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

IQ tests results for AI

trackingai.org

Post reply on HN
Print view View original

211–220 of 359 posts

Re: IQ tests results for AI

#211

Post by nialse »

wizzwizz4 wrote: post #92
nialse wrote: post #86

Earlier quoted context omitted.

One is certainly not, unless one is not well read. The g-factor is one of the most stable findings in psychology. It is well established and well defined.

If you're calling g-factor "that which remains after you have eliminated all environmental factors", then you're not using the common definition. See https://en.wikipedia.org/wiki/G_factor_(psychometrics) . To challenge your other assertion, I'll quote the article: > The measured value of this construct depends on the cognitive tasks that are used, and little is known about the underlying causes of the observed corre…

Working in psychometrics I’m in the somewhat conservative “g is simply shared variance of many tests measuring human abilities”-camp.

https://www.jstor.org/stable/1412107?origin=crossref&seq=1

I’m not subscribing to the notion that g should be controlled for environment, quite the contrary, but if you do, what is left is the part of g which is genetics.

EDIT: The bit of knowledge I have comes from being published in psychiatric epidemiology on the topic of cognitive impairment and substance use.

Re: IQ tests results for AI

#212

Post by pxc »

grugagag wrote: post #201
Workaccount2 wrote: post #194

Earlier quoted context omitted.

EQ, SQ and whatever other-q, are not really a true thing. They're more feel good tests for Facebook dwellers who get confused on IQ tests. There are social assessments, but they are for identifying disorders.

Same could be said about IQ..

IQ test questions have clear right and wrong answers that can be determined in advance of writing the test. But EQ tests just measure a (not necessarily unanimous) consensus of subjective intuitions by a handful of psychologists.

It's true that EQ tests have all the same problems as IQ tests. But they also have additional problems.

(I learned this when I chatted with a psychologist about an EQ test he administered to me, but I just reviewed it now. See the "Psychometric properties" section of the Wikipedia article: https://en.m.wikipedia.org/wiki/Empathy_quotient )

Re: IQ tests results for AI

#213

Post by antegamisou »

root_axis wrote: post #148
laichzeit0 wrote: post #141

Earlier quoted context omitted.

So were their claims falsified?

You can't determine someone's IQ based on their race, you need to give them an IQ test to do that, thus the suggestion that we prejudge people based on their race is seen as racist. You might feel that the racism is scientifically justified, but that belief is controversial.

> You might feel that the racism is scientifically justified, but that belief is controversial.

Sir, this is HN, we love junk science and Sam Altman.

Re: IQ tests results for AI

#214

Post by LtWorf »

nsoonhui wrote: post #31
gpt5 wrote: post #6

The way human IQ testing developed is that researchers noticed people who excel in one cognitive task tend to do well in others - the “positive manifold.” They then hypothesized a general factor, “g,” to explain this pattern. Early tests (e.g., Binet–Simon; later Stanford–Binet and Wechsler) sampled a wide range of tasks, and researchers used correlations and factor analysis to extract the common component, then norm…

Another component of this theory concerning g is that it's largely genetic, and immune to "intervention" AKA stability as you mentioned. See the classic "The Bell Curve" for a full exposition. Which makes me wonder what's the point of all the intervention in the form of teaching/parenting styles and whatnot, if g factor is nature and immutable by large? What's the logic of the educators here?

According to a study, IQ of a group can increase of like 20 points if you motivate them by taking 2 hours of boring test by paying them :)

Re: IQ tests results for AI

#216

Post by antegamisou »

bgwalter wrote: post #103

Well, the site owner works for Stossel TV and Stossel is a "rationalist" AI apologist: https://www.johnstossel.com/ai-is-coming-for-your-job/ All standard talking points on one page (he forgot lump of labor though). So I'd take this test with a big grain of salt.

Saved me a click, thanks.

Re: IQ tests results for AI

#217

Post by guelo »

nsoonhui wrote: post #31
gpt5 wrote: post #6

The way human IQ testing developed is that researchers noticed people who excel in one cognitive task tend to do well in others - the “positive manifold.” They then hypothesized a general factor, “g,” to explain this pattern. Early tests (e.g., Binet–Simon; later Stanford–Binet and Wechsler) sampled a wide range of tasks, and researchers used correlations and factor analysis to extract the common component, then norm…

Another component of this theory concerning g is that it's largely genetic, and immune to "intervention" AKA stability as you mentioned. See the classic "The Bell Curve" for a full exposition. Which makes me wonder what's the point of all the intervention in the form of teaching/parenting styles and whatnot, if g factor is nature and immutable by large? What's the logic of the educators here?

The Bell Curve is a classic in racist science and it accelerated the destruction of america's greatness which was always that we are a land of immigrants.

Re: IQ tests results for AI

#218

Post by nialse »

mieubrisse wrote: post #190
thechao wrote: post #107

Earlier quoted context omitted.

My high school was right across from a branch of a university (UHD) where the PhD candidates developed IQ tests. We (the HS students) could take them for extra credit. My favorite example was a block-arranging test (there was a set of blocks & some pictures). Anyways, they printed the blocks "symmetrically"; once I figured that out, making the picture was limited only by how quickly I could move. (The test normally h…

A similar thing happened to me. I once took a timed test with a section that had me translating a string of symbols to letters using a cipher, response being multiple choice. If you read the string left to right, there were multiple answer options that started with the same sequence of letters (so ostensibly you had to translate the entire string). But if you read the string right to left, there was often only one an…

If the pattern generalizes to other tasks, maybe the test was right? ;)

Appreciate your post and the post you commented on. Taking shortcuts in test development often ends up being detrimental. There is also an inherent challenge in developing test for people who may well be smarter than you are. It’s like that programmer thing: “If you write the smartest program you can, and debugging is harder than writing code. Who’s gonna debug the code?” Many people have tried developing “smart” tests for cognitive abilities, some realize when they fail, some unfortunately don’t.

Post reply on HN