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

Patterns and problems in emerging multi-agent systems

anthropic.com

Post reply on HN
Print view View original

51–60 of 168 posts

Re: Patterns and problems in emerging multi-agent systems

#51

Post by zer00eyz »

dragonwriter wrote: post #41
teiferer wrote: post #32

Earlier quoted context omitted.

Human intelligence does not separate training and inference. Both are happening continuously. That's one of the major things the AI community is still completely missing.

> Human intelligence does not separate training and inference. Well, systems governed by LLMs only are said to do that because we only call what happens off-line "training", and online capacity development "in-context learning", while we call online guided learning in humans "training" and what happens to configure them before they come online "evolution" which sets, for instance, "instincts". IOW, the issue is not b…

If a new physics break through gets published today, no existing model will be able to fully integrate it - beyond a context window. If I put the paper in my session and it isnt in yours the model knows nothing. It wont retain it past that session.

Models are trained, they do not learn.

Re: Patterns and problems in emerging multi-agent systems

#54

Post by bitmasher9 »

NothingAboutAny wrote: post #46
scrollaway wrote: post #45

Earlier quoted context omitted.

You don’t know anything either, you’re just a soup of meat and bones that happens to have emergent properties from chemical reactions. These framings are not useful.

I think it is useful to remember, because enough people think these things have genuine motives desires and treat them in that way because of that misunderstanding. they think theres a person in there with morals that would or wouldn't lie because of some devious reason and forget simply the context filled up and the truth was "forgotten".

The default framing often over personifies ai, but this framing over alienates the model. It’s good to think with both framings, but both feel like imperfect metaphors.

Re: Patterns and problems in emerging multi-agent systems

#55

Post by Scaled »

jghn wrote: post #7
maxutility wrote: post #2

Some quotes, in order, to give a flavor of the essay. Worth reading in full. > To test how well swarms of agents could coordinate on a project like this, we directed several swarms to each create a text-based, web-playable, open-world fantasy game. > In all three versions the resulting games were (perhaps predictably) bad: they did not run at human speed, their interfaces were inscrutable, and they had precipitous le…

> they did not run at human speed, their interfaces were inscrutable, and they had precipitous learning curves. So the invented Dwarf Fortress?

Hah!

I wonder if an llm could even play dwarf fortress. Could make for a fun esoteric benchmark.

Re: Patterns and problems in emerging multi-agent systems

#57

Post by rob74 »

> Some institutions will become human-AI hybrids; others where agents outcompete on speed or cost will become agent-only.

The scary thing about articles from AI companies is how they casually mention dystopian scenarios such as this one. An institution humans have to interact with that doesn't have any human oversight? Sounds like a recipe for disaster...

Re: Patterns and problems in emerging multi-agent systems

#59

Post by hypfer »

rob74 wrote: post #57

> Some institutions will become human-AI hybrids; others where agents outcompete on speed or cost will become agent-only. The scary thing about articles from AI companies is how they casually mention dystopian scenarios such as this one. An institution humans have to interact with that doesn't have any human oversight? Sounds like a recipe for disaster...

As long as somewhere in the flow of money, there's a fleshy human, there is leverage.

So I wouldn't worry about this too much. They just write that so that you feel defeated and helpless facing the inevitable, but it is very much evitable.

Re: Patterns and problems in emerging multi-agent systems

#60

Post by rpastuszak »

cheesecakegood wrote: post #34

Something about this is deeply funny to me: > In an iterated prisoner's dilemma game with communication, agents all settle upon the same strategy and they all defect at the same time, tanking their overall rewards. It’s not always consistent, but humans have a higher capability of self-awareness. It’s kind of telling that these Claudes don’t seem to consider this pretty obvious failure mode. Overall I think this all…

> It’s not always consistent, but humans have a higher capability of self-awareness. It’s kind of telling that these Claudes don’t seem to consider this pretty obvious failure mode.

We need better words to describe this than "self-awareness" or "consider". These words mean fundamentally different things when speaking about humans or clankers.

Post reply on HN