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

301–310 of 359 posts

Re: IQ tests results for AI

#301

Post by tick_tock_tick »

somenameforme wrote: post #205
api wrote: post #155

Earlier quoted context omitted.

Throughout 99% of human history, the economy was mostly zero sum. If someone was rich it was because they stole it. If a group was wealthier it was because they stole it. By "stole it" I'm including theft of labor through slavery as well as the usual conquests and raiding. There was little to no innovation over time spans as long as thousands of years. Most of human culture and philosophy evolved during these periods…

You're ignoring inflation. Real (inflation adjusted) median earnings are up 12%, in total, over the past 45 years. [1] That also understates the problem because many things (education, healthcare, debt costs, etc) are understated or not even considered in inflation measurements. There's also been a substantial increase in baseline necessities for the average person (internet, computing device, etc). Factor these in a…

> You're ignoring inflation. Real (inflation adjusted) median earnings are up 12%, in total, over the past 45 years. [1] That also understates the problem because many things (education, healthcare, debt costs, etc) are understated or not even considered in inflation measurements. There's also been a substantial increase in baseline necessities for the average person (internet, computing device, etc). Factor these in and it's fairly safe to say that real incomes have declined for the majority of people.

So what your saying even though peoples baseline expectations are higher they got, cellphones, Netflix, and are taking home more money?

Re: IQ tests results for AI

#302

Post by briHass »

hirvi74 wrote: post #263
alphazard wrote: post #70

Earlier quoted context omitted.

This is misleading. Anyone who wants to learn about IQ should Google it. It's the most replicated finding in psychology, and any questions you have about twins or groups with similar or different genes have probably been investigated. There is a lot of noise online in the form of commentary about IQ, so it's important to look at actual data if you are skeptical/curious.

> It's the most replicated finding in psychology Why would it not be? It's not like intelligence was some sort of unknown intrinsic discovery that psychologist happened to uncover. Intelligence was defined and the tests were created to support the definition. I've done quite a lot of personal, hobby-research on this subject, and I remain convinced that IQ deserves to be met with a lot of skepticism and controversy. I…

One that jumps immediately to mind is IQ testing used for epidemiology, such as exposure to toxins and the effects on children. IQ tests were used in the original study (Phillip Landrigan) used to show how leaded gasoline causes cognitive imparement in children. For things that cause sub-clinical imparement, you need a way to test for lowered intelligence, that doesn't rise to disability level.

That's a few million, if not billion people who's lives have been improved by having IQ tests that were used to force environmental regulation worldwide.

Re: IQ tests results for AI

#303

Post by petesergeant »

belter wrote: post #259
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…

If a model can get an IQ of 120, but can't draw clocks at a precise requested time, or properly count the b's in blueberry, can we then agree IQ tests don't measure intelligence?

> or properly count the b's in blueberry

This is more akin to you being unable to tell apart the syllables or tones in a very unfamiliar language.

Re: IQ tests results for AI

#304

Post by somenameforme »

tick_tock_tick wrote: post #301
somenameforme wrote: post #205

Earlier quoted context omitted.

You're ignoring inflation. Real (inflation adjusted) median earnings are up 12%, in total, over the past 45 years. [1] That also understates the problem because many things (education, healthcare, debt costs, etc) are understated or not even considered in inflation measurements. There's also been a substantial increase in baseline necessities for the average person (internet, computing device, etc). Factor these in a…

> You're ignoring inflation. Real (inflation adjusted) median earnings are up 12%, in total, over the past 45 years. [1] That also understates the problem because many things (education, healthcare, debt costs, etc) are understated or not even considered in inflation measurements. There's also been a substantial increase in baseline necessities for the average person (internet, computing device, etc). Factor these in…

No, for the average person the cost of a basic computing device and the rent attached to operate it, is probably eating up the extremely modest gain in income. And in modern times that's not really a luxury so much as a necessity, meaning people today are in effect earning less, significantly less for many, than they did 45 years ago.

I intentionally avoided entertainment, which is of course also greatly increasing costs even further - though that's probably at least partially balanced by the internet which provides an immense amount of entertainment for just the already accounted for baseline cost.

Re: IQ tests results for AI

#305

Post by hirvi74 »

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…

> has a 140 “IQ” but understands nothing.

There are probably millions of humans that fit this criteria too.

Re: IQ tests results for AI

#307

Post by famouswaffles »

machomaster wrote: post #268
flir wrote: post #250

Earlier quoted context omitted.

So define one. A race.

A group of people that have lived long enough in relative isolation that they became unique, distinguished and separate from other races.

The problem is that Human 'races' are not in fact unique, distinguished and separate from other 'races'. Genetically, two sub Sahara African men could be more genetically distinct than one of those men and a random white man even they should be both 'black'.

Re: IQ tests results for AI

#308

Post by famouswaffles »

Jensson wrote: post #292
throwaway284927 wrote: post #200

Earlier quoted context omitted.

You seem to be arguing that talking about races within humans may be useful even if the reality only approximates the definition of race (similarly to the idea of a "circle", which even though it does not apply in all it's precision to any real object it may still be a useful concept as an approximation nonetheless). However, I don't think that comparison is particularly insightful, and it may even be a bit misleadin…

Ok, so saying race doesn't exist is like saying chairs doesn't exist, since you can't really say what is a chair, what is a shelf and what is a table, correct? Technically you could say that a chair is a table or a shelf, but people still like to call them chairs, you know the difference when you see it. Races is like that, scientists can't define it but its still a useful concept like a chair. Scientists can't exact…

Two sub Sahara African men could be more genetically distinct than one of those men and a random white man even they should be both 'black'.

The thing about race is that it has no biological justification. It's still 'real' of course but in the same way money has 'real' value. It's a powerful social construct.

Re: IQ tests results for AI

#309

Post by famouswaffles »

Der_Einzige wrote: post #260
flir wrote: post #250

Earlier quoted context omitted.

So define one. A race.

https://en.wikipedia.org/wiki/I_know_it_when_I_see_it https://en.wikipedia.org/wiki/Duck_test https://en.wikipedia.org/wiki/Pragmatic_maxim

There’s more genetic variation within any so-called racial group than between groups, so race obviously has no genetic justification. It's real in the way other social constructs are real.

Re: IQ tests results for AI

#310

Post by famouswaffles »

holbrad wrote: post #192
bearl wrote: post #137

Earlier quoted context omitted.

Specifically, as well stated by [23] there is no such thing as “race.” The premise of racial group differences is not possible; we can’t have racial differences if race is not real. Sadly, a lot of people very much believe in race, especially the ones that shouldn’t!

People who say there's no such thing as race are complete charlatans playing semantic word games.

There’s more genetic variation within any so-called racial group than between groups, so race obviously has no genetic justification. That's not semantics. Yes it's real, but for social, not genetic reasons.
Post reply on HN