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

Project Sid: Many-agent simulations toward AI civilization

github.com

Post reply on HN
Print view View original

101–110 of 173 posts

Re: Project Sid: Many-agent simulations toward AI civilization

#101

Post by grugagag »

ekianjo wrote: post #85
grugagag wrote: post #44

Earlier quoted context omitted.

Not if we’re pretending it is any inteligent. Other than that I’m all in for new utility to come out from it. But I do see a lot of tangents off technology with claims to something it is not. I have no problem of calling that out. Why do you mind? Just ignore me if Im holding your enthusiasm back, there’s plenty of sources to provide that for you.

> Not if we’re pretending it is any inteligent. We have been shifting the definition of what it means to be intelligent every 3 months following the advances of LLM...

So what? I’m not disputing that the immitation of intelligence is not good and it gets better and better every 3 months or so. But that doesn’t mean anything, even if it gets close to 99.9%. It is not real intlligence and it is quite limited in what it does. If LLMs solve logic or problems or chemistry problems it is solely not because it made a leap in understanding but because it was trained on a zillion examples. If you have a similar problem it will try to showhorn an answer without understanding where it fails. Am I saying this is useless? NO. What I’m saying is that the current approach to intelligence is missing some key ingredients. Im actually surprised so many get fooled by the hype and are ready to declare a winner. Human intelligence with it’s major flaws is still king of the hill.

Re: Project Sid: Many-agent simulations toward AI civilization

#102

Post by FeepingCreature »

InDubioProRubio wrote: post #95
bob1029 wrote: post #70

I feel like there is some kind of information theory constraint which confounds our ability to extract higher order behavior from multiple instances of the same LLM. I spent quite a bit of time building a multi agent simulation last year and wound up at the same conclusion every day - this is all just a roundabout form of prompt engineering. Perhaps it is useful as a mental model, but you can flatten the whole thing…

Maybe we need gazelles and cheetahs - many gazelle-agents getting chased towards a goal, doing the brute force work- and the constraint cheetahs chase them, evaluate them and leave them alive (memory intact) as long as they come up with better and better solutions. Basically a evolutionary algo, running on top of many agents, running simultaneously on the same hardware?

Do you want stressed and panicking agents? Do you think they'll produce good output?

In my prompting experience, I mostly do my best to give the AI way, way more slack than it thinks it has.

Re: Project Sid: Many-agent simulations toward AI civilization

#103

Post by grugagag »

mistermann wrote: post #90
ekianjo wrote: post #85

Earlier quoted context omitted.

> Not if we’re pretending it is any inteligent. We have been shifting the definition of what it means to be intelligent every 3 months following the advances of LLM...

There's also this: https://en.m.wikipedia.org/wiki/Closed-world_assumption I wonder, once LLM's exceed Humans beyond some substantial threshold, will it crack the simulation allowing us to get back in the game again.

Crack what simulation exactly? You can get back into the game right now, armed with these tools such as LLMs, ML and so on.

Re: Project Sid: Many-agent simulations toward AI civilization

#104

Post by FeepingCreature »

mindcrime wrote: post #60
whatshisface wrote: post #57

Earlier quoted context omitted.

Just so you know, the English noun for things that have been learned is, "lessons."

Also: "learnings". https://dictionary.cambridge.org/us/dictionary/english/learn... "knowledge or a piece of information obtained by study or experience" "I am already incorporating some of these learnings into my work and getting better results."

That example was added in 2022. https://web.archive.org/web/20190903044149/https://dictionar...

You can clearly see that the prior use was very different.

Cambridge Dictionary just documents that it's in fact used that way. One may still disagree on whether it should be.

"That's not English" is usually prescriptive, rather than descriptive. And though English does not have a central authority, individuals are very much allowed to hold prescriptive beliefs - that is how language evolves.

Re: Project Sid: Many-agent simulations toward AI civilization

#105

Post by nobrains »

InDubioProRubio wrote: post #95
bob1029 wrote: post #70

I feel like there is some kind of information theory constraint which confounds our ability to extract higher order behavior from multiple instances of the same LLM. I spent quite a bit of time building a multi agent simulation last year and wound up at the same conclusion every day - this is all just a roundabout form of prompt engineering. Perhaps it is useful as a mental model, but you can flatten the whole thing…

Maybe we need gazelles and cheetahs - many gazelle-agents getting chased towards a goal, doing the brute force work- and the constraint cheetahs chase them, evaluate them and leave them alive (memory intact) as long as they come up with better and better solutions. Basically a evolutionary algo, running on top of many agents, running simultaneously on the same hardware?

I had the opposite thought. Opposite to evolution...

What if we are a CREATED (i.e. instant created, not evolved) set of humans, and evolution and other backstories have been added so that the story of our history is more believable?

Could it be that humanity represents a de novo (Latin for "anew") creation, bypassing the evolutionary process? Perhaps our perception of a gradual ascent from primitive origins is a carefully constructed narrative designed to enhance the credibility of our existence within a larger framework.

What if we are like the Minecraft people in this simulation?

Re: Project Sid: Many-agent simulations toward AI civilization

#106

Post by thrway01234 »

nobrains wrote: post #105
InDubioProRubio wrote: post #95

Earlier quoted context omitted.

Maybe we need gazelles and cheetahs - many gazelle-agents getting chased towards a goal, doing the brute force work- and the constraint cheetahs chase them, evaluate them and leave them alive (memory intact) as long as they come up with better and better solutions. Basically a evolutionary algo, running on top of many agents, running simultaneously on the same hardware?

I had the opposite thought. Opposite to evolution... What if we are a CREATED (i.e. instant created, not evolved) set of humans, and evolution and other backstories have been added so that the story of our history is more believable? Could it be that humanity represents a de novo (Latin for "anew") creation, bypassing the evolutionary process? Perhaps our perception of a gradual ascent from primitive origins is a car…

I feel that is too complicated. The most simplest explanation is usually the right one. I think we live on an earth with actual history. Note that this does not necessarily mean that we are not living in a simulation, as history itself can be simulated.

If we are indeed in a simulation, I feel there are too many details to be "designed" by a being. There are too many facts that are connected and unless they fix the "bugs" as they appear and reboot the simulation constantly, I don't think it is designed. Otherwise we would have noticed the glitches by now.

If we are in a simulation, it has probably been generated by a computer following a set of rules. Maybe it ran a simplified version to evolve millions of possible earths, and then we are living in the version they selected for the final simulation? In that case all the facts would align and it could potentially be harder to noticed the glitches.

I don't think we are living in a simulation because bugs are hard to avoid, even with close to "infinite" computing power. With great power comes great possibilities for bugs

Perhaps we are in fact living in one of the simplified simulations and will be turned off at any second after I have finished this senten

Re: Project Sid: Many-agent simulations toward AI civilization

#107

Post by ElFitz »

jsemrau wrote: post #25
isoprophlex wrote: post #3

Now these seem to be truly artificially intelligent agents. Memory, volition, autonomy, something like an OODA loop or whatever you want to call it, and a persistent environment. Very nice concept, and I'm positive the learnings can be applied to more mundane business problems, too. If only I could get management to understand that a bunch of prompts shitting into eachother isn't "cutting-edge agentic AI"... But then…

>If only I could get management to understand that a bunch of prompts shitting into eachother isn't "cutting-edge agentic AI"... It should never be this way. Even with narrow AI, there needs to be a governance framework that helps measure the output and capture potential risks (hallucinations, wrong data / links, wrong summaries, etc)

Do you have any resources on that topic? I’d be interested.

Re: Project Sid: Many-agent simulations toward AI civilization

#108

Post by InDubioProRubio »

FeepingCreature wrote: post #102
InDubioProRubio wrote: post #95

Earlier quoted context omitted.

Maybe we need gazelles and cheetahs - many gazelle-agents getting chased towards a goal, doing the brute force work- and the constraint cheetahs chase them, evaluate them and leave them alive (memory intact) as long as they come up with better and better solutions. Basically a evolutionary algo, running on top of many agents, running simultaneously on the same hardware?

Do you want stressed and panicking agents? Do you think they'll produce good output? In my prompting experience, I mostly do my best to give the AI way, way more slack than it thinks it has.

No, i want the hunters to zap the prey with tiredness. Basically electron holes, hunting for free electrons, annhilating state. Neurons have something similar, were they usually prevent endless excitement and hyperfixation, which is why a coder in flow is such a strange thing.

Re: Project Sid: Many-agent simulations toward AI civilization

#109

Post by logicchains »

bob1029 wrote: post #70

I feel like there is some kind of information theory constraint which confounds our ability to extract higher order behavior from multiple instances of the same LLM. I spent quite a bit of time building a multi agent simulation last year and wound up at the same conclusion every day - this is all just a roundabout form of prompt engineering. Perhaps it is useful as a mental model, but you can flatten the whole thing…

>I feel like there is some kind of information theory constraint which confounds our ability to extract higher order behavior from multiple instances of the same LLM.

It's a matter of entropy; producing new behaviours requires exploration on the part of the models, which requires some randomness. LLMs have only a minimal amount of entropy introduced, via temperature in the sampler.

Re: Project Sid: Many-agent simulations toward AI civilization

#110

Post by ValentinA23 »

bbor wrote: post #68
hackathonguy wrote: post #65

I'm curious if it might be possible that an AI "civilization", similar to the one proposed by Altera, could end up being a better paradigm for AGI than a single LLM, if a workable reward system for the entire civilization was put in place. Meaning, suppose this AI civilization was striving to maximize [scientific_output] or [code_quality] or any other eval, similar to how modern countries try to maximize GDP - would…

Yes, good sense for progress! This has been a central design component of most serious AI work since the ~90s, most notably popularized by Marvin Minsky’s The Society of Mind . Highly, highly recommend for anyone with an interest in the mind and AI — it’s a series of one-page essays on different aspects of the thesis, which is a fascinating, Martin-Luther-esque format. Of course this has been pushed to the side a bit…

I don't think "mixture of experts" can be assimilated to a society of agents. It is just routing a prompt to the most performant model: the models do not communicate with each other, so how could they form a society ?
Post reply on HN