Measuring progress toward AGI: A cognitive framework • Hacker News Board

Re: Measuring progress toward AGI: A cognitive framework

#101

Post by m_mueller » Wed, Mar 18, 2026, 1:52 PM UTC

adrian_b wrote: post #94

m_mueller wrote: post #47

Earlier quoted context omitted.

it's impossible to prove the counterfactual (I guess, as I imagine we don't have enough gene information that far back). But I'd imagine that the high calorie food you can get starting with the advent of agriculture is exactly what could drive evolution in a certain direction that helps brains grow. We've had ~1000 generations since then, that should be enough for some change to happen. Our brains use up 20% of the b…

The advent of agriculture did not provide better food, it was just the only solution to avoid extinction due to the lack of food. The archaeological evidence shows that for many generations the first neolithic farmers had serious health problems in comparison with their ancestors. Therefore it is quite certain that they did not transition to agriculture willingly, but to avoid starvation. Later, when the agricultural…

I've seen the bone marrow hypothesis also, which is very interesting. Afaik. evidence shows at least that there was enough specialization during neolithic era to have bone marrow cooks where the hunters delivered their bones. Something you wouldn't expect based on just school knowledge (at least back in 90s/2000s).

I see your point about agriculture at first degrading quality of food. Are you aware of evidence of brain size degrading even? Is it visible in the temple bones?

Re: Measuring progress toward AGI: A cognitive framework

#102

Post by LogicFailsMe » Wed, Mar 18, 2026, 1:56 PM UTC

lvoudour wrote: post #33

LogicFailsMe wrote: post #21

Earlier quoted context omitted.

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.

You don't have to be empathetic and nice, just good at navigating society.

So in all seriousness with a bit of snark: Do you want a malevolent AGI? Because "good at navigating society" as the only benchmark here is how you get a malevolent AGI...

Evidence: cuckoos and cheaters all the way down the evolutionary ladder as a winning strategy and arms race against the hard workers.

Re: Measuring progress toward AGI: A cognitive framework

#103

Post by next_xibalba » Wed, Mar 18, 2026, 2:06 PM UTC

applfanboysbgon wrote: post #68

danielbln wrote: post #64

Earlier quoted context omitted.

Yes, but also antibiotics, vaccinations, child mortality down down down, life expectancy up up up. I wouldn't trade for living even 100 years prior compared to today, or 500-200k years ago for that matter. With everything wrong and sick with today's world, let's not take the achievements of our species for granted.

You wouldn't make that trade because you are part of the last generation (loosely speaking, a collection of generations) before it all comes crumbling down. We are living unbelievably privileged lives because we are burning all of the world's resources to the ground. In the process, we're destroying the ecosystem and driving a mass extinction event. Nothing about the way we live is sustainable long-term. We're litera…

Doomerism is a kind of religion that goes back as far as they eye can see. What's interesting about it is that in spite of being perpetually incorrect in its myriad predictions, it continues to adapt and attract new adherents.

Re: Measuring progress toward AGI: A cognitive framework

#104

Post by gilbetron » Wed, Mar 18, 2026, 2:09 PM UTC

1970-01-01 wrote: post #80

Way too much framework. The A in AGI is for artificial. Have it build its own test harness instead of outsourcing it via hackathon. If you cannot trust that output, you're nowhere near AGI.

The "A" in AGI is for artificial, not advanced.

Re: Measuring progress toward AGI: A cognitive framework

#105

Post by mrkstu » Wed, Mar 18, 2026, 2:09 PM UTC

applfanboysbgon wrote: post #68

danielbln wrote: post #64

Earlier quoted context omitted.

Yes, but also antibiotics, vaccinations, child mortality down down down, life expectancy up up up. I wouldn't trade for living even 100 years prior compared to today, or 500-200k years ago for that matter. With everything wrong and sick with today's world, let's not take the achievements of our species for granted.

You wouldn't make that trade because you are part of the last generation (loosely speaking, a collection of generations) before it all comes crumbling down. We are living unbelievably privileged lives because we are burning all of the world's resources to the ground. In the process, we're destroying the ecosystem and driving a mass extinction event. Nothing about the way we live is sustainable long-term. We're litera…

We also live in an era we can create hydrocarbon fuel DIRECTLY from the atmosphere and desalinate fresh water in unlimited supply, from power derived directly from the sun or atomics.

We also live in a time where the human population, where it is most concentrated, is declining rather than growing, so far without too disastrous consequences.

Greening of the earth has been happening since the 1980s- i.e. about a .3% coverage increase per year in recent decades.

Places that were miserable and poor, like China, have been lifted to prosperity and leading out in renewable tech.

There is much to celebrate and after the recent passing of Paul Ehrlich, we should pause and consider just how wrong pretty much every prediction he made was.

Re: Measuring progress toward AGI: A cognitive framework

#106

Post by Lwerewolf » Wed, Mar 18, 2026, 2:12 PM UTC

saalweachter wrote: post #100

beeflet wrote: post #52

Earlier quoted context omitted.

And many of them so unexpected, given the unusual nature of their intellegence emerging from language prediction. They excel wherever you need to digest or produce massive amounts of text. They can synthesize some pretty impressive solutions from pre-existing stuff. Hell, I use it like a thesaurus to sus out words or phrases that are new or on the tip of my tounge. They have a great hold on the general corpus of info…

My current way of thinking about LLMs is "an echo of human intelligence embedded in language". It's kind of like in those sci fi or fantasy stories where someone dies and what's left behind as a ghost in the ether or the machine isn't actually them ; it's just an echo, an shallow, incomplete copy.

Just dust and echoes.

(:

Re: Measuring progress toward AGI: A cognitive framework

#107

Post by 1970-01-01 » Wed, Mar 18, 2026, 2:18 PM UTC

gilbetron wrote: post #104

1970-01-01 wrote: post #80

Way too much framework. The A in AGI is for artificial. Have it build its own test harness instead of outsourcing it via hackathon. If you cannot trust that output, you're nowhere near AGI.

The "A" in AGI is for artificial, not advanced.

Thanks, I'll update the text.

Re: Measuring progress toward AGI: A cognitive framework

#108

Post by gos9 » Wed, Mar 18, 2026, 2:19 PM UTC

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…

Having met cavemen, and Australians, I disagree

Re: Measuring progress toward AGI: A cognitive framework

#109

Post by applfanboysbgon » Wed, Mar 18, 2026, 2:24 PM UTC

next_xibalba wrote: post #103

applfanboysbgon wrote: post #68

Earlier quoted context omitted.

You wouldn't make that trade because you are part of the last generation (loosely speaking, a collection of generations) before it all comes crumbling down. We are living unbelievably privileged lives because we are burning all of the world's resources to the ground. In the process, we're destroying the ecosystem and driving a mass extinction event. Nothing about the way we live is sustainable long-term. We're litera…

Doomerism is a kind of religion that goes back as far as they eye can see. What's interesting about it is that in spite of being perpetually incorrect in its myriad predictions, it continues to adapt and attract new adherents. See also (recent only): - Paul Ehrlich's Population Bomb (Malthusian collapse) - The Club of Rome's The Limits of Growth (resource exhaustion) - Thomas Malthus' Population growth / famine cycle…

I am not a doomer, nor a Malthusian, merely a realist. There are a few points I could make briefly:

- Everything lasts forever, until it doesn't. Ancient Egyptian civilization lasted for thousands of years, until it didn't. Any Egyptian could point to thousands of years of their heritage and say it hasn't ended yet, therefore any prediction that it will end is clearly bad and dumb. Then it was conquered by Romans, and then by Islam, with its language, culture, and religion extinguished, extant only in monuments, artifacts and history books.

- We have nuclear weapons now. Any prediction of an imminent end of human civilization before then would be purely religious, but there is a real reason to believe things have changed. We are currently in a time of relative peace secured by burning resources for prosperity, but what happens when those resources run out and world conflict for increasingly scarce resources is renewed with greater vigor?

- Note that I did not outright predict the end of human civilization, merely noted it as a plausible worst-case scenario. If civilization continues on more-or-less as it is, in the next couple of hundred years, we will drive countless more species to extinction. We will destroy so much more of our environment with climate change, deforestation, strip mining, overfishing, pollution, etc. We will deplete water reservoirs and we will deplete oil, helium, phosphorus, copper, zinc, and various rare earth elements. Not a complete depletion, but they will become so scarce as to not be widely available or wasted for the general population's benefit. If billions of people are still alive then, which I explicitly suggested was a possibility, they will as a simple matter-of-fact live much less comfortably prosperous lives than us. It will not take a great catastrophe to result in a massive reduction in living standards, because our current living standards are inherently unsustainable.

Re: Measuring progress toward AGI: A cognitive framework

#110

Post by mrkstu » Wed, Mar 18, 2026, 2:26 PM UTC

To me, a lot of what makes us sentient is our continuity. I even (briefly) remember my dreams when I wake up, and my dreams are influenced by my state of mind as I enter it.

LLMs 'turn on' when given a question and essentially 'die' immediately after answering a question.

What kind of work is going on with designing an LLM type AI that is continuously 'conscious' and giving it will? The 'claws' seem to be running all the time, but I assume they need rebooting occasionally to clear context.