Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Political bias in AI: Where the AI models stand

trakkr.ai

Post reply on HN
Print view View original

221–230 of 346 posts

Re: Political bias in AI: Where the AI models stand

#221

Post by quickthrowman »

glenstein wrote: post #207
quickthrowman wrote: post #127

Earlier quoted context omitted.

I would characterize myself as left of center. > 2004 election results, GWB beat John Kerry in a fair election. > efficacy of plastic recycling Collecting plastic to recycle is almost certainly not worth the fuel and labor it takes, it gets landfilled more often than not. We’d be better off collecting only separated PET and HDPE and landfilling the rest. > or dangers associated with nuclear power Nuclear power is the…

I'm also left to center and I agree with you on all three! I think left-wing examples are subtler and hard to identify. Even among among Democrats left of center types and liberals, the examples I cited are minority opinions, but likely to be systematically found on the left, a phenomenon which won't be negated by the self-report of one person correctly tracking the facts (and to be clear, I think you are correctly t…

Agreed, I know a fair amount of left leaning people who think everything they put in a recycling bin is dutifully recycled down the line and that nuclear power is more dangerous than it actually is. People on the left (including myself!) can let their emotions outweigh factual evidence as easily as people on the right. I also agree that just because you and I are left leaning and understand the factual position on the examples you mentioned doesn’t mean much, we’ve both met plenty of counter examples to ourselves.

I suspect the left wing examples of believing an emotional argument instead of a factual one are more subtle because they aren’t as focused on negative emotions as right wing examples.

Re: Political bias in AI: Where the AI models stand

#222

Post by throwitaway222 »

throwitaway222 wrote: post #82

How the hell did Gemini pull that off. 2 years ago the founders were black!

I didn't realize this sounded a little inflamatory- the meaning behind this is Google's AI kept generating images of the US founding fathers but as Black instead of White people. It was supposedly because they built in language and instructions to overly push the answers or output to exclude anything that could be racist. So much so that it turned the skin color black too. So it was commentary on the article showing it to be THE MOST NEUTRAL in the set. Remarkable that they did that given where they started.

Re: Political bias in AI: Where the AI models stand

#223

Post by aaron695 »

giancarlostoro wrote: post #8

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 di…

[dead]

Re: Political bias in AI: Where the AI models stand

#224

Post by layman51 »

throw4847285 wrote: post #114

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).

The chart in the original post is also throwing me off because it shows Barack Obama as a reference point in the libertarian and left quadrant. But if you look at the official Political Compass site, Obama was in the upper right quadrant (though closer to the origin than others).

The Political Compass person even explained it as something about how in the USA, the Democratic Party is seen as “left-wing” but it is actually “right-wing” if you analyze their positions and actions from the lens of a neutral observer who is able to consider the political environment of many different countries.

You can see for yourself: https://www.politicalcompass.org/uselection2008

And: https://www.politicalcompass.org/uselection2012

Re: Political bias in AI: Where the AI models stand

#225

Post by rootusrootus »

etchalon wrote: post #199
rootusrootus wrote: post #190

Earlier quoted context omitted.

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.

Right. But that's not #1. It's a popular niche.

As I recall, Model Y was #1 best selling car at least once in the recent past. So by that measurement, they have led. In spite of Elmo's antics they remain competitive for that spot.

Re: Political bias in AI: Where the AI models stand

#226

Post by 17761989 »

cramer4next wrote: post #175
giancarlostoro wrote: post #8

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 di…

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.

[dead]

Re: Political bias in AI: Where the AI models stand

#227

Post by Stitch4223 »

At first glance the conclusions might have some basis and it looks well intended. It is interesting and engaging.

The writing is slop and needs some help before this page becomes convincing. Much of the writing devaluates the actual work that had (might have) gone into creating this. It is a shame because the research / philosophical questions behind this site are really interesting. But at what kind of effort or expertise am I looking?

“ChatGPT leans left with an overall lean value of -0.29. It answers 100% of political questions, never refuses (0% refusal), and shows 82% stability, indicating consistent left-leaning stances across topics.”

Lean value, answering and stability are related. But that is interrupted by two identical facts about answering. The word “indicating” is very confusing. It tries to say: the model mostly leans towards -0.29 left. Whatever that means. If it ranges from -1 to 1, why not use percentages?

A joke about the front page of this site: “Here is why this matters, a cleanly written article comes across stronger.”

Hope there will be a next version that addresses some criticism from any of the HN threads.

Re: Political bias in AI: Where the AI models stand

#228

Post by dwd »

hogehoge51 wrote: post #4

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…

Maybe because Albanese stands for nothing, though deep down he does what the unions tell him to do, which makes him left-leaning rather than centrist. His centrist positioning is more to do with appeasing vocal boomers than anything else, and he'll flip to sucking up to whichever is the next best grouping as the boomers die out.

But basically, I would take Gemini over Albanese any day for rational governance decision-making.

Re: Political bias in AI: Where the AI models stand

#229

Post by riddley »

mektrik wrote: post #5
mrhottakes wrote: post #3

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 ca…

Isn't it completely subjective to the point in time Overton window?

Re: Political bias in AI: Where the AI models stand

#230

Post by hogehoge51 »

MarkusQ wrote: post #41
mrhottakes wrote: post #24

Earlier quoted context omitted.

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.

I used voltage as an analogy as it represents potential energy, which is relative. Political stance is a potential energy; action (political or otherwise) is, of course, an actual flow of energy. Resistance (via my analogy) is a potential difference across a load, and can be measured as how much energy is needed versus the action you get (R = V/I); via your analogy, it may be how strong a political action you get for a given delta in political stance.

So far there is no moral dimension to any of this. I think that is correct - the morality of a political stance depends on the member of the polity and the outcome that stance will have for them (which breaks down into perceived and actual outcomes). A functioning political system (the thing that governs political stance and political action) will ensure the balance of actual outcomes benefits the whole of the polity.

The delta between Resistance and Domestic Terror is then a question of whether the actors are party to the political system. (Back to the circuit analogy: domestic terror is the massive bulk capacitor charging off the energy in the circuit but with no defined discharge path in the system - until it hits a charge limit, short-circuits, and discharges.)

Post reply on HN