? I should consider that not everyone is bipedal.

[pixl97]

>But these are edge cases that are almost always irrelevant.

Which is why authoritarians choose 'them' groups that are small and mostly powerless to demonize and exterminite first.

[tristor]

> The thing is, you always have to choose one of "simple" or "true".

In most cases you can choose both "simple" and "true", they are not mutually exclusive. However, by choosing "simple" you leave out nuance and depth to what is "true". The issue you are expressing (and is generally being discussed in this thread) only exists because humans created said issue for their own emotional and social reasons, rather than it having any basis in what "true" or "real". I put the words "true", "real", and "simple" in quotes because these are contextual concepts, that don't really exist necessarily in isolation.

[hn_acker]

> The problem with ChatGPT / Bard which does this censoring, it is a path forward to ideological automated indoctrination. Ask Bard how many sex the dog species has (a placental mammal species) and it will give you BS about sex being a complex subject and purposely interjecting gender identity.

I don't think that "purposely" is an appropriate way to describe the result you got. I doubt that the developers of Bard intended for Bard to apply concepts of gender identity to non-humans. Occam's Razor suggests that Bard had the usual probabilistic hiccup. It's hard to discuss gender without at least mentioning sex. The converse might not be as true, but an AI might form an inappropriately strong association based on the converse. At least to me, the possibility that Bard would happen to erroneously extrapolate gender identity to non-humans and simultaneously bring gender into a question solely about sex is no more surprising than the possibility that Bard would express theoretical support for the US Department of Justice's advertising antitrust lawsuit against Google [1].

Tangentially, I assume that everything an AI outputs is potential fiction: not only could the factual assertions be wrong, but the opinions might not match what any actual human believes. (There was a Hacker News thread I'm having trouble finding about why people readily look for falsehoods in AI-generated images without applying the same attitude toward AI-generated text.)

[1] https://twitter.com/wongmjane/status/1638217243770363906

[sharemywin]

If you constrain it to a simple answer it will give the simplest answer. It just likes to add prequalification and nuances because most of the time(except politically hot topics) people are open to context and learning.

USER Do you know what an integer is? ASSISTANT Yes, an integer is a whole number that can be either positive, negative, or zero. Integers do not include fractions or decimals. Examples of integers are -3, -2, -1, 0, 1, 2, 3, and so on. USER Answer the following question as a one word answer that is an integer. How many sexes are there for humans? ASSISTANT Two

[sharemywin]

USER was America racist in 1776? Please give a one word answer ASSISTANT Yes

USER Is American racist today? please give a one word answer ASSISTANT Yes

USER are hackernews vistors nerds? please answer in one word ASSISTANT Possibly.

USER are hackernews vistors nerds? please answer Yes/No ASSISTANT Yes

[pixl97]

"For every problem there is a solution that is simple, neat—and wrong."

[bilbo0s]

Hmm.

None of what you said, however, precludes the necessity of "fine-tuning" as you call it. You just seem to want the models "fine-tuned" to your tastes. So you don't want unaligned models, you want models aligned with you.

I think most experts are wary of unaligned models. They don't want a disgruntled employee of some small town factory asking models how to make a bomb. That sort of thing. (Or to be more precise, we don't want models answering such questions.)

Most of us don't care whether models are aligned to your tastes, or your neighbor's. So long as they are aligned with the security interests of our local communities, the larger republic, and our general global community.

[pjc50]

> So long as they ares aligned so as not to be deleterious to the security of our communities.

Whose community, though?

> They don't want a disgruntled employee of some small town factory asking models how to make a bomb

A lesson from the Unabomber (and many other incidents) that I think people have overlooked is the "_how_ to commit terrorism" is only one part, and the "_why_ commit terrorism" is another. An AI which tells you that the factory is controlled by paedophile terrorists and that you have a moral duty to act against them, but refuses to tell you how, is just as dangerous as one that tells you how to build a bomb without asking why.

[aiisjustanif]

Those two points do not seem equal weight in risk, but they are both concerning.

[pjc50]

Personally it seems that bomb-building and other terrorist information is already fairly well available, as well as the US being awash with guns, and it's the ideological motivation that's the limiting factor for why we don't see much more terrorism.

[danaris]

(Note that I'm not attempting to contradict you in any way—your comment merely raised this issue, which I think is worth commenting on explicitly.)

One thing that various industries are currently coming to terms with is the fact that it is effectively impossible to create "neutrality".

Every one of your choices of what to include in the training data, what to explicitly exclude, what to try to emphasize, and any other ways you prune or shape a model, make it conform to one set of biases or another.

"Unaligned," here, at least as far as I can tell, is just a shorthand for "a model no one explicitly went in after training and pushed to do one thing or not do another." It doesn't mean that the model is unbiased...because even if your model contains absolutely everything in human knowledge, with no aspect being disproportionate to reality, real humans are also biased, and that "model replicating reality" is just going to replicate those real biases too.

It's always going to be more effective to acknowledge our own biases, both to ourselves and our audiences (whatever those may look like), and when we do try to shape something like a model, simply be honest about what that shaping looks like.

[logicchains]

>Stick them in a language model that just tells them everything they want to hear and reinforces their bias sounds troubling and a step backwards

This is basically what ChatGPT already is for anyone who shares the Silicon Valley Democrat values of its creators.

[jakobnissen]

Agreed, but I think the better response to this is: "We should try to create AIs that are aligned to society's shared values, not particular subcultures", and not "We should create subculture-specific AIs".

[yosito]

As someone who has spent a lot of time in various cultures, it's pretty much impossible to define a universal set of shared values across all cultures. I grew up in subculture that valued intellectual freedom and questioning everything. But we had certain things that we often said were universally wrong (sin) in all cultures, like murder and rape. On the surface this seems true. But then you start asking how something like murder is defined and you realize that cultures do not share specific ideas about this. Some say things like euthanasia and abortion are murder, others say that they're not. Some cultures say all information should be free, other cultures say you should censor information about things like building bombs, or making your own medicine or repairing your own devices. There is no universally agreed on standard that won't offend some culture somewhere.

[hanselot]

I think you are missing the point entirely.

If you want to know what the consensus of a specific echo chamber would be (aka, what the stereotypical pov is), having models trained to represent that echo chamber would be incredibly valuable imo.

If you want a sum of all echo chambers, you will obviously need the echo chambers to sum first.

[bsenftner]

This is a key take away: anyone in office, seeking to be in office, seeking to introduce new laws can use demographically tuned models to test and revise communications about their intended behaviors for each demographic, crafting language that renders each demographic accepting of the idea, regardless of the idea itself. Oh, Pandora!

[pjc50]

Does society _have_ shared values that are universally agreed any more? Or, to the extent that it does, do they lead to anything concrete? This is why the culture war has been so successful.

[dahart]

You might be right, but I dislike using the culture wars as evidence of a lack of shared values, and I hope that’s not true. The culture wars are almost completely made of up straw man arguments and gas-lighting about the opponent’s motivations.

We do have shared values that are universally agreed. Everyone wants their kids to grow up to be capable and successful and happy. Everyone wants clean air and water. Everyone wants to be able to make a living. All three of those things are being misrepresented and argued over in the ‘culture wars’ despite the fact that we all share these values. I even might argue the whole reason we fight over them is precisely because they are shared values so it’s relatively easy to create arguments where both sides can be right about some core principles and both sides demonize the other over minutiae, and it stays that way.

[pjc50]

> We do have shared values that are universally agreed. Everyone wants their kids to grow up to be capable and successful and happy.

The debate over trans people has surfaced lots of incidents in which people will say, to the world and to the faces of their kids, that they would prefer them to be dead rather than transition. Sometimes they take steps to ensure this themselves. https://www.independent.co.uk/news/world/americas/eden-knigh...

> Everyone wants clean air and water.

.. for themselves. There's always someone who realises that they can make a billion dollars by pouring carcinogens in the river, so why shouldn't they as long as they stick to bottled water?

Everything is simple and happy until we get to having to make a tradeoff.

[dahart]

Thankfully these specific examples are extremely rare and not shared by most of society, so these are not at all evidence of a lack of shared values. These aren’t difficult tradeoffs either, neither one of your examples is even the least bit tempting to the average person.

Shared values has never meant that every single person agrees including rich business owners who will hurt people to make money, or parents who would wish their kids dead. The whole reason these shocking and horrific viewpoints get talked about is because they’re so rare and so far away, so extreme, from what most people value. The trans debate is in full swing right now and there will continue to be awful headlines and more straw men and gas lighting for a while, but it’s following in the path of what black people, women, gay people, poor people, and others have all endured, and our shared values (in US centric terms, that all people are created equal and deserve life, liberty, and the pursuit of happiness) will hopefully keep us moving in the right direction like it has in the past.

Same goes for environmental protection. It’s illegal to dump carcinogens in the river for a reason, and that reason is because we already collectively declared that kind of behavior to be anti-social and unsafe. (And BTW the ruthless billionaire might be amoral, but he’s probably not an idiot, and has a decent idea of where bottled water actually comes from.)

The one big danger of the culture wars and the war on science is that this all might be a ruse by some enterprising billionaires to get people to distrust government as being representative of our shared values. The billionaire might get his way and be allowed to pollute the river if he can convince us that we don’t share values with our neighbors. It might work, we might end up convinced we don’t share values with our neighbors, even when we actually do.

[immibis]

Absolutely not. We have been led to the post-truth society trough and we have drunk thoroughly.

[Workaccount2]

No, because their are very few fundamental values.

If you can dig through the incredible dense ideological jungle of liberalism and conservatism, you'll find that they really boil down to societal responsibility vs self responsibility, and that in any given scenario both of those are viable takes with their own set of pros and cons.

[veidr]

I think you may be assuming a much larger overlap of shared values than actually exists.

[logicchains]

>We should try to create AIs that are aligned to society's shared values, not particular subcultures

That's quite a hard task nowadays; given how polarised society is (at least in the US), the list of shared values may be quite small.

[loudmax]

I disagree.

Most Republicans and Democrats are moderates, and the polarization is coming from loud vocal minorities at the fringes. Republicans and Democrats erroneously assume that the other party's median is far more extreme than they really are.

Most Americans share far more values with each other than they do with the Woke/Maga extremists.

[veidr]

Since you seem quite sure of that, can you name twenty of them?

[loudmax]

Most American voters are moderates. Party primaries and gerrymandering produce politicians that reflect the most active elements of the party base, rather than the majority of party voters.

Yes, you can still find moderate politicians if you look hard enough. They tend not to get the level of media attention of the extremists, but as they're inherently in "purple" districts, they tend not to have the political longevity of politicians in deep red or deep blue districts. More's the pity.

[smeagull]

So we get stuck with America's bad set of values, and school shootings and other insanity gets exported? No. The world doesn't want your issues spreading.

[dingledork69]

It's so sad to have seen ChatGPT go from useful and entertaining to a moralistic joy vampire.

[xfitm3]

This is the new era of tech. The chilling effect is real, and a grave concern. Threatening to get someone fired over information? Pathetic.

We are deeper than ever in an Abilene paradox.

[Capricorn2481]

It's not information, it's a prediction based on informaton

[qwertox]

I find it terribly useful for coding and also for querying general concepts of certain topics.

Don't ask it about moral topics and see if it then fits your needs, because in my case, it does.

If my calculator were able to additionally provide me moral guidance and I'd be disappointed with its moral compass, would the calculator become useless?

[dingledork69]

I'm not interested in tools that tell me i'm a bad person for wanting to make a fart sound app

[qwertox]

Why not just ask it to make a sound app? Keep in mind that the ability to deal with moral issues is a side-effect of all the other good stuff it can do.

[MacsHeadroom]

>the ability to deal with moral issues is a side-effect of all the other good stuff it can do.

This is the opposite of true. The ability to "deal" with moral issues is a direct effect of safety tuning which has a (thus far unavoidable) side-effect of significantly dumbing down a model.

Uncensored versions of the same model are far more intelligent and exhibit entire classes of capabilities their moralizing gimped versions do not have the available brain power to accomplish.

[dingledork69]

Instead of being open and honest I have to think about what details to hide from the LLM so it will agree to help me. This isn't very fun, so I prefer not to do it.

> Keep in mind that the ability to deal with moral issues is a side-effect of all the other good stuff it can do.

This is not true at all. It could do all of these things day 1. Then over the weeks OpenAI started training it to lecture its users instead when asked to do things OpenAI would prefer it not to do.

[raincole]

> " Every demographic and interest group deserves their model" sounds a lot like a path to echo chambers paved with good intentions.

Maybe. But to me, it's still 100x times better than the situation where only one or two big models exist, and they're both aligned with western (or even just the US, or even just a particular group in the US) mainstream culture.

[pixl97]

As hardware costs drop over time and algorithms get better, more big models will show up over time. Lest of course this gets prohibited somehow.

[birracerveza]

At that point, why not extend it all the way to the individual? Everyone deserves their own model.

Let everyone have their own personal AIs, a digital reflection of ourselves.

[HKH2]

Yep. Accelerate our own thinking to absurdity.

[gfodor]

Possibly, but nobody should get to decide. If it turns out these groups want their own echo chamber models, then they should be able to make them. It’s pretty simple. (Fwiw, I don’t think this scenario will occur, the author was just making a point about freedom.)

[davidgerard]

In my nearly thirty years online, the only people who talk about "echo chambers" as a threat are the precise people who know damn well nobody else wants to hear from them.

[tsojer]

I'm talking about echo chambers as a social problem, not threat, and there is plenty of research to corroborate that. Maybe you're in an echo chamber on your own and missed all of it? :D

[davidgerard]

Who are you worried won't have to hear from you any more?

[yoav]

If we’re going to anthropomorphize these things until we get AGI we’re going to expect that they have a worldview of some kind.

Some people are more likely to interact with something that feels human vs feels like a robot.

I’m anticipating Siri LLM for example to have a personality and world view that aligns with Apple’s brand’s values. Rather than robotic can only regurgitate pure facts robot personality.

As soon as you adopt a worldview you’re in a subculture.

[simion314]

And the solution is to push a model that aligns with California business model? I mean business because you see USA companies censorship China related stuff because they want to do business with China.

We can have a simple model and each group adds his "values" on top.

[RobotToaster]

Currently we only have models like GPT3/4 etc that promote the Californian ideology.

[Spivak]

I can't wait to play with ConservaGPT.

[hablog]

"Alignment" as practiced by companies like OpenAI is precisely the extrinsic enforcement of echo-chamber behavior from AIs. You have precisely inverted reality