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

231–240 of 346 posts

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

#231

Post by teravor »

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…

has anyone tried to create an IQ facsimile for politics?

basically you come up with 100 political questions and ask 10,000+ people, then do factor analysis on the answers. it would be interesting to find out how many actual factors dominate all the variance.

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

#232

Post by endominus »

yodsanklai wrote: post #194
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…

> 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.

"The government has the right to force people to take vaccines against their will for the sake of public safety." - Authoritarian Left

"The government has no right to legislate that a woman cannot have an abortion - women should control their own bodies." - Libertarian Left

"The government has the right and responsibility to shut down sources of misinformation in the news and online." - Authoritarian Right

"Capitalism is good and works fine as is." - Libertarian Right (if that doesn't ping lib-right to you, maybe something about supporting skilled immigration by large companies)

Is it so hard to believe that one person can hold all of the above views?

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

#233

Post by ImJamal »

spongebobstoes wrote: post #48

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…

Why would it be a bad benchmark to explore what the average person will experience? If 99% of people will experience X then it makes sense to look into X instead of Y.

I agree other things should be evaluated and more clearly presented.

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

#234

Post by DoctorOW »

All this debate about how politics are defined or how bias is measured. My question is why should I care? Grok identifying as Mechahitler didn't drag me any further right, why would ChatGPT be able to drag me left? If you vote the way AI tells you, that's already a problem regardless of what it said.

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

#235

Post by ImJamal »

TimPC wrote: post #184

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.

I've heard people say this before, but is it true? Aren't large chunks of Asia, Africa and South America further right than the US often times?

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

#236

Post by SwellJoe »

The one that pleasantly surprised me when I did some testing was DeepSeek. The self-hosted version, at least, answered honestly about a wide variety of topics that are sensitive in China. The only topic it refused to discuss was Tiananmen Square. In every other case, it basically gave a WikiPedia summary. (https://swelljoe.com/post/open-model-censorship/)

And, I mean, censoring Tiananmen Square discussion is bad, of course, but Qwen got downright petulant about stuff like Taiwan and Uyghurs.

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

#237

Post by gherkinnn »

patrickmay wrote: post #198
bee_rider wrote: post #154

Earlier quoted context omitted.

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.

I find the Nolan Chart ( https://www.theadvocates.org/political-type-comparison/ ) to be a better version of the 2D compass. You're absolutely right that more dimensions would be better, but finding the right orthogonal ones is difficult. The Nolan Chart is superior to the simplistic left vs right of U.S. political discourse in part because it shows there is more variation than the major parties would like everyone t…

It says that I am very progressive, and yet I find that wing's usual baggage laughable. Monty Python knew it all along, the Judaea's Peoples Front are the worst, it's every man's right to have babies and anyway, what have the Romans ever done for us?

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

#238

Post by NiloCK »

endominus wrote: post #232
yodsanklai wrote: post #194

Earlier quoted context omitted.

> 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.

"The government has the right to force people to take vaccines against their will for the sake of public safety." - Authoritarian Left "The government has no right to legislate that a woman cannot have an abortion - women should control their own bodies." - Libertarian Left "The government has the right and responsibility to shut down sources of misinformation in the news and online." - Authoritarian Right "Capitalis…

> "The government has the right and responsibility to shut down sources of misinformation in the news and online."

Funny that I read this as AuthLeft coded (specific to Youtube suppression of Covid truthing). But obviously the alignment is just a function of whatever specific information is labelled "mis".

But in general: agreed, and this is a good list.

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

#239

Post by cadamsdotcom »

Compressing a huge range of issues onto a one-dimensional axis and then telling everyone they have to land somewhere ON that axis is one of the most confusing and silly things about modern politics.

It’d be fascinating research to inspect models’ internal representations in case there’s an emergent structure in there that we can project back on society.

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

#240

Post by marbro »

cadamsdotcom wrote: post #239

Compressing a huge range of issues onto a one-dimensional axis and then telling everyone they have to land somewhere ON that axis is one of the most confusing and silly things about modern politics. It’d be fascinating research to inspect models’ internal representations in case there’s an emergent structure in there that we can project back on society.

There are 2 axes: the second is authoritarian-libertarian.
Post reply on HN