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

Measuring progress toward AGI: A cognitive framework

blog.google

Post reply on HN
Print view View original

21–30 of 229 posts

Re: Measuring progress toward AGI: A cognitive framework

#21

Post by LogicFailsMe »

lvoudour wrote: post #16
lnenad wrote: post #14

Earlier quoted context omitted.

It is not. Why is that relevant to social entities?

How well you interact with other members of a society increases your chances of procreation, survival, knowledge acquisition, ie. it makes sense as a measure of intelligence

It's a pretty ambiguous definition. The most powerful man in the world right now is not someone I consider a role model for social cognition and yet there he is with the football for the second time demonstrating grandmaster skill at social cognition to get there.

Re: Measuring progress toward AGI: A cognitive framework

#22

Post by 10xDev »

sourcegrift wrote: post #19
zug_zug wrote: post #17

I'm sorry what even is this? Giving $10k rewards for significant advancements toward "AGI"? What does "making a framework" even mean, it feels like a nothing post. When I think of what real AGI would be I think: - Passes the turing test - Writes a New York Times Bestseller without revealing it was written by AI - Writes journal articles that pass peer review - Wins a Nobel Prize - Writes a successful comedy routine -…

Grok recently created a cancer vaccine for a dog that reduced tumor size by 75%

Severely misleading statement.

Re: Measuring progress toward AGI: A cognitive framework

#23

Post by dist-epoch »

ArekDymalski wrote: post #12

It's good to have some kind of benchmark at least to structure the ongoing, fruitless discussion around "are we there already?". However I must admit that including the last point that is partially hinting at the emotional or rather social intelligence surprised me. It makes this list go beyond usual understanding of AGI and moves it toward something like AGI-we-actually-want. But for that purpose this last point isn…

Capability and alignment are orthogonal.

Stalin was AGI-level.

Re: Measuring progress toward AGI: A cognitive framework

#24

Post by onlyrealcuzzo »

pocketarc wrote: post #20

When people imagined AI/AGI, they imagined something that can reason like we can, except at the speed of a computer, which we always envisioned would lead to the singularity. In a short period of time, AI would be so far ahead of us and our existing ideas, that the world would become unrecognizable. That's not what's happening here, and it's worth remembering: A caveman from 200K years ago would have been just as int…

The amount of things LLMs can do is insane.

It's interesting to me how much effort the AI companies (and bloggers) put into claiming they can do things they can't, when there's almost an unlimited list of things they actually can do.

Re: Measuring progress toward AGI: A cognitive framework

#25

Post by raincole »

pocketarc wrote: post #20

When people imagined AI/AGI, they imagined something that can reason like we can, except at the speed of a computer, which we always envisioned would lead to the singularity. In a short period of time, AI would be so far ahead of us and our existing ideas, that the world would become unrecognizable. That's not what's happening here, and it's worth remembering: A caveman from 200K years ago would have been just as int…

> A caveman from 200K years ago would have been just as intelligent as any of us here today

In other words, intelligence offers zero evolutionary advantage?

Re: Measuring progress toward AGI: A cognitive framework

#26

Post by sho_hn »

tyleo wrote: post #8

It still seems like something is missing from all these frameworks. I feel like an average human wouldn't pass some of these metrics yet they are "generally intelligent". On the other hand they also wouldn't pass a lot of the expert questions that AI is good at. We're measuring something, and I think optimizing it is useful, I'd even say it is "intelligent" in some ways, but it doesn't seem "intelligent" in the same…

On the other hand, AI being very good at everything while select humans may only be very good at some things is likely also a quality we want to retain (or, well, achieve).

Re: Measuring progress toward AGI: A cognitive framework

#27

Post by Traubenfuchs »

pocketarc wrote: post #20

When people imagined AI/AGI, they imagined something that can reason like we can, except at the speed of a computer, which we always envisioned would lead to the singularity. In a short period of time, AI would be so far ahead of us and our existing ideas, that the world would become unrecognizable. That's not what's happening here, and it's worth remembering: A caveman from 200K years ago would have been just as int…

> A caveman from 200K years ago would have been just as intelligent as any of us here today, despite not having language or technology, or any knowledge.

Doubt. If we would teleport cavemen babies right out of the womb to our times, I don't think they'd turn into high IQ individuals. People knowledgeable on human history / human evolution might now the correct answer.

Re: Measuring progress toward AGI: A cognitive framework

#28

Post by guerrilla »

raincole wrote: post #25
pocketarc wrote: post #20

When people imagined AI/AGI, they imagined something that can reason like we can, except at the speed of a computer, which we always envisioned would lead to the singularity. In a short period of time, AI would be so far ahead of us and our existing ideas, that the world would become unrecognizable. That's not what's happening here, and it's worth remembering: A caveman from 200K years ago would have been just as int…

> A caveman from 200K years ago would have been just as intelligent as any of us here today In other words, intelligence offers zero evolutionary advantage?

It looks like quite the disadvantage, in fact. We're killing ourselves and a lot of other stuff in the process.

Re: Measuring progress toward AGI: A cognitive framework

#30

Post by ahoka »

zug_zug wrote: post #17

I'm sorry what even is this? Giving $10k rewards for significant advancements toward "AGI"? What does "making a framework" even mean, it feels like a nothing post. When I think of what real AGI would be I think: - Passes the turing test - Writes a New York Times Bestseller without revealing it was written by AI - Writes journal articles that pass peer review - Wins a Nobel Prize - Writes a successful comedy routine -…

I find it very interesting about the Turing test that as chatbots improve, so do humans get better at recognizing them.
Post reply on HN