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

91–100 of 359 posts

Re: IQ tests results for AI

#91

Post by froh »

hemabe wrote: post #73
brabel wrote: post #48

Earlier quoted context omitted.

Really? If not genetics then what is it? Just random??

IQ is largely genetic, even if some people claim otherwise. The evidence for this is now overwhelming: even when different ethnic groups grow up in very similar conditions in the same country, the PISA (which correlates r=0.9 with IQ) scores measured vary greatly. For example, among second-generation children in Germany, there are significant differences in PISA scores. Polish children achieve similar or even better…

especially Germany is a very poor example for this claim as school performance (PISA) in this country correlates with the parents academic background more than anything. if your parents aren't educated you can be intelligent AF and still will fail the German school system while you can be dumb as a brick but still make Abitur if your parents drill you through. in Germany.

and Welt is a media source with a right conservative agenda pushing the genetics narrative.

Re: IQ tests results for AI

#92

Post by wizzwizz4 »

nialse wrote: post #86
gus_massa wrote: post #84

Earlier quoted context omitted.

I think everyone is using a different definition of the g factor.

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 correlations.

(We've had a lot of discussions of IQ on Hacker News. My observations suggest that everyone who supports it in more than 3 comments in the same thread is a scientific racist with a poor understanding of the research on IQ.)

Re: IQ tests results for AI

#93

Post by tim333 »

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?

Education is to learn stuff, not increase your IQ.

Re: IQ tests results for AI

#94

Post by flir »

nialse wrote: post #83
gus_massa wrote: post #77

Earlier quoted context omitted.

>>> They then hypothesized a general factor, “g,” to explain this pattern. >> 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? > does not nutrition and education help some people more than others? That’s the g factor which is mainly genetic. Yes, if you ignore or compensate everithing el…

That is correct. The null hypothesis tested is: if you compensate for everything the result is the same for everyone, given that genetics have no effects on g. Hence, the null hypothesis is rejected. Thus, mainly genetic factors underlie the g factor.

We are limited by our biology. A dog can't play the harmonica.

That doesn't sound like a deep insight, to be honest.

Re: IQ tests results for AI

#95

Post by tim333 »

Telemakhos wrote: post #25

AI has a 140 “IQ” but understands nothing. That’s because AI does not understand anything: it just predicts the next token based on previous tokens and statistics. AI can give me five synonyms for any Latin word, because that’s just statistics, and it can regurgitate rules about metrical length of syllables, but it can’t give me synonyms matching a particular metrical pattern, because that would involve applying know…

I had no idea what "synonyms matching a particular metrical pattern" is but googling that, their AI explained it to me nicely and gave some examples.

Re: IQ tests results for AI

#96

Post by tim333 »

cateye wrote: post #55

Isn’t giving LLMs “IQ scores” a category error? Human IQ is norm-referenced psychometrics under embodied noise. Calling both “IQ” isn’t harmless, it invites bad policy and building decisions on a false equivalence. Don’t promote it.

IQ scores are basically scores on an IQ test. They can be interesting or misapplied with both humans and AI.

Re: IQ tests results for AI

#97

Post by terminalshort »

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?

There is no logic. Some people are just born much smarter than others and there is nothing you can do about it if you aren't one of them. The implications of that fact are too much for most people to accept so we pretend that it isn't true.

Re: IQ tests results for AI

#98

Post by tim333 »

It's interesting there is a such a large spread for ChatGPT-5 Quite low for "5 Thinking" and high for "5 PRO Vision". They are probably trying to control their compute and energy costs by switching people to the simpler models where they can.

Re: IQ tests results for AI

#99

Post by judofyr »

hemabe wrote: post #73
brabel wrote: post #48

Earlier quoted context omitted.

Really? If not genetics then what is it? Just random??

IQ is largely genetic, even if some people claim otherwise. The evidence for this is now overwhelming: even when different ethnic groups grow up in very similar conditions in the same country, the PISA (which correlates r=0.9 with IQ) scores measured vary greatly. For example, among second-generation children in Germany, there are significant differences in PISA scores. Polish children achieve similar or even better…

Your first link (Wikipedia) directly contradicts your examples:

> Although IQ differences between individuals have been shown to have a large hereditary component, it does not follow that disparities in IQ between groups have a genetic basis[18][19][20][21]. The scientific consensus is that genetics does not explain average differences in IQ test performance between racial groups.[22][23][24][25][26][27].

Re: IQ tests results for AI

#100

Post by Consultant32452 »

tim333 wrote: post #93
nsoonhui wrote: post #31

Earlier quoted context omitted.

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?

Education is to learn stuff, not increase your IQ.

I would argue the purpose of public education is directionally to attempt to level the playing field between people who start with a lot and people who start with a little. And in this regard, it is an absolute failure. People sometimes attribute public schooling to helping someone "escape poverty" or whatever, but I think it's mostly IQ and big 5 personality traits. And it's extremely unfortunate that both of those appear to be largely genetic.

Here's a real brain bender. Let's assume it takes approximately average IQ to understand basic algebra, so approximately 100 IQ. Half of the population has less than that IQ. Squinting really hard and making things up, something like 40% of the population is intellectually incapable of understanding exponential growth and decay. So how can it be legal/ethical for them to sign a contract to get a credit card or a mortgage if they literally cannot understand it? That's just one example. Once you crack this egg open, it breaks a lot of things required for modern society to function.

Post reply on HN