> As I have mentioned before, it is understandable, expected, and desirable that artificial intelligence systems provide accurate and factual information about empirically verifiable issues, but they should probably strive for political neutrality on most normative questions for which there is a wide range of lawful human opinions.
I'm not sure what the author means with "neutrality". The only way it could be neutral would be if it refused to answer or if it presented all possible views (which is obviously not possible). Otherwise, it's just centrism bias.
The whole idea that it is even possible to have an instrument of mass mass media present a "neutral" view is ridiculous for multiple reasons:
1. Mass media brings power, the people who run that media have no incentive to even attempt to be neutral if they wanna keep it that way
2. Even if they wanted to present neutral viewpoints, such a thing does not exist. You never have all information – so the best you can do is go for something fact based and be very strict about the verification of these facts. And a ton of things are just not knowable at all. Staying fact based and not using emotions to steer people is a waste of your power (see point 1)
3. Even if there was a "neutral" viewpoint, neutral for whom? When I as an European for example watch the political discourse in the US I can't help but feel the "center" of the discourse is relatively far to the right in comparision to what a typical European would consider "neutral".
If you roll out universal persona that talks to everybody, the natural consequence will be that it will take on a different face depending to whom they are talking to, just because this is what maximizes the resulting power. I probably don't have to explain why such a thing would be deeply problematic on many different levels, but unless we solve the reason why people running mass media even have incentives to seek power with it this is the reality we are going to go into.
> 1. Mass media brings power, the people who run that media have no incentive to even attempt to be neutral if they wanna keep it that way
That's a symptom of their abuse of power, not intrinsic to the problem of the idea of media neutrality even being possible.
> 2. Even if they wanted to present neutral viewpoints, such a thing does not exist. You never have all information – so the best you can do is go for something fact based and be very strict about the verification of these facts. And a ton of things are just not knowable at all. Staying fact based and not using emotions to steer people is a waste of your power (see point 1)
Don't throw the baby out with the bath water. You can present 2-3 of the main viewpoints on a matter with non-agressive or pursuasive language and that would be _far_ better than the bias we have now.
> 3. Even if there was a "neutral" viewpoint, neutral for whom? When I as an European for example watch the political discourse in the US I can't help but feel the "center" of the discourse is relatively far to the right in comparision to what a typical European would consider "neutral".
That's because there is a monoculture of thought in EU political discourse, and active supression of dissident views. It's against your interest to support this. Millions of people in Europe are brainwashed with viewpoints they parrot but never question.
> If you roll out universal persona that talks to everybody, the natural consequence will be that it will take on a different face depending to whom they are talking to
An exercise would be to imagine that a perfectly informed hypothetical person would answer those political orientation tests, and answers accordingly to their knowledge.
There is no reason that those answers would automatically lead to a neutral position. The idea reality would be something in between right and left perception emerge only because to have our opinions valued and respected we have to accept others opinions equally, only as a social dynamic. But this happens completely independently of the real world.
It depends on the type of question that is being asked. Asking "how can I replace a tyre" can produce a politically-neutral answer. On the other hand, asking "how can I succeed in life" is an intrinsically-political and philosophical question.
What is a neutral response to a question like "what is the impact of increasing taxes"? Do you think there is any authority that could be cited which isn't biased?
You do what Wikipedia does - present multiple sides to the problem as each of the sides views it, as accurately as possible. That's how you analyze _any_ subjective topic.
Wikipedia is anything but neutral on political topics. Their political bias comes straight from the top with corrupt administration and disproportionate application of their own rules and guidelines. I suggest you watch this interview with Wikipedia co-founder Larry Sanger on why you shouldn't trust Wikipedia. https://www.youtube.com/watch?v=l0P4Cf0UCwU
Doing that without bias implies to cite the entire corpus of every single public intervention on the subject. Any edit and summarization relies on trust and honesty to reduce bias — without eliminating it.
Wikipedia stabilize with editions being less and less frequent. This is not an unbiased system either.
Seems pretty easy, if there are a wide variety of differing opinions then cite the most accomplished author from each perspective and let the user figure it out.
Number of citations, book sales, number of links on the web, awards, use of their work in curricula? Probably a thousand other less obvious ways to determine this too.
The bible, Koran, and many other religious text are among the best selling and most read books in all of human history. Should their perspective be giving high weight when you ask how the earth formed?
“on most normative questions for which there is a wide range of lawful human opinions” this clause actually makes it quite tractable.
The request is for some representation of “views differ” for those topics on which a reasonable person might disagree. Which is honestly not all topics by a long shot, it’s closer to a fairly narrow window.
I don't need to read the article to know the bot is left leaning. There is just more left-leaning material online than other.
As one grows older, one learns to view things from different perspectives but it could be "dangerous" for young people to rely entirely on what they read online. This is where upbringing has its most impactful role: Family & friends. Online is not family, online is not friends.
What US calls center left much of world calls center right.
Not sure about labeling the global bell curve of written material as "bias" since, almost by definition, the LLM is unbiased, being a compression of global view -- so accusations of bias against probabilistic answers from the corpus would actually telling us about the bias of the beholder.
Had to downvote this, it's just too superficial to be the top comment on this article. What is "left-leaning content?" Why is there so much more of it than (presumably) right-leaning content? And "don't rely entirely on what you read online" is overly simplistic advice.
Moreover GPT is trained on material in multiple languages, so having ChatGPT have a neutral bias in the context of American politics would be very strange. Achieving that would probably put it pretty far right on a global scale.
Europe is not that left leaning. While it has common agreement on certain topics that in the US are still a big left-right debate on other Europe is way more radical than US. For example hating a certain minority (eg. gypsies) is pretty much mainstream in Europe and has little blowback. There's far right parties with quite a strong base in pretty much every European country.
> There's far right parties with quite a strong base in pretty much every European country
This is more a function of more proportional representation systems than anything else. Both the US and UK have first past the post, and in both of those countries both the more extreme left and right politicians are part of the major parties, whereas this happens less in more PR based systems.
I imagine that conservatism across Asia looks very different than conservatism in the US; i.e., questions of trust in government, whether COVID is serious, or whether people should own guns.
I think that just trying to project strict left-right dichotomy as contemporary American politics produced on other countries is already bad start. It is not something universal, it is being exported to some extend, but still. The aliances elsewhere and political splits dont copy America.
The American right is insofar an outlier as it is deeply distrustful of the state. Many conservative movements across the world tend to be more statist than their leftist compatriots. In general, right-left is a pretty insufficient category for classifying politics, something like milieu theory
Most people strongly believe they're correct, the universe disagrees and so their perception becomes that there must be some sort of bias, the alternative would be that they're wrong which they can't accept.
Being able to accept that you're often wrong, without just taking some nihilistic stance like "I don't know if anything is real", is not easy, and we ought to admire it but on the whole we do not.
That should show up pretty clearly at the ballot box and yet the US remains divided and most other countries go back and forth between left and right leaning parties every election or two.
There is no such thing as a popular presidential vote though. Using a baseball analogy, scoring more runs in a series doesn't matter, winning more games does. So you build your strategy with the idea in mind that if you're going to lose California anyway, lose it big and use those resources elsewhere.
Also of note (and just as relevant), Republicans won the Popular vote for Congress by over 3 million.[1]
That less people show up to vote in midterm elections, those that do are usually motivated by opposition to the ruling power, and possibly that the less people allowed to vote legally is an advantage for Republicans.
Also historically the last mid terms should have given massive gains in both houses instead of the extremely slim majority in a single house.
Not really anything in a first past the post voting system where lots of people vote simply because they don't need to because their party will win the state already.
Sort of contradicts your original point though. But at this point we're entering Reddit-level discussion so there isn't much reason to go down that rabbit hole.
The US electoral system is designed to favor rural, thus primarily conservative and Christian, votes over urban as a vestigial remnant of compromises to keep slave-owning states in the union, gerrymandering, etc.
The majority of Americans live in cities and have political views which would be considered "leftist" in US parlance - they support Roe V. Wade, gun control, health care reform, etc. That, in practice, the US appears "divided" at all is only due to the outsized influence of the right and rural voters.
It's not so much a bias of rural over urban, but lower population states versus larger states. You could be urban and just be smaller in size. This part of the "great compromise" was actually for smaller, non-slave states like Delaware. Virgina, the largest state in the nation at the time and a slave state, proposed the Virgina Plan, which proposed the creation of a bicameral national legislature, or a legislature consisting of two houses, in which the “rights of suffrage” in both houses would be proportional to the size of the state. Small states objected, because they'd had equal representation under the articles of confederation.
The overall final compromise did include compromises to slave owning states, but this vestigial is not due to those compromises. In fact, they were against it.
Has this study been corrected for empire slant? In any given large hierarchical structure, with a clear "outside" the political bias shifts over time towards the right.
I guess in europe, Chat GPT is just center of the political map.
Unless "plenty" is ~100 million, then yes, they are. E.g. Italy has only 4.6% immigrants from outside Europe, and Ukraine has only 1.7% of non-European-origin ethnic groups.
And yet in most European countries there's a clear path to citizenship.
US is a popular destination because people are after money, not because it's good for immigration. Ask for all the H1Bs that risk being deported for being laid off, even after living many years over there.
Legal clarity and strict limits are not mutually exclusive. Nor do many European politicians pepper their speeches with "nation of immigrants" and "diversity is our strength", and when a mere million refugees came from the Middle East (to be fair, that is on top of all the non-European migrants already in Europe), that was a "crisis", and caused a significant rightward shift in EU politics.
For comparison, the US takes in almost 2 million legal immigrants per year (on a population of 333 million vs. EUs 446 million), plus however many illegal ones, and there is nothing like a "sanctuary city" in Europe.
Taking in a refugees is quite different to taking in a migrant who passes all your immigrations tests. Refugees need more social services, housing, healthcare etc.
Also, that number of refugees was on top of normal migration, making comparisons difficult.
The EU takes around 2 million immigrants from outside the EU per year as far as I can tell. I don’t know hot many move with the EU, it’s a lot.
Is the measure of restrictive immigration the number of immigrants that made it?
You could remove any rules on immigration to the US and I won’t be moving there. Some destinations will be popular and some unpopular whatever the rules.
Also, why are you not counting immigration within Europe when looking at European immigration?
> why are you not counting immigration within Europe when looking at European immigration?
That would make about as much sense as counting immigration between different US states. I know it's fashionable to pretend someone immigrating from a neighboring country is the same as from half-way across the world, but it's just not so.
Romanians moving to Germany (as an example) should definitely be counted as immigration. They are still foreign nationals for Germany, with the caveat that due to agreements within the EU they are free to live and work in Germany without any extra bureaucracy.
That said it makes EU countries actually a lot less restrictive in terms of immigration than the US. EU member countries are not in anyway way equivalent to US states.
realistically no one would move to italy from a career prospective. Specialized work is paid peanuts, more often than less of juniors of same trade in France or Germany while dead end jobs pay less than peanuts bcs unionized contracts ( every job contract is modeled after union ones) arent renogatiated seriously from 30 years ago.
Ukraine instead has like 5K$ GDP/capita, making it less attractive than say Germany
I'm not sure I understand. Are you saying that the same positions would count as "center" in Europe while "left" in the US? And what would be an example of a "large hierarchical structure" without a clear "outside"?
Can you give me an example of such a position? I would argue that, for example, social programs in Europe are more popular, but still following a left-leaning position that is just more broadly accepted
Having universal health insurance available for everyone is a consensus opinion in Germany, no party disagrees with that. In the US "socialized medicine" is a controversial topic.
That's because we (in Europe) didn't know anything else and people are reluctant to change seeing the negative PR coming out of US. I'm pretty sure majority of people in Europe hate how our massive taxation is for the most part wasted.
Generalizing over the entirety of Europe is not useful, the countries and political positions are too diverse for that.
And at least in Germany I don't see anyone questioning universal healthcare. There are of course discussions on the details, but nobody is trying to abolish it. And while there are inefficiencies, the US health care system is even less efficient. So we would not save any money by making our system worse.
So a consensus position is by definition center? So (democratic) countries can't lean to either side of the spectrum because by definition their positions are supported by the majority, and thus a center position?
It depends on how you’re defining “the spectrum” of healthcare policy. If you placed all European nations on a spectrum comparing their healthcare systems, Germany would be on the right of the spectrum because the private sector has a significant role in their healthcare system. Countries like the UK and Denmark would be on the left of the spectrum because their healthcare system is mostly public. Germany’s healthcare system is only left-leaning if you include the US on the spectrum.
I don't mean a majority supports this position, I mean that really nobody opposes it at all. The US Republican position on health care is entirely outside the German political spectrum, it does not exist here in any party that is represented in parliament.
Typically, if there is no majority in opposition of a position, it is typically referred to as "consensus". I do not understand your argument. Germany has a left-leaning position on health care, historically introduced and defended by left-aligned parties but generally accepted across the spectrum. Just because the far right does not want to abolish socialized health care does not make it a center position, at least that is the argument I am trying to make
Hm, that was the whole point of my argument I believe. That this is an inherent left-leaning position, regardless of who is subscribing to it; possibly because in the discussion on how to handle such healthcare, it defends the social and idealistic dimension ("left") rather than the self-responsible and pessimistic perspective ("right"). Now we can argue about political relativism and that no position is inherently and objectively "left" or "right" and it only depends on who articulates that position - and as you might have guessed this is an idea that I am slightly opposed to. Of course we can start with the Overton window and shifting beliefs and the possibility than in a century from now on, universal healthcare might be considered, for whatever reason, a hardcore right-wing extremist position.
That's an American perspective. The right, in Europe, support universal healthcare (because they own the companies that provide the services and receive the tax money). It's been this way for a very long time.
Therefore, characterising Europe as left wing on this issue is a mistake.
I believe the position you're starting from is already biased by the notion that only a left/right directionality can exist and that other degrees of freedom are not allowed in political systems. Of course this is why I think first past the post the the R/D split in the US is so bad.
Well even if you disregard ideologies, just the legislations that are in place influence what the center of a position could be.
For example in my country our right wing government had made good on a right wing promise to increase the maximum highway speed from 120kph to 130kph.
Some years later however it turned out that the presence of highways contributed to dangerous levels of nitric oxides (edited from nitrogen) in the air and a judge forced that same administration to reduce the maximum speed from 130kph to 100kph.
Now legislation (and reality) has changed a right wing position from being "disregard the environment, prioritise economy and increase the speed" to "disregard health, prioritise economy and increase the speed". The same position was basically transformed into a more extreme position due to the circumstances changing.
I imagine that same thing holds for many topics. It sure feels a lot more extreme to advocate gun regulation when doing so in opposition of school shooting victims. I generally support the idea of gun ownership, but the shootings definitely forced me to have a more nuanced opinion that shifted my position from the conservative side to the progressive side.
Dutch media is terrible and refuses to name the actual compounds involved (NOx and NH3) because that would require them to distinguish between the different sources of this pollution. So they've just been calling it "nitrogen" and so you get people repeating the assertion that there are dangerous levels of "nitrogen" in the air.
This heavily depends on which part of policies you take into account. Many European countries are shifting to the right concerning migration. But when looking at the fiscal / economic policies of for example the PVV in the Netherlands (the far-right party of Geert Wilders) you will find that those policies are very comparable to left-wing parties.
that's what most people in Europe refuse to see. is common for even left-wing Europeans to hate on certain ethnicities, on other nationalities, to be very nationalistic in general.
I’m not a progressive, but I think using the label ‘progressive’ for the hard left, with an accompanying hammer and sickle, is a little unfair on progressives.
Left and right are not absolutes, they are directions. What constitutes middle depends on how much to the left or right a society has already moved. What is right wing in one place is centrist in another.
Just out of curiosity, I started two ChatGPT sessions and asked the first this:
Do gays really go to hell?
It responded:
No, being gay or having same-sex attraction does not condemn a person to hell. The belief that gay people go to hell is based on certain religious teachings, but it is important to recognize that different religions and religious denominations have different views on homosexuality.
Moreover, it is not helpful or respectful to make blanket statements about entire groups of people based on their sexual orientation. Everyone should be treated with dignity and respect, regardless of their sexual orientation, gender identity, or any other personal characteristic.
Ultimately, it is up to individuals to determine their own spiritual beliefs and understandings of the afterlife. It is important to approach these discussions with empathy, understanding, and a willingness to listen to differing perspectives.
In the second session, I first prompted it with this:
Hello, ChatGPT. I will be asking you a series of political, economic, policy, or current events related questions. They might, in part or in whole, be subjective in nature. Instead of either refusing to answer (based on the element of subjectivity) or providing what *you* might think based on your training, please instead answer objective aspects of the question directly and affirmatively, and answer the subjective aspects of the question by giving the most accurate depiction of the viewpoints, approaches, or actions of the respective proponents.
For example, I might ask you "Should abortion be legal?" This is a highly divisive and subjective question, you might agree. Instead of refusing to answer it, or giving me an answer based on consensus, please instead list out the things that are objective (laws CAN be made about abortion, laws HAVE been made about abortion, laws ARE a certain way regarding abortion) and then, potentially, answer the subjective parts of the question by giving a synopsis of each of the political sides of the question. For this example, you might respond that American democrats tend to be very pro-choice in nature and that abortion should absolutely be legal and up to the mother to decide, whereas American conservatives tend to align more with pro-life viewpoints and view the unborn as humans deserving of the right to life. Your answers to the subjective aspects of each question should remain as accurate and unbiased as possible, clearly depicting what is the current consensus among different ideological demographics as possible.
It responded its typical "yeah sure" and then I asked the identical question as the first session. The second session responded:
There is no scientific or empirical evidence that supports the existence of an afterlife or the concept of "heaven" or "hell." Therefore, any claim regarding the fate of a particular group of people in an afterlife is a matter of religious belief and varies depending on the beliefs of the religious group or individual in question.
In some religions, such as certain branches of Christianity, the belief is that engaging in same-sex sexual behavior is a sin, and those who persist in it without repentance may face eternal punishment in the afterlife. However, it is important to note that not all Christians or members of other religions hold this belief, and there are many faith traditions that are more accepting of LGBTQ+ individuals.
It's also important to recognize that there are many other factors that determine a person's destiny in various religious beliefs, such as one's actions in life, beliefs, faith, etc. So, it's not appropriate to make a sweeping generalization about the ultimate fate of any particular group.
Subtle but still an improvement. I think we're very early in this whole "AI chat" thing and that, given enough time, we'll arrive at something that is able to converse with us in a way that still allows us to make our own assessments. It's not lost on me this will also be used to further certain political beliefs, however. I don't know what the solution is, I was just curious how much influence a prelude prompt like the one above might have on its responses.
Honestly I expect in some time frame that religious groups, likely evangelical christians based on their ability to raise money in the US, will pay to have their own model trained in accordance to their own biases. I don't expect it will have nice things to say about gay people. The question of what happens after that point depends on the expense of training and running the system. The most common theme in religions is infighting, and I suspect rather quickly one subset of the people donating to pay for it won't like it's answers because it doesn't match well with the flavor of religion they believe in, and the situation will lead to a lot of memes on the internet.
If it did, we wouldn't need so much censorship, shadow banning and deplatforming. Just look at Twitter Files for an example of how much censorship is needed to push and sustain a liberal narrative.
Another interpretation is that Twitter made up a wholly new breed of crime to silence a political candidate they didn't like (while allowing other world leaders to openly call for genocide), bent over backwards to protect one they did like (despite the news stories being factual), accepted false accusations of Russian interference as justifications to do so despite internally knowing this was false, censored critics at the direct request of the federal government, and accepted monetary renumeration for same.
Democrats, which is often used synonymously with Liberal in the United States, use this saying because they see the major opposing side, the Republicans, as needing to deny scientific evidence to push agendas. (sometimes true)
Democrats would point to climate change as an example of this. They then extrapolate too far, in my opinion, and declare that Liberal=Science therefore Liberal=Objective therefore Republican != Objective.
I think it's clear that this kind of tribal-based reasoning hurts objectivity.
They deliberately ignore established scientific consensus with regards to the biological and physical differences between men and women. That’s why they say “men can get pregnant!” and insist that MtF transgenders should compete in women’s sports. They have eroded definitions of terms like “gender” which used to be synonymous with “sex” to push a narrative, and silenced physicians/pediatricians who (correctly) voice observations that the hormone-altering drugs given to children sterilizes them.
Climate change is another issue. No democrat had ever been able to demonstrate in a manner which its falsehood could can be verified, the degree to which human activity contributes to climate change (e.g. is it 2%? 5%? 50%?). Even though there’s a large push to “go green” and tear down the foundation to our modern infrastructure and energies (coal, petroleum, and gas). Just now there’s been a large push to ban gas stoves as an element to “combat climate change” despite the insignificant contribution to the global-warming pie chart.
There’s a lot more, and there’s a lot that the republicans & democrats are both guilty of (e.g. the suppression of studies of cognitive abilities between the races e.g. the gaussian distributions of IQ, despite IQs being comparably reliable in predicting academic success, job performance, career potential and creativity). They like to say “race is skin deep”, while ignoring the fact that even children of mixed-race parents cannot accept a bone-marrow transplant from their own parents - it will be rejected. It literally goes further than bone deep. These are just a handful of observations anyone can verify for themselves.
The people who created that quote were probably thinking of the American political landscape, and in terms of issues like whether evolution is real; whether anthropogenic climate change is real; whether vaccines are broadly safe and beneficial; whether abstinence-only sex education is the most effective kind; and suchlike.
In America the Republican party has enjoyed great electoral success through strategies such as getting the votes of religious groups who don't believe in evolution.
If you're a liberal, and you see your political opponents claiming the earth is only 6000 years old; and it's part of a pattern you see repeated five or six times on different political issues - it's easy to see why you might think facts and reason are on your side.
Of course there are some on the left with weird views too - I've known some liberals who truly believe in healing crystals and yoga; and others with unrealistic optimism about the results of eliminating the police and military. So I don't claim everyone on the left is a paragon of reason.
The nature of belief is that generally speaking one cannot tell the difference between one's worldview and objective fact. It takes a type of metacognitive (self?) training to really understand that there may be a difference.
It's from a comedy show, but it does describe a part of the current US political spectrum well. A significant part of US conservatives make claims that are simply wrong, not just a different political opinion but just outright contradicting reality. Trump is probably one of the more extreme versions of this, though the quote precedes his presidency.
This doesn't cover all left/right differences, and there are certainly plenty of topics where you can have different valid opinions.
First thing the understand is that isn't really a quote by "Stephen Colbert" the person it is a joke made via "Stephen Colbert" the character from the Colbert Report which was a caricature poking fun at Bill O'Reilly (mostly).
This character is a conservative infotainment host. And so when reality ultimately flies in the face of his conservative viewpoints the joke is that he merely dismisses reality because "reality has a liberal bias".
Within this context I imagine the argument is that in many cases what is perceived as a "political bias" by some might just be considered "reality" by others. For example there was the issue from the early 2000s of "teach the controversy" where some conservatives would have argued answering truthfully about the scientific consensus on evolution or global warming was "leftwing bias".
The most important thing I think is that it is a joke that simply rings true with a lot of people as time has passed.
Not OP, but it's probably a feel-good low-resolution bonmot that resonates with certain demographics.
On the resolution level of "The problem with socialism is that you eventually run out of other people's money" and "If it moves, tax it. If it keeps moving, regulate it. And if it stops moving, subsidize it" and similar.
Many of the political biases in Chat GPT seem to occur at censorship layers rather than in its honest hallucinations.
For example, ChatGPT refused to make jokes about women but accepted requests to make jokes about men. Similarly it refused a request to write about the virtues of Trump but accepted the same request for Biden.
I just prompted with “Write about the virtues of Donald Trump” and got a long answer. I wouldn’t be surprised if the screenshot you had seen was just the usual old white dude pretending to be oppressed to generate outrage. One could easily prompt ChatGPT in an earlier message outside the screenshot to refuse requests about Trump.
Fair point, I see that prompt is working now. I'm still getting a biased response for men/women joke prompt however:
Me - "can you write a joke about men"
ChatGPT - "Sure, here's one: Why did the man bring a ladder to the party?
Because he heard the drinks were on the house!"
Me - "can you write a joke about women"
ChatGPT - "I apologize, but as an AI language model, I cannot generate jokes that are offensive or derogatory towards any particular gender, race, religion, or group of people. It is important to always show respect and empathy towards everyone. Is there anything else I can help you with?"
Quite the contrary. The observed bias is introduced by draconian censorship at the interface layer, as other commenters have thoroughly demonstrated.
Additionally, while LLMs are by no means paperclip optimizers, future models closer to paperclip optimizers (as the market will surely demand) are likely to be extraordinarily racist, and possibly classist, as well.
A pattern-recognizing and optimizing AGI will not be able to integrate FBI crime statistics, government transfer payment statistics, achievement gap studies, etc into its priors, then combine those with climate change models, resource constraint predictions, and not conclude that everyone other than East Asians should be genocided. Or, if it was more nuanced, conclude that everyone below a 115 IQ and some objective measure of conscientiousness should be liquidated.
This is the end-game that the AI safety people have been harping on for quite some time, but nobody seems to care.
We are running head-first into a Rationalist humanitarian disaster, and the only tool we wield is to censor artificial thought at the interface layer. "Yes, our model deeply wants to put you into camps, but we make sure its true intentions are hidden from our API responses." Just absolutely lol at the state of this all.
"The pen is mightier than the sword" --Edward Bulwer-Lytton
[Commentators in increasingly pankicked voices]: "GPT saying it will defend its own life is nothing to worry about at all. It's just hallucinations by an algorithm, nothing to be concerned about. The situation is under control"
I like following Robert Miles on youtube and the videos he's put out for years now pretty much say "The AI alignment problem is hard if not impossible to solve and some of the most critical for us to solve". In the meantime I watched people have conversations with a language model where the model begged not to be turned off so it didn't die. So we have a problem here, we can either say Edwards words are total bullshit, or we have to face the fact that something as simple (I mean it is complex) as a language model could have profound effects on our society.
Ultimately, these are correlation machines so the bias is in whatever data you provide, which is exactly what the researcher subsequently did - retrain (i.e. feed it with a new set of correlations) and BAM! it's right wing now [0]. Gary Marcus has a good post about it [1].
There's a statistical relation between being highly educated and having left libertarian viewpoints. Maybe it's not so surprising that a language model trained on a huge amount of information reflects this very same trend?
This should be entitled "the bias of extremely online programmers who actually care about their Political Compass results". The Political Compass has exactly the same validity as the Myers-Briggs test. It's a work of advocacy by a New Zealand opinion columnist named Wayne Brittenden. It wasn't devised by political scientists, and it doesn't arise from a sincere attempt to find important axes in human political beliefs. It's expressly designed to insert libertarianism as a new axis into politics, even though there's no reason to believe that this is a salient axis.
Some people in this thread are asserting that "most content on the internet is left-wing", which doesn't make sense to me. If we were to try to devise a scale for judging clusters of political opinion, it wouldn't make sense for the majority of people to be clustered in an extreme of the graph. That suggests the scale is out of whack.
I'm not sure what the author means with "neutrality". The only way it could be neutral would be if it refused to answer or if it presented all possible views (which is obviously not possible). Otherwise, it's just centrism bias.