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

Show HN: Decided to play god this morning, so I built an agent civilisation

github.com

Post reply on HN
Print view View original

31–40 of 40 posts

Re: Show HN: Decided to play god this morning, so I built an agent civilisation

#31

Post by svilen_dobrev »

urav wrote: post #15
gyomu wrote: post #6

> Werld drops 30 agents onto a graph with NEAT neural networks that evolve their own topology, 64 sensory channels, continuous motor effectors, and 29 heritable genome traits. communication bandwidth, memory decay, aggression vs cooperation — all evolvable. No hardcoded behaviours, no reward functions. - they could evolve in any direction. In the days when Sussman was a novice, Minsky once came to him as he sat hacki…

Love the MIT AI Koans. Minsky's actual words to Sussman were "well, it has them, it's just that you don't know what they are." And he's right, the room isn't empty. Werld's room has walls. The graph topology, energy mechanics, metabolic costs, seasons, those are all design choices. But those are the physics, not the behavior. I chose the laws of nature, not what agents do with them. Whether they cooperate or attack,…

some hand-wavy thoughts..

> it has them (preconceptions), it's just that you don't know what they are.

further in this direction... the "thing" might evolve into some cyclic (or not) system. a bit like that LIFE game, emerging a tv-tennis-like ping-ponging, or whatever. How would you know there is such thing? just stats/counts do not tell. (Which pulls another freaky question - how would u notice a different intelligence/world-order/culture/resemblance-of?)

maybe feature: some stop-gap animation over world-map in time? Then, some pattern analysis over that.. History of the world, part one..

btw check these "interactive simulations", maybe some ideas about "loading" the agents with preconceptions :)

https://ncase.me/

Re: Show HN: Decided to play god this morning, so I built an agent civilisation

#32

Post by BrandoElFollito »

m0llusk wrote: post #20

Arguably a powerful demonstration of why even simple creatures make use of parenting as a strategy to improve the success of their offspring.

This is a very different conclusion from the one in the scientific documentary "Idiocracy"

Re: Show HN: Decided to play god this morning, so I built an agent civilisation

#33

Post by wibbily »

dash2 wrote: post #2

I think it looks fun, but at the same time I really wish you had written the readme yourself and not using an llm. My view: if you can’t be bothered to write it yourself, why should I read it myself?

He's not writing his comments himself either. Better off ignoring the whole thing, unfortunately

Re: Show HN: Decided to play god this morning, so I built an agent civilisation

#35

Post by urav »

svilen_dobrev wrote: post #31
urav wrote: post #15

Earlier quoted context omitted.

Love the MIT AI Koans. Minsky's actual words to Sussman were "well, it has them, it's just that you don't know what they are." And he's right, the room isn't empty. Werld's room has walls. The graph topology, energy mechanics, metabolic costs, seasons, those are all design choices. But those are the physics, not the behavior. I chose the laws of nature, not what agents do with them. Whether they cooperate or attack,…

some hand-wavy thoughts.. > it has them (preconceptions), it's just that you don't know what they are. further in this direction... the "thing" might evolve into some cyclic (or not) system. a bit like that LIFE game, emerging a tv-tennis-like ping-ponging, or whatever. How would you know there is such thing? just stats/counts do not tell. (Which pulls another freaky question - how would u notice a different intellig…

thing you've caught onto something there, after running it for a while (maybe not long enough) it can feel cyclical.

I'll definitely add in the time-lapse, and some sort of a pattern detection over the agent positions/actions - shouldn't be too tough given the graph structure of the world.

for the ncase.me - super interesting way to visualise it - the polyworld example someone gave before also had a 'view' into their worlds. on the preconceptions, maybe running two parallel experiments and comparing the outputs might work best? thanks for the pointers - let me know if you've got any ideas on how to approach.

Re: Show HN: Decided to play god this morning, so I built an agent civilisation

#36

Post by supersparrow »

dash2 wrote: post #2

I think it looks fun, but at the same time I really wish you had written the readme yourself and not using an llm. My view: if you can’t be bothered to write it yourself, why should I read it myself?

Just because he didn’t write the readme himself doesn’t mean it’s irrelevant. The OP will have (hopefully) at least read through it before committing it and at that point the content is relevant and if the OP cares, accurate. You’re generalising if you think everyone blindly copy pastes LLM output

Re: Show HN: Decided to play god this morning, so I built an agent civilisation

#38

Post by hulitu »

alexhans wrote: post #5

I love emergent behaviour and story telling. Anyone who has played City builders like Sim City or roguelikes like Dwarf Fortress knows how interesting, fun and even informative they can be. In a world where setting them up and letting rogue agents run rampant becomes relatively low cost and fast, I think focusing on the desired outcomes, the story telling and specially the UX for the human user, is key and maybe we c…

> Anyone who has played City builders like Sim City or ... knows how interesting, fun and even informative they can be.

Yes. The most intersting and fun thing in SimCity was always having to upgrade your storage. So instead of building a City you were building storage. /s

Post reply on HN