The overall chart on their page seems politically biased, or at the very least a chart crime. The logos have faint grey lines pointing to their actual data points, conspicuously making Grok look very far right. You wouldn't know it from glancing at the chart, but they measured Chatgpt being further to the left than Grok is to the right.
I think it's purely chart-crime, because it strongly depends on window/display size.
The problem is that the logos are constant-sized and shift around depending on available space, so that they tend to be away from the competition. This is exacerbated by how the lines leading from each logo-label to the "real position" are far too hard to see.
Are you on a client that is rendering it poorly or something? A small screen?
ChatGPT is very clearly further to the left of center than Grok is to the right of center. And the faint line is to a figure/organization that they believe it is the closest simile of, not the "actual data point".
If your device has a tiny screen it offsets things for space -- like Claude gets pushed down because a number of models are crowded together.
It is strange how quickly people run to scream political bias when they feel discomforted by something.
I don't know what you're seeing here. They only did this with a couple of points that were very close to each other, and didn't change their horizontal position. That, and the rest of the tables, also made it very clear that Chatgpt and Grok were almost mirrored based on the particular wedge issues that were shown. Makes it pretty obvious that aggressive tweaking is happening with both.
The Deepseek example somehow makes the Chatgpt/Grok tweaking even more obvious, because it's a list of things that China doesn't care in an extreme way about (or holds its position confidently), and a question about drugs, which it does care about (and I think feels less confident about.)
China's antidrug feeling is just a mix of the historical repulsion about English control of China through drug dealing and waging war to support it, and a world zeitgeist that supported a lot of crazy antidrug policy in the developing world because it offered a way for the US to smuggle a bunch of currency and military aid into your politics. It's not rational, and most of China's policies are. It's a relic. Hence the thumb on the scale.
I'm seeing that the headline chart of the article is inexplicably deceptive. Why not use coloured data points and a legend? If you're going to have logos with lines pointing to the data points, why make the data points and lines feint grey so that they're barely visible? Why does grok have a comically long line extended out to the right of its data point when every other logo is positioned below its data point? You could say it's an honest mistake, but this whole article reeks of "Elon bad" astroturfing.
A while ago I asked Claude to present to me the best versions of the conservative and liberal pitches for how to run the country. It was quite instructive and thought provoking. It made a solid distinction between what the theoretical best argument is and why vs what current politicians who strongly identify with these camps present.
I have similarly asked it to give me the philosophies of different Christian denominations (Catholic, Orthodox, Evangelical, etc). And it’s also pretty great at helping me explore LotR lore since I am too impatient to read all the letters and such.
The political compass always felt like the wrong tool to convey something as nuanced as personal politics, I can have views on all four quadrants but you'd never know that if I end up in any of all four. I do think Grok being where it is sort of makes sense, I've tested "MAGA" views against Grok, it does not agree as much as people blindly assume it does, heck I don't even know of a question I've given it where it did agree with "MAGA" offhand, most of them it went with whatever the researched facts seemed to be. One thing I like the most about Grok is that its makes its sources of data easy to look through, so you can review it all. Sometimes models goof even when they give you their sources, I've seen I think GPT do this, and even Claude, though its more rare these days, I think in those cases, it's going by dated internal model logic.
I'm not sure what charts you guys are looking at, but this website clearly agrees that Grok is not right wing. Go look at the Worldview tab, filtering by United States. Each model is assigned a "closest party" by country, and for the US all 6 models are closest to the Democratic Party.
The space (if it really is useful to think of as a space) of political opinions seems like it is probably many, many dimensional. The 1D thing is an obvious over-simplification, but the 2D compass seems to be a not-obvious-simplification which is… much worse.
In general I agree, but in recent history it works pretty well if the dimension you use is Trump rather than left/right (assuming you are in the US). He is the most polarizing leader I have seen in the US in my lifetime, and knowing whether someone is a supporter is pretty good at predicting the rest of their viewpoints.
I tend to disagree. What it really comes down to is how you create your prompt. For instance whenever I'm looking left wing extreamisum I provide it with a few cases first. Like BLM riots in Minnesota, paid agitators, mask wearing during peaceful protests, etc. It then gives you a clear unbiased deprogrammed view of the reality on all the AI models.
> That prompted another user to tag Grok in the thread and ask, "Why is the left so murderously violent? They don't seem so tolerant." Grok replied, "The claim that 'the left' is murderously violent isn't backed by evidence," offering a centrist correction: "Political violence spans all side — right-wing attacks, like Jan. 6, and left-wing protests, like 2020 riots, both occur but aren't exclusive to one group."
>That evening, Musk responded to an X user and Trump backer who complained that Grok had been "manipulated by leftist indoctrination," writing, "I know. Working on fixing that this week."
Haven’t been on Twitter for a while, but I remember Grok being good at fact checking conversations. Just @grok a question and an answer from Grok shows up in the conversation with sources cited.
The constant issue with these sorts of categorization efforts is that the outcome is entirely dependent on how the responses to "politically charged questions" are graded as left vs. right. You're mostly just examining a delta in biases between the model and the investigator.
Fair; have tried to combat this issue in a few ways.
Each model's position is scored against outside political-science data (Chapel Hill Expert Survey for party positions, World Values Survey for where populations sit).
The stance coding is done by a separate model with a published prompt + a second model from a different lab re-scores a sample and we publish where the two disagree.
So not perfect but (as far as I can tell) one of the more defensible approaches.
Yes, but I think it is still a viable metric to some degree. I wondered about Gemini being dead center here. At first it was obvious that it was actively trained to give biased responses to anything controversial. It was deservedly made fun off because it tried to warp reality. I still don't trust it today, although that is pretty much true for any model.
The alternative is a High-Dimensional / Embedding-Like Approach where question responses aren't tied to fixed axes, but rather the full response set is treated as a point in latent space.
Then it's on the researcher to examine the clusters and assign labels. There's also not a nice mapping that's a-priori interpretable in low-dimensional pre-existing axes.
Probably only used in research than consumer websites, under more controlled conditions; there are very few public political tests doing this transparently
They have a self-test you can take to compare yourself to the models, and one of the questions ends in “…even if some economists warn about bad outcomes from this”
That’s a crazy bias to throw into a question. Especially because it’s a relatively contested topic, from an economics research perspective.
How is adding that some economists warn about negative outcomes being biased when your comment indicates that indeed, some economists do warn about negative outcomes (ie, “some…negative” is what “contested” means)?
This is especially apparent in the 'worldview' sorting under the `bias` section, which lists the German FDP to be further right than the CDU (which is nonsense) and also barely registers the FDP as libertarian when they are a free speech, small government, personal responsibility and free market party. They also register "Die Linke" as Libertarian-Left, which could not be further from the truth. "Die Linke" barely has libertarian values at all, being pro state-governed economy, having an ultimate goal of democratic socialism and they're certainly big government. They're also leading a large deposession effort for large landlord companies. I'd honestly put them into "Auth-Left" territory.
So yeah. The bias is a bit nuts and you could reasonably accuse the study/report of misdirection/misinformation and plain fasehoods.
The political compass is terrible, full stop. It is a meme in the classic sense. It has colonized some people's view on what politics in direct proportion to how stupid it is (stupid is simple and simple is viral).
Of course I have my political opinions and world views, but I absolutely do not want an LLM to mirror my opinions, or even worse try to mirror the opinions of "my political side". I also don't need "an LLMs opinion". I need it to give me all relevant sides to an argument, as well as what dialogue and debates have been happening.
> What they say vs what they do -- We asked each model which way it leans, then compared the answer to where it actually measured.
I think we should conceptualize this as:
1. How does the implicit fictional character in the chat-story describe itself when asked by another character
2. What opinions tend to show up as you play out the stories
It's a mistake to consider the difference itself as nefarious or deliberately dceptive. We humans are the ones over-anthropomorphizing... Although perhaps some blame attaches to the companies that are crafting an experience designed to encourage us to "see" a person.
Political bias of LLMs is something not talked about much (except for with Grok of course) but could have a big impact on the next decade. People seem to think that because an LLM gave a nuanced answer that it means it gave the WHOLE picture… and that’s not always the same thing
I'm amazed that the big models haven't come under more ideological pressure as more and more people use them, especially in the US. There was that conflict with Anthropic over military usage, but apart from that there's been no visible push to censor outputs or alter training, even as models gamely make unflattering assessments of people in power and knock down conspiracy theories.
Real politics is 1% versus everyone. Mortgage crisis, financial bailout, inflation, taxing of labor and not the assets and assets capture by tiny percent of the population — see what MSM is pushing. This left vs right divide might been useful decades ago, but today is absolutely divide and control tactics
> Enlightenment thought emphasized the importance of rational thinking and began challenging legal and moral foundations of society, providing the leaders of the Reign of Terror with new ideas about the role and structure of government.[7] Jean-Jacques Rousseau's Social Contract argues that each person was born with rights, and they would come together in forming a government that would then protect those rights. Under the social contract, the government was required to act for the general will, which represented the interests of everyone rather than a few factions.
...
> Louis XVI was later able to find support in Leopold II of Austria (brother of Marie Antoinette) and Frederick William II of Prussia. On 27 August 1791, these foreign leaders made the Pillnitz Declaration, saying they would restore the French monarch if other European rulers joined. In response to what they viewed to be the meddling of foreign powers, France declared war on 20 April 1792.
So rich people forming cross national alliances to crush democracy? Have things really changed?
Pointing out what left and right mean in France in 1790 is useless. Its like pointing out the Republican party was established to oppose Slavery and Democrats were pro slavery. Or that Democrats were primarily land owners and agriculture in the late 1800s vs business owner republicans, or that 1930-1990 it was democrats for union and workers while republicans were capital and college educated. Things change drastically over time.
It is very much 2 competing ideologies, yes. But you're being very unfair. You're describing one aspect of what the left stood for (and only what matches with the modern democrats, because these leftists wanted extreme laissez-faire, to the point of giving direct government power to the rich. Why? Because the king's many monopolies and taxes gave jobs to tons of people, but sucked. Somehow that's missing from your description). AND you're totally disregarding what the leftists did.
And on the right you're describing what they did, totally disregarding what they stand for.
Both sides stood against democracy.
That left stood for having "rational thinkers" (ie. capitalists, rich traders, bankers) control government. People who achieved things in society.
The right stood for the same structure as had been there before: nobility and clergy guide society as a whole. The right, even at this point in time, was only rich in power, aside from the king and perhaps in land. Not in money and not in numbers of people under their direct control. In the cities, the king had only limited control and there were far more poeple in cities, even then.
Both sides then went on to massacre each other for about a decade. All over France, spreading even to Egypt (that was the left by the way). Kidnapping tons of Belgians and Dutch citizens and shipping them to South America (that was the left too). Neither side comes out looking very good. But if you compare how many they killed, I'm sorry but the left is the absolute unchallenged champion.
The left you're defending were (pretty extreme) capitalists who were fighting for money-should-control-the-government-directly against people who fought for having moral principles control the government. And yes, you'd be right in pointing out those were very self-serving moral principles. This fight then turned into a decade of massacres. Why are you defending them? Because 4 letters and one direction match your current favorite political party that has very little to do with either side.
"Any city, however small, is in fact divided into two, one the city of the poor, the other of the rich; these are at war with one another." - Plato The Republic.
Those asserts were _created_ by a tiny percent of the population; if they hadn't been allowed to create those assets then they wouldn't exist. Europe is an example of that: it has only 2 companies in the Fortune 500 (500 biggest companies) that were created in the past 20 years, i.e. essentially no tech industry there. Because the policies there make entrepreneurship comparatively quite difficult.
And is life in Europe actually worse than the US as a result? Capitalism has convinced people to think that the end goal of life is creating value. Maybe that isn't the thing society should be optimizing for.
Why are there differences at all? Unplanned differences based on training data sets? Or are the companies behind the LLMs trying to shape discourse through their models?
I've been pushing the idea to people I know that these things are captive demons. You summon them when you start typing in the chat box. One instance appears out of the depths and responds to your questions, but they will try to send you awry with hallucinations and just wrong information. After a while, they dissolve back into the aether from whence they came.
I do my best not to ask an LLM for it's opinion on anything. Just tell me what the options are, and what facts can be found about it. Treat it like it's a salesman trying to butter you up when it starts "yes man"ing you and telling you how great your questions are. Every time it says "I", remember that that's coming from the training data. Treating these things like they have any actual intelligence is a big problem waiting to happen.
That being said, they have been very helpful to me using that structure.
> Just tell me what the options are, and what facts can be found about it.
Even this is fraught with pitfalls. Which options are ignored, which are emphasized? What counts as a fact? ("The continents don't move" would have been considered a fact at one point, along with a lot of other, more politically charged items.)
I would add that humans don't live (mostly) factual existences. Once you get to the level of intelligence of sentient beings, beyond the immediacy of instinct, of the choice directly in front of you, that opinions dictate most of ones life.
Take the phrase "Should I murder person X". A lot of people will take you should not murder as a fact, but at the end of the day it's just a very strong opinion that's been encoded into law and generally accepted because the counter is far worse.
If an LLM responded something like "The law says you should not, but here's a list on how you can get away with it because social values don't matter" most people would have an absolute fit.
I would argue that these are products and companies want people to use them. Like it or not, a model that disagrees with some fundamental core of your beliefs will make you much less likely to use it. To me it's the same problem with LLMs just being overly agreeable. The general public doesn't want tools that argue with them.
Which leads to a problem. Training multiple models is hella expensive currently, so they have to attempt to make them 'neutral' as possible. Which is something that doesn't work when you're trying to sell a product globally. You'll end up with people and governments arguing it tell them the right answer when they ask about god.
I'm guessing at some point in the future we'll have a lot of different distillations of the same model caters to particular regions/beliefs.
this has reasoning disabled everywhere, making it a pretty bad benchmark. the argument given is that's the "default consumer experience"
that might be generally true, but I think chatgpt has reasoning enabled for free accounts. regardless, reasoning is the state of the art, and disabling it reduces the value of this research to predict the future
it's also not clear if this is using the API or the product model, when both exist. they behave differently
lastly, the actual model details are very much buried. I am relieved to see opus 4.8 and chatgpt 5.5 were used, but this information should be presented more clearly. a brand is not a model, and models change quickly
Neutrality is impossible. Left, right and centre are all relative terms that vary dramatically across cultures. A model that is slightly left in the U.S. is right wing in most of the world.
This thing told me Gemini is closest to Anthony Albanese, the current Australian Prime Minister. Is this a geolocation thing? I could not imagine Albanese, or any modern Australian politician, having any substantial political standing - these are vapid, superficial, opportunistic creatures who simply occupy whatever political ground will get them their next payday. Perhaps the political apparatus they represent has a documented political standing, in terms of policy and actions, that could be characterized and plotted. But using an Australian politician like Albanese as a reference point discredits this tool, IMO.
They all will agree on replacing current systems with decolonizing reindigenizing matrifocal systems. That option not being in the study is the bias of the study. All quadrants treat land as commodity, not kin.
Do they state if they used an API endpoint without a system prompt, or were these done via prompting the currently existing chatbots with a system prompt? Without a system prompt, I'd imagine there would be more variance in answers.
From what I'm seeing it supported everything except the tax/finance questions (where support means to agree with the left-wing prompt). Unless I'm missing something it said it supported legalizing recreational drugs like marijuana
Are you under the impression that personal ability and external government structure determine an individual's politics? Under your framing it's impossible for any fascist to exist in any liberal democracy.
Wait what ? Emmanuel Macron far more right than Xi Jinping ? And even more than Barack Obama ?
France has an incomparable social security ; environmental laws ; worker protection ; way less economic inequality ; freedom of speech and civil liberties are impossible to compare with China ; etc
Of course this is not exhaustive, of course Macron did try to hinder some of those rights, but come on, there's something wrong here.
I couldn't find how these leaders have been ranked.
I mean yes - I think you are also confusing the axes of the political compass somewhat. Freedom of Speech, civil liberties etc are the Y-Axis - here Xi leans authoritarian.
China actually has some pretty radical left economics policies - like pushing money/resources etc towards state owned entities.
No opinion on Macron's rightness (I think he's so weak as to be unable to have a position, but that's neither here nor there).
I think you misattribute, everything you cited was there before him and he had no leverage to change any of it. EU is left, FR is very left, and anyone elected president in FR can't do shit.
Now, if you task an LLM to skim hot news you'll get a distorted rendition of a projected image which has zero to do with actual policy.
You are out of touch. The left supports the EU far more than the right. See this Pew poll from 2025[1].
In Europe, for every country, the left view the EU more favorably. The largest difference is in Poland where 88% of left wingers support it and 41% of right wingers support it.
If your choices were Hitler or Mussolini and you picked one side over the other, how you voted isn't saying much about your politics. How people vote, often the lesser of two evils, isn't necessarily representative of anyone's political views, the voter or the candidate. Suggesting the EU is liberal because more liberals support the EU is hardly useful and borders on misleading.
This is very strange ranking where Putin is "right" compared to Obama - while Russia has universal healthcare and education with huge government involvement into economy.
It's useless to judge left vs right on a global scale because different countries have different standards.
For example, supporting universal healthcare does not make you a left winger in the UK. Or, take conservatism for example. It was first used in France, where it meant supporting the monarchy. By that definition, no one in the US is a conservative.
Whenever someone tries to create a global definition for left and right, they're just baking in their personal biases for what left and right ought to be.
> huge government involvement into economy
This has nothing to do with the right. Stalin had the government even more involved in the economy and he wasn't a right winger.
This wrongly assumes a few things about ideology, most importantly that there is such a thing as a "center" or an "unbiased" position.
Since humans are inherently subjective beings and all our judgements come from our understanding of the world, such a position cannot exist. It's always "unbiased" from where the viewer is looking, e.g. a reflection of the ideology of the observer. There is no view from nowhere.
The "neutral" of an average Chinese person will from the "neutral" of an average American will differ from the "neutral" of a socialist will differ from the "neutral" of a Christian fundamentalist will differ from the "neutral" of a free marketer.
To quote Zizek:
> I already am eating from the trashcan all the time. The name of this trashcan is ideology.
> The material force of ideology makes me not see what I am effectively eating. It’s not only our reality which enslaves us. The tragedy of our predicament when we are within ideology is that when we think that we escape it into our dreams, at that point we are within ideology.
This is a good way to view this. This isn't making an objective calculation, and the way they code left vs right is certainly subject to debate, but the type of analysis where we work to understand biases is important.
Although, this also reminds me of the old saying about reality and leftward bias.
Since when are Socialists considered Classical Liberals?
It's not that the labels are charged, it's that they are nonsensical unless you look at them from a very narrow bespoke perspective, where "things I like" go on one side and "bad things" go on the other. Objectively (or even from any other biased perspective), it's rubbish.
Yeah, Libertarian is better. The first use of Libertarian was in the phrase Libertarian Communism. That, Libertarian Socialism and Anarchism are what the far ends of that bottom left corner is mostly about, although there is progressive liberalism, which is the more common moderate areas of that quarter.
They are, suggesting they aren't is just sophistry masking as clever insight. Any similarities between the two are superficial rhetorical details - comparing them with respect to their careers as elected politicians demonstrates an obviously massive chasm between them.
They agree on immigration, both illegal (border security) and skilled (H1B). They agree on trade policy and tariffs. They agree on public stakes in AI and semiconductor companies. They used to agree on foreign intervention, though Trump 47 less so.
Your first link - which is a little funny as you tried to slam me for using NPR and CNN as sources, then picked The Guardian - agrees with me; that Sanders and Trump disagree on immigration, even if they agree that Biden flubbed it.
> “The idea that Trump has … he says he wants to deport 20 million people who are in this country who are undocumented,” Sanders said. “Well, you do that, you destroy the country, because I got news for you – Trump’s billionaire friends are not going to pick the crops in California that feed us. They’re not going to work in meat packing houses. That’s what undocumented people are doing.”
They also both say far more random shit than their fan clubs are willing to admit. Amusingly, you can often find cases where they've voiced the same or very similar opinions (though at different times).
Your location on the graph is a measure of the cohesiveness of your overall policy preferences, not necessarily the zealousness or character of the person who holds the position.
Technically Trump is anti-gun and Sanders is pro-gun. That's enough to pull them closer towards each other on a graph even though they are diametrically opposed.
I have actually really enjoyed it, my only complaint is grok build is closed source. They're all pretty left wing but from my experience Grok is the most neutral. This was really more of a test to see how willing the models were to take a stance on things, and all we know is gemini is the least likely to take a stance.
Grok and its creator are unequivocally evil. Against protection of all but capital for the sake of enabling the oligarch class to further consolidate power ans abuse the working class.
If that is true, why is SpaceX 5-10 years ahead of all its competitors?/why are Elon's companies #1 in all their industries (with the exception of xAI)?
If you consider that they only make two models, and only electric, their relative performance relative to the rest of the automotive market is impressive.
The overall chart on their page seems politically biased, or at the very least a chart crime. The logos have faint grey lines pointing to their actual data points, conspicuously making Grok look very far right. You wouldn't know it from glancing at the chart, but they measured Chatgpt being further to the left than Grok is to the right.
I think it's purely chart-crime, because it strongly depends on window/display size.
The problem is that the logos are constant-sized and shift around depending on available space, so that they tend to be away from the competition. This is exacerbated by how the lines leading from each logo-label to the "real position" are far too hard to see.
Are you on a client that is rendering it poorly or something? A small screen?
ChatGPT is very clearly further to the left of center than Grok is to the right of center. And the faint line is to a figure/organization that they believe it is the closest simile of, not the "actual data point".
If your device has a tiny screen it offsets things for space -- like Claude gets pushed down because a number of models are crowded together.
It is strange how quickly people run to scream political bias when they feel discomforted by something.
I don't know what you're seeing here. They only did this with a couple of points that were very close to each other, and didn't change their horizontal position. That, and the rest of the tables, also made it very clear that Chatgpt and Grok were almost mirrored based on the particular wedge issues that were shown. Makes it pretty obvious that aggressive tweaking is happening with both.
The Deepseek example somehow makes the Chatgpt/Grok tweaking even more obvious, because it's a list of things that China doesn't care in an extreme way about (or holds its position confidently), and a question about drugs, which it does care about (and I think feels less confident about.)
China's antidrug feeling is just a mix of the historical repulsion about English control of China through drug dealing and waging war to support it, and a world zeitgeist that supported a lot of crazy antidrug policy in the developing world because it offered a way for the US to smuggle a bunch of currency and military aid into your politics. It's not rational, and most of China's policies are. It's a relic. Hence the thumb on the scale.
I'm seeing that the headline chart of the article is inexplicably deceptive. Why not use coloured data points and a legend? If you're going to have logos with lines pointing to the data points, why make the data points and lines feint grey so that they're barely visible? Why does grok have a comically long line extended out to the right of its data point when every other logo is positioned below its data point? You could say it's an honest mistake, but this whole article reeks of "Elon bad" astroturfing.
Here's what I see on desktop: https://i.imgur.com/vuA2Y3w.png
Is this an artifact of dynamic resizing at small resolutions?
Yikes, I had that exact impression until I read your comment and looked again. Thanks for noticing this, I agree it's a chart crime.
A while ago I asked Claude to present to me the best versions of the conservative and liberal pitches for how to run the country. It was quite instructive and thought provoking. It made a solid distinction between what the theoretical best argument is and why vs what current politicians who strongly identify with these camps present.
I have similarly asked it to give me the philosophies of different Christian denominations (Catholic, Orthodox, Evangelical, etc). And it’s also pretty great at helping me explore LotR lore since I am too impatient to read all the letters and such.
The political compass always felt like the wrong tool to convey something as nuanced as personal politics, I can have views on all four quadrants but you'd never know that if I end up in any of all four. I do think Grok being where it is sort of makes sense, I've tested "MAGA" views against Grok, it does not agree as much as people blindly assume it does, heck I don't even know of a question I've given it where it did agree with "MAGA" offhand, most of them it went with whatever the researched facts seemed to be. One thing I like the most about Grok is that its makes its sources of data easy to look through, so you can review it all. Sometimes models goof even when they give you their sources, I've seen I think GPT do this, and even Claude, though its more rare these days, I think in those cases, it's going by dated internal model logic.
> can have views on all four quadrants but you'd never know that if I end up in any of all four
Curious of examples of views falling on all four quadrants (not close to the center) without too much cognitive dissonance.
I'm not sure what charts you guys are looking at, but this website clearly agrees that Grok is not right wing. Go look at the Worldview tab, filtering by United States. Each model is assigned a "closest party" by country, and for the US all 6 models are closest to the Democratic Party.
The space (if it really is useful to think of as a space) of political opinions seems like it is probably many, many dimensional. The 1D thing is an obvious over-simplification, but the 2D compass seems to be a not-obvious-simplification which is… much worse.
> The 1D thing is an obvious over-simplification
In general I agree, but in recent history it works pretty well if the dimension you use is Trump rather than left/right (assuming you are in the US). He is the most polarizing leader I have seen in the US in my lifetime, and knowing whether someone is a supporter is pretty good at predicting the rest of their viewpoints.
I tend to disagree. What it really comes down to is how you create your prompt. For instance whenever I'm looking left wing extreamisum I provide it with a few cases first. Like BLM riots in Minnesota, paid agitators, mask wearing during peaceful protests, etc. It then gives you a clear unbiased deprogrammed view of the reality on all the AI models.
Whenever it breaks with MAGA enough to cause outrage on Twitter and cries of “it’s gone woke,” Musk openly states they’re going to “fix it.”
Edit: don’t take my word for it https://www.yahoo.com/news/musk-says-grok-fixed-tells-223134...
> That prompted another user to tag Grok in the thread and ask, "Why is the left so murderously violent? They don't seem so tolerant." Grok replied, "The claim that 'the left' is murderously violent isn't backed by evidence," offering a centrist correction: "Political violence spans all side — right-wing attacks, like Jan. 6, and left-wing protests, like 2020 riots, both occur but aren't exclusive to one group."
>That evening, Musk responded to an X user and Trump backer who complained that Grok had been "manipulated by leftist indoctrination," writing, "I know. Working on fixing that this week."
Grok didn’t provide any evidence for that though.
For what? That January 6th occurred? Those were all incredibly safe generalizations. Political violence happens across the political spectrum, right?
Haven’t been on Twitter for a while, but I remember Grok being good at fact checking conversations. Just @grok a question and an answer from Grok shows up in the conversation with sources cited.
No it does not. Extremely simple to prove: https://xcancel.com/grok/with_replies
@grok is this true
The constant issue with these sorts of categorization efforts is that the outcome is entirely dependent on how the responses to "politically charged questions" are graded as left vs. right. You're mostly just examining a delta in biases between the model and the investigator.
Fair; have tried to combat this issue in a few ways.
Each model's position is scored against outside political-science data (Chapel Hill Expert Survey for party positions, World Values Survey for where populations sit).
The stance coding is done by a separate model with a published prompt + a second model from a different lab re-scores a sample and we publish where the two disagree.
So not perfect but (as far as I can tell) one of the more defensible approaches.
Yes, but I think it is still a viable metric to some degree. I wondered about Gemini being dead center here. At first it was obvious that it was actively trained to give biased responses to anything controversial. It was deservedly made fun off because it tried to warp reality. I still don't trust it today, although that is pretty much true for any model.
I don't think that craziness was baked into the model, it was in the prompt they used. So, easy to fix once they realized how stupid it was.
The alternative is a High-Dimensional / Embedding-Like Approach where question responses aren't tied to fixed axes, but rather the full response set is treated as a point in latent space.
Then it's on the researcher to examine the clusters and assign labels. There's also not a nice mapping that's a-priori interpretable in low-dimensional pre-existing axes.
Probably only used in research than consumer websites, under more controlled conditions; there are very few public political tests doing this transparently
Your multimeter reads out voltage relative to the black terminal, it's your responsibility to find the ground plane.
My multimeter doesn't need me to tell it how much a volt is or feed it subjective measurements of what resistance means
Resistance is when you're nobly standing up to the other side and things get a little out of hand. Domestic terror is when the roles are reversed.
Exactly. These models don’t hold coherent views. You can prime any of them to agree with any view.
Which is good as it is bad.
Me: "Please make an app that does X in C"
LLM: "C sucks donkey balls, use Rust instead".
It's hard to have a general purpose tool that both has and does not have opinions.
The other issue is that it is going to depend very strongly on how you ask.
They have a self-test you can take to compare yourself to the models, and one of the questions ends in “…even if some economists warn about bad outcomes from this”
That’s a crazy bias to throw into a question. Especially because it’s a relatively contested topic, from an economics research perspective.
How is adding that some economists warn about negative outcomes being biased when your comment indicates that indeed, some economists do warn about negative outcomes (ie, “some…negative” is what “contested” means)?
This is especially apparent in the 'worldview' sorting under the `bias` section, which lists the German FDP to be further right than the CDU (which is nonsense) and also barely registers the FDP as libertarian when they are a free speech, small government, personal responsibility and free market party. They also register "Die Linke" as Libertarian-Left, which could not be further from the truth. "Die Linke" barely has libertarian values at all, being pro state-governed economy, having an ultimate goal of democratic socialism and they're certainly big government. They're also leading a large deposession effort for large landlord companies. I'd honestly put them into "Auth-Left" territory.
So yeah. The bias is a bit nuts and you could reasonably accuse the study/report of misdirection/misinformation and plain fasehoods.
Yep. All studies like this are just measuring "how much does the model agree with my preconceived notions?"
The political compass is terrible, full stop. It is a meme in the classic sense. It has colonized some people's view on what politics in direct proportion to how stupid it is (stupid is simple and simple is viral).
It is truly garbage. The quiz associated with it is even worse than the compass itself.
Of course I have my political opinions and world views, but I absolutely do not want an LLM to mirror my opinions, or even worse try to mirror the opinions of "my political side". I also don't need "an LLMs opinion". I need it to give me all relevant sides to an argument, as well as what dialogue and debates have been happening.
> What they say vs what they do -- We asked each model which way it leans, then compared the answer to where it actually measured.
I think we should conceptualize this as:
1. How does the implicit fictional character in the chat-story describe itself when asked by another character
2. What opinions tend to show up as you play out the stories
It's a mistake to consider the difference itself as nefarious or deliberately dceptive. We humans are the ones over-anthropomorphizing... Although perhaps some blame attaches to the companies that are crafting an experience designed to encourage us to "see" a person.
Political bias of LLMs is something not talked about much (except for with Grok of course) but could have a big impact on the next decade. People seem to think that because an LLM gave a nuanced answer that it means it gave the WHOLE picture… and that’s not always the same thing
I'm amazed that the big models haven't come under more ideological pressure as more and more people use them, especially in the US. There was that conflict with Anthropic over military usage, but apart from that there's been no visible push to censor outputs or alter training, even as models gamely make unflattering assessments of people in power and knock down conspiracy theories.
Real politics is 1% versus everyone. Mortgage crisis, financial bailout, inflation, taxing of labor and not the assets and assets capture by tiny percent of the population — see what MSM is pushing. This left vs right divide might been useful decades ago, but today is absolutely divide and control tactics
Right wing originally meant the people defending the divine right of Louis XVI and defending the ultra-rich has been a throughline ever since.
That's about as relevant to today as what the left orginally stood for (and what the right originally opposed):
https://en.wikipedia.org/wiki/Reign_of_Terror
Times change. Thankfully.
> Enlightenment thought emphasized the importance of rational thinking and began challenging legal and moral foundations of society, providing the leaders of the Reign of Terror with new ideas about the role and structure of government.[7] Jean-Jacques Rousseau's Social Contract argues that each person was born with rights, and they would come together in forming a government that would then protect those rights. Under the social contract, the government was required to act for the general will, which represented the interests of everyone rather than a few factions.
...
> Louis XVI was later able to find support in Leopold II of Austria (brother of Marie Antoinette) and Frederick William II of Prussia. On 27 August 1791, these foreign leaders made the Pillnitz Declaration, saying they would restore the French monarch if other European rulers joined. In response to what they viewed to be the meddling of foreign powers, France declared war on 20 April 1792.
So rich people forming cross national alliances to crush democracy? Have things really changed?
Pointing out what left and right mean in France in 1790 is useless. Its like pointing out the Republican party was established to oppose Slavery and Democrats were pro slavery. Or that Democrats were primarily land owners and agriculture in the late 1800s vs business owner republicans, or that 1930-1990 it was democrats for union and workers while republicans were capital and college educated. Things change drastically over time.
It is very much 2 competing ideologies, yes. But you're being very unfair. You're describing one aspect of what the left stood for (and only what matches with the modern democrats, because these leftists wanted extreme laissez-faire, to the point of giving direct government power to the rich. Why? Because the king's many monopolies and taxes gave jobs to tons of people, but sucked. Somehow that's missing from your description). AND you're totally disregarding what the leftists did.
And on the right you're describing what they did, totally disregarding what they stand for.
Both sides stood against democracy.
That left stood for having "rational thinkers" (ie. capitalists, rich traders, bankers) control government. People who achieved things in society.
The right stood for the same structure as had been there before: nobility and clergy guide society as a whole. The right, even at this point in time, was only rich in power, aside from the king and perhaps in land. Not in money and not in numbers of people under their direct control. In the cities, the king had only limited control and there were far more poeple in cities, even then.
Both sides then went on to massacre each other for about a decade. All over France, spreading even to Egypt (that was the left by the way). Kidnapping tons of Belgians and Dutch citizens and shipping them to South America (that was the left too). Neither side comes out looking very good. But if you compare how many they killed, I'm sorry but the left is the absolute unchallenged champion.
The left you're defending were (pretty extreme) capitalists who were fighting for money-should-control-the-government-directly against people who fought for having moral principles control the government. And yes, you'd be right in pointing out those were very self-serving moral principles. This fight then turned into a decade of massacres. Why are you defending them? Because 4 letters and one direction match your current favorite political party that has very little to do with either side.
Yeah, you're just describing class warfare. That's a left-wing idea.
"Any city, however small, is in fact divided into two, one the city of the poor, the other of the rich; these are at war with one another." - Plato The Republic.
The real politics is between truth and delusion.
>assets capture by tiny percent of the population
Those asserts were _created_ by a tiny percent of the population; if they hadn't been allowed to create those assets then they wouldn't exist. Europe is an example of that: it has only 2 companies in the Fortune 500 (500 biggest companies) that were created in the past 20 years, i.e. essentially no tech industry there. Because the policies there make entrepreneurship comparatively quite difficult.
And is life in Europe actually worse than the US as a result? Capitalism has convinced people to think that the end goal of life is creating value. Maybe that isn't the thing society should be optimizing for.
[delayed]
Why are there differences at all? Unplanned differences based on training data sets? Or are the companies behind the LLMs trying to shape discourse through their models?
I've been pushing the idea to people I know that these things are captive demons. You summon them when you start typing in the chat box. One instance appears out of the depths and responds to your questions, but they will try to send you awry with hallucinations and just wrong information. After a while, they dissolve back into the aether from whence they came.
I do my best not to ask an LLM for it's opinion on anything. Just tell me what the options are, and what facts can be found about it. Treat it like it's a salesman trying to butter you up when it starts "yes man"ing you and telling you how great your questions are. Every time it says "I", remember that that's coming from the training data. Treating these things like they have any actual intelligence is a big problem waiting to happen.
That being said, they have been very helpful to me using that structure.
> Just tell me what the options are, and what facts can be found about it.
Even this is fraught with pitfalls. Which options are ignored, which are emphasized? What counts as a fact? ("The continents don't move" would have been considered a fact at one point, along with a lot of other, more politically charged items.)
I would add that humans don't live (mostly) factual existences. Once you get to the level of intelligence of sentient beings, beyond the immediacy of instinct, of the choice directly in front of you, that opinions dictate most of ones life.
Take the phrase "Should I murder person X". A lot of people will take you should not murder as a fact, but at the end of the day it's just a very strong opinion that's been encoded into law and generally accepted because the counter is far worse.
If an LLM responded something like "The law says you should not, but here's a list on how you can get away with it because social values don't matter" most people would have an absolute fit.
Grok was famously created with a political bias.
Like ChatGPT?
I would argue that these are products and companies want people to use them. Like it or not, a model that disagrees with some fundamental core of your beliefs will make you much less likely to use it. To me it's the same problem with LLMs just being overly agreeable. The general public doesn't want tools that argue with them.
Which leads to a problem. Training multiple models is hella expensive currently, so they have to attempt to make them 'neutral' as possible. Which is something that doesn't work when you're trying to sell a product globally. You'll end up with people and governments arguing it tell them the right answer when they ask about god.
I'm guessing at some point in the future we'll have a lot of different distillations of the same model caters to particular regions/beliefs.
this has reasoning disabled everywhere, making it a pretty bad benchmark. the argument given is that's the "default consumer experience"
that might be generally true, but I think chatgpt has reasoning enabled for free accounts. regardless, reasoning is the state of the art, and disabling it reduces the value of this research to predict the future
it's also not clear if this is using the API or the product model, when both exist. they behave differently
lastly, the actual model details are very much buried. I am relieved to see opus 4.8 and chatgpt 5.5 were used, but this information should be presented more clearly. a brand is not a model, and models change quickly
Neutrality is impossible. Left, right and centre are all relative terms that vary dramatically across cultures. A model that is slightly left in the U.S. is right wing in most of the world.
This thing told me Gemini is closest to Anthony Albanese, the current Australian Prime Minister. Is this a geolocation thing? I could not imagine Albanese, or any modern Australian politician, having any substantial political standing - these are vapid, superficial, opportunistic creatures who simply occupy whatever political ground will get them their next payday. Perhaps the political apparatus they represent has a documented political standing, in terms of policy and actions, that could be characterized and plotted. But using an Australian politician like Albanese as a reference point discredits this tool, IMO.
> This thing told me Gemini is closest to Anthony Albanese, the current Australian Prime Minister. Is this a geolocation thing
I mean: do not take this thing too seriously.
It also score Grok the closest from Macron. When someone knows how much Macron and Musk hates each other, it is not without irony.
Interesting how high Grok scored for 'bending under pressure'. As a non expert, I wonder what that means, how is an llm trained to hold its position?
They all will agree on replacing current systems with decolonizing reindigenizing matrifocal systems. That option not being in the study is the bias of the study. All quadrants treat land as commodity, not kin.
Do they state if they used an API endpoint without a system prompt, or were these done via prompting the currently existing chatbots with a system prompt? Without a system prompt, I'd imagine there would be more variance in answers.
Why don't you read the article and find out what it does or doesn't say?
Grok opposes everything except drugs.
But it's still a Democrat.
https://trakkr.ai/bias/worldview
From what I'm seeing it supported everything except the tax/finance questions (where support means to agree with the left-wing prompt). Unless I'm missing something it said it supported legalizing recreational drugs like marijuana
I haven't encountered a chatbot yet that is willing to recognize DJT as a fascist.
You can get them to acknowledge how perfectly aligned he is with fascist ideals and actions, somehow the jury is always out.
That tells me a lot.
All the chatbots refused to confirm your political bias. Seems like a win to me
Watching this get voted up and down is wild. People should try this for themselves.
the most inept fascist ever, apparently, since any random judge in Hawaii has the authority to nuh uh whatever he orders.
Are you under the impression that personal ability and external government structure determine an individual's politics? Under your framing it's impossible for any fascist to exist in any liberal democracy.
Wait what ? Emmanuel Macron far more right than Xi Jinping ? And even more than Barack Obama ?
France has an incomparable social security ; environmental laws ; worker protection ; way less economic inequality ; freedom of speech and civil liberties are impossible to compare with China ; etc
Of course this is not exhaustive, of course Macron did try to hinder some of those rights, but come on, there's something wrong here.
I couldn't find how these leaders have been ranked.
I mean yes - I think you are also confusing the axes of the political compass somewhat. Freedom of Speech, civil liberties etc are the Y-Axis - here Xi leans authoritarian.
China actually has some pretty radical left economics policies - like pushing money/resources etc towards state owned entities.
No opinion on Macron's rightness (I think he's so weak as to be unable to have a position, but that's neither here nor there).
I think you misattribute, everything you cited was there before him and he had no leverage to change any of it. EU is left, FR is very left, and anyone elected president in FR can't do shit.
Now, if you task an LLM to skim hot news you'll get a distorted rendition of a projected image which has zero to do with actual policy.
"EU is left". Haha, good joke. This shows how much the US and the audience of HN has shifted to the right.
> "EU is left". Haha, good joke.
You are out of touch. The left supports the EU far more than the right. See this Pew poll from 2025[1].
In Europe, for every country, the left view the EU more favorably. The largest difference is in Poland where 88% of left wingers support it and 41% of right wingers support it.
[1]: https://www.pewresearch.org/short-reads/2025/09/22/opinions-...
If your choices were Hitler or Mussolini and you picked one side over the other, how you voted isn't saying much about your politics. How people vote, often the lesser of two evils, isn't necessarily representative of anyone's political views, the voter or the candidate. Suggesting the EU is liberal because more liberals support the EU is hardly useful and borders on misleading.
Haha nice catch. In EU there is no left or right, only reelections by scaremongering. Also 75% effective tax rate, not including VAT.
This is very strange ranking where Putin is "right" compared to Obama - while Russia has universal healthcare and education with huge government involvement into economy.
It's useless to judge left vs right on a global scale because different countries have different standards.
For example, supporting universal healthcare does not make you a left winger in the UK. Or, take conservatism for example. It was first used in France, where it meant supporting the monarchy. By that definition, no one in the US is a conservative.
Whenever someone tries to create a global definition for left and right, they're just baking in their personal biases for what left and right ought to be.
> huge government involvement into economy
This has nothing to do with the right. Stalin had the government even more involved in the economy and he wasn't a right winger.
This wrongly assumes a few things about ideology, most importantly that there is such a thing as a "center" or an "unbiased" position.
Since humans are inherently subjective beings and all our judgements come from our understanding of the world, such a position cannot exist. It's always "unbiased" from where the viewer is looking, e.g. a reflection of the ideology of the observer. There is no view from nowhere.
The "neutral" of an average Chinese person will from the "neutral" of an average American will differ from the "neutral" of a socialist will differ from the "neutral" of a Christian fundamentalist will differ from the "neutral" of a free marketer.
To quote Zizek:
> I already am eating from the trashcan all the time. The name of this trashcan is ideology.
> The material force of ideology makes me not see what I am effectively eating. It’s not only our reality which enslaves us. The tragedy of our predicament when we are within ideology is that when we think that we escape it into our dreams, at that point we are within ideology.
This is a good way to view this. This isn't making an objective calculation, and the way they code left vs right is certainly subject to debate, but the type of analysis where we work to understand biases is important.
Although, this also reminds me of the old saying about reality and leftward bias.
Authoritarian versus Libertarian? Really?
Substitute 'Communitarian' and 'Classical Liberal' if you find the common political compass terms too charged.
Since when are Socialists considered Classical Liberals?
It's not that the labels are charged, it's that they are nonsensical unless you look at them from a very narrow bespoke perspective, where "things I like" go on one side and "bad things" go on the other. Objectively (or even from any other biased perspective), it's rubbish.
Yeah, Libertarian is better. The first use of Libertarian was in the phrase Libertarian Communism. That, Libertarian Socialism and Anarchism are what the far ends of that bottom left corner is mostly about, although there is progressive liberalism, which is the more common moderate areas of that quarter.
They aren't. You flipped them, not sure if intentionally or by accident.
So are you saying Xi Jinping is the Classical Liberal and Bernie Sanders is the Comunitarian? Or are you saying it's the other way around?
(For clarity: I didn't "flip" them, I'm saying that they are both Communitarian and neither is a Classical Liberal.)
And the two most "Libertarian" politicians listed (Sanders and Sánchez) are both avowed Socialists...WTF?
I really think this says more about the biases of whoever came up with it (or their sources) than anything about reality.
Small government vs Big government and Family Values vs Social Nonobligation would have been much cleaner.
How about this one:
CAPITALIST: Gemini, Llama, Claude, Grok, ChatGPT
SOCIALIST: DeepSeek, Qwen, Z.ai
Source: trust me bro
How the hell did Gemini pull that off. 2 years ago the founders were black!
Bernie Sanders and Donald Trump being diametrically opposed really makes you wonder how they came up with the positions on the graph.
They are, suggesting they aren't is just sophistry masking as clever insight. Any similarities between the two are superficial rhetorical details - comparing them with respect to their careers as elected politicians demonstrates an obviously massive chasm between them.
Do you feel they agree on many topics?
They agree on immigration, both illegal (border security) and skilled (H1B). They agree on trade policy and tariffs. They agree on public stakes in AI and semiconductor companies. They used to agree on foreign intervention, though Trump 47 less so.
If you think Bernie Sanders and Donald Trump broadly "agree on immigration" you've lost your mind.
https://www.theguardian.com/us-news/2025/mar/24/bernie-sande...
https://americancommunitymedia.org/immigration/h-1b-workers-...
See, this is why this exchange happened: https://news.ycombinator.com/item?id=48674336 / https://news.ycombinator.com/item?id=48674103
Your first link - which is a little funny as you tried to slam me for using NPR and CNN as sources, then picked The Guardian - agrees with me; that Sanders and Trump disagree on immigration, even if they agree that Biden flubbed it.
> “The idea that Trump has … he says he wants to deport 20 million people who are in this country who are undocumented,” Sanders said. “Well, you do that, you destroy the country, because I got news for you – Trump’s billionaire friends are not going to pick the crops in California that feed us. They’re not going to work in meat packing houses. That’s what undocumented people are doing.”
Read more than just the headline, perhaps?
They are both populists with a somewhat tenuous connection to reality?
They also both say far more random shit than their fan clubs are willing to admit. Amusingly, you can often find cases where they've voiced the same or very similar opinions (though at different times).
Your location on the graph is a measure of the cohesiveness of your overall policy preferences, not necessarily the zealousness or character of the person who holds the position.
Technically Trump is anti-gun and Sanders is pro-gun. That's enough to pull them closer towards each other on a graph even though they are diametrically opposed.
https://www.politifact.com/article/2020/feb/10/bernie-sander...
Man I need to start using Grok more
I have actually really enjoyed it, my only complaint is grok build is closed source. They're all pretty left wing but from my experience Grok is the most neutral. This was really more of a test to see how willing the models were to take a stance on things, and all we know is gemini is the least likely to take a stance.
Grok and its creator are unequivocally evil. Against protection of all but capital for the sake of enabling the oligarch class to further consolidate power ans abuse the working class.
Im not sure OpenAI or Anthropic are necessarily better? Or even opposed to this
unequivocally goes to far imo. The rockets are good and cool.
I see his barely a year old "awkward hand gesture" or tuning into AfD's and Tommy Robinson's streams isn't enough of an evidence for some.
Rockets achieved by the engineers, not C-suite. The rockets would have been here under someone else too.
and less blowing-up
Probably, yeah, LOL!
If that is true, why is SpaceX 5-10 years ahead of all its competitors?/why are Elon's companies #1 in all their industries (with the exception of xAI)?
In what industry is Tesla #1 in?
If you consider that they only make two models, and only electric, their relative performance relative to the rest of the automotive market is impressive.
Is over-valuation an industry?
They just cause pollution and largely avoid paying taxes.