Comment by stared | Hacker News Reader

Comment by stared | Hacker News Reader

There’s already a vague definition that AGI is an AI with all the cognitive capabilities of a human. Yes, it’s vague - people differ.

This paper promises to fix "the lack of a concrete definition for Artificial General Intelligence", yet it still relies on the vague notion of a "well-educated adult". That’s especially peculiar, since in many fields AI is already beyond the level of an adult.

You might say this is about "jaggedness", because AI clearly lacks quite a few skills:

> Application of this framework reveals a highly “jagged” cognitive profile in contemporary models.

But all intelligence, of any sort, is "jagged" when measured against a different set of problems or environments.

So, if that’s the case, this isn’t really a framework for AGI; it’s a framework for measuring AI along a particular set of dimensions. A more honest title might be: "A Framework for Measuring the Jaggedness of AI Against the Cattell–Horn–Carroll Theory". It wouldn't be nearly as sexy, though.

Huh. I haven’t read the paper yet. But, it seems like a weird idea—wouldn’t the standard of “well educated (I assume, modern) adult” preclude the vast majority of humans who ever lived from being considered general intelligences?

And this is indeed a huge problem with a lot of the attacks on LLM even as more limited AI - a lot of them are based on applying arbitrary standards without even trying to benchmark against people, and without people being willing to discuss where they draw the line for stating that a given subset of people do not possess general intelligence...

I think people get really uncomfortable trying to even tackle that, and realistically for a huge set of AI tasks we need AI that are more intelligent than a huge subset of humans for it to be useful. But there are also a lot of tasks where AI that is not needed, and we "just" need "more human failure modes".

I read this as a hypothetical well-educated adult. As in, given the same level of knowledge, the intelligence performs equally well.

I do agree that it’s a weird standard though. Many of our AI implementations exceed the level of knowledge of a well-educated adult (and still underperform with that advantage in many contexts).

Personally, I don’t think defining AGI is particularly useful. It is just a marketing term. Rather, it’s more useful to just speak about features/capabilities. Shorthand for a specific set of capabilities will arise naturally.

You can't measure intelligence directly. Instead, the idea is to measure performance in various tasks and use that as a proxy for intelligence. But human performance depends on other aspects beyond intelligence, including education, opportunities, and motivation, and most humans are far from reaching their true potential.

If you compare the performance of the average human to a state-of-the-art AI model trained by top experts with a big budget, you can't make any conclusions about intelligence. For the comparison to make sense, the human should also be trained as well as reasonably possible.

The bar of "reasonable" is very different though.

Is it reasonable to invest $10 million in education of one human? Not really. One human can only do so much.

But is it reasonable to invest the same sum in training one AI, which can be replicated and used indefinitely? Or in acquiring high quality training data, which can be used to train every future AI?

>But all intelligence, of any sort, is "jagged" when measured against a different set of problems or environments.

On the other hand, research on "common intelligence" AFAIK shows that most measures of different types of intelligence have a very high correlation and some (apologies, I don't know the literature) have posited that we should think about some "general common intelligence" to understand this.

The surprising thing about AI so far is how much more jagged it is wrt to human intelligence

I think you are talking about correlation in humans of, say, verbal and mathematical intelligence. Still, it is a correlation, not equality - there are many word-acknowledged writers who suck at math, and mathematical prodigies who are are not the best at writing.

If you go beyond human species (and well, computers are not even living organisms), it gets tricky. Adaptability (which is arguably a broader concept than intelligence) is very different for, say octopodes, corvids and slime molds.

It is certainly not a single line of proficiency or progress. Things look like lines only if we zoom a lot.

Human intelligence has had hundreds of thousands of years of evolution that removes any 'fatal' variance from our intelligence. Too dumb is obvious on how it's culled, but 'too smart' can get culled by social creatures too, really 'too different' in any way.

Current AI is in its infancy and we're just throwing data at it in the same way evolution throws random change at our DNA and sees what sticks.

Reply on news.ycombinator.com