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

151–160 of 173 posts

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

#151

Post by MichaelZuo »

chefandy wrote: post #138
mywittyname wrote: post #137

Earlier quoted context omitted.

Sandbox games are probably where they will shine. Imagine being able to play Minecraft, and tell a prompt to generate a world that resembles Tatooine, or a vampire-themed mansion. Expectations are lower with sandbox games, so there's no risk of breaking immersion like would happen with an LLM Elder Scrolls game when someone tricks in NPC into solving problems in python. Granted, I'm certain there will be copyrights i…

The problem is what it takes to implement that. I've seen companies currently trying to do exactly that, and their demos go like this "ok, give me a prompt for the environment" and if they're lucky, they can cherry pick some stuff the crowd says and if they're not, they sheepishly ask for a prompt that would visit indicate one of 5 environment types they've worked on and include several of the dozen premade textured…

What are the actual claims and/or arguments?

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

#152

Post by chefandy »

MichaelZuo wrote: post #151
chefandy wrote: post #138

Earlier quoted context omitted.

The problem is what it takes to implement that. I've seen companies currently trying to do exactly that, and their demos go like this "ok, give me a prompt for the environment" and if they're lucky, they can cherry pick some stuff the crowd says and if they're not, they sheepishly ask for a prompt that would visit indicate one of 5 environment types they've worked on and include several of the dozen premade textured…

What are the actual claims and/or arguments?

To automatically generate a freeform 3D sandbox environment based on a prompt? Do you have a specific criticism or counterpoint?

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

#153

Post by MichaelZuo »

chefandy wrote: post #152
MichaelZuo wrote: post #151

Earlier quoted context omitted.

What are the actual claims and/or arguments?

To automatically generate a freeform 3D sandbox environment based on a prompt? Do you have a specific criticism or counterpoint?

How does this relate to the parent comment? Is there some counterargument why X is unlikely due to Y reasons?

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

#154

Post by bbor »

ValentinA23 wrote: post #110
bbor wrote: post #68

Earlier quoted context omitted.

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 ?

Hmm that's a good point, but IMO the distinction isn't sharp enough to make a big deal over. The core idea of SoM as I see it is that human cognition is often quite decentralized, and that any illusion of a unified self is constructed piecemeal from the outputs of smaller, less-aware subsystems. Generally it's expected that the subsystems communicate with each other, yes, but I think "disproportionately rely on one or two members for complex questions but act like you're unified overall" still fits the bill.

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

#155

Post by sangnoir »

j1elo wrote: post #121
wongarsu wrote: post #118

Earlier quoted context omitted.

We also can't rule out that Gaia or Odin made the world five minutes ago, and went to great lengths to make the world appear ancient. It certainly makes sense if you assume that the world is a simulation. But does it actually explain anything that isn't equally well explained by assuming the simulation simulated the last 13 billion years, and evolution really happened?

As long as we don't get to the point of being able to simulate a Universe ourselves, the odds are against us being in a simulation, it seems! :) https://www.youtube.com/shorts/EeqyGquTHK4

There's a built-in assumption that there would be no constraints applied on nested simulation anywhere further down the stack, which is IMO unlikely, unless every layer has unlimited compute, or otherwise interested in investigating nested simulations.

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

#156

Post by chefandy »

MichaelZuo wrote: post #153
chefandy wrote: post #152

Earlier quoted context omitted.

To automatically generate a freeform 3D sandbox environment based on a prompt? Do you have a specific criticism or counterpoint?

How does this relate to the parent comment? Is there some counterargument why X is unlikely due to Y reasons?

"Sandbox games are probably where they will shine. Imagine being able to play Minecraft, and tell a prompt to generate a world that resembles Tatooine, or a vampire-themed mansion."

"The problem is what it takes to implement that. I've seen companies currently trying to do exactly that, and their demos go like this "ok, give me a prompt for the environment" and if they're lucky, they can cherry pick some stuff the crowd says and if they're not, they sheepishly ask for a prompt that would visit indicate one of 5 environment types they've worked on and include several of the dozen premade textured meshes they've made[...]"

I was clearly directly addressing what they said. Unless you have a specific, substantive, on-topic question or statement, I'm going to assume that you're just fishing for things to argue about.

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

#157

Post by herewulf »

whatshisface wrote: post #57
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…

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

"learning" as a noun descends from Old English so has always been current in the language in the intended sense.[1]

"lesson" came from Old French in the 13th century and has changed its original meaning over time.[2]

There's not one single dialect of English so your comment comes off as unnecessarily prescriptivist and has spawned significant off-topic commentary (including this very comment) in response to an otherwise perfectly worded composition.

[1]: https://www.etymonline.com/word/learning [2]: https://www.etymonline.com/word/lesson

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

#158

Post by MichaelZuo »

chefandy wrote: post #156
MichaelZuo wrote: post #153

Earlier quoted context omitted.

How does this relate to the parent comment? Is there some counterargument why X is unlikely due to Y reasons?

"Sandbox games are probably where they will shine. Imagine being able to play Minecraft, and tell a prompt to generate a world that resembles Tatooine, or a vampire-themed mansion." "The problem is what it takes to implement that. I've seen companies currently trying to do exactly that, and their demos go like this "ok, give me a prompt for the environment" and if they're lucky, they can cherry pick some stuff the cr…

You can assume whatever you want, but your assumptions can never outweigh the assumptions of anyone else on HN… so the last sentence doesn’t make sense?

Plus listing past examples doesn’t indicate future possibilities must conform to that… unless there is a specific argument on why that should be the case on the balance of probabilities… so are you sure you understood my previous questions?

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

#159

Post by chefandy »

MichaelZuo wrote: post #158
chefandy wrote: post #156

Earlier quoted context omitted.

"Sandbox games are probably where they will shine. Imagine being able to play Minecraft, and tell a prompt to generate a world that resembles Tatooine, or a vampire-themed mansion." "The problem is what it takes to implement that. I've seen companies currently trying to do exactly that, and their demos go like this "ok, give me a prompt for the environment" and if they're lucky, they can cherry pick some stuff the cr…

You can assume whatever you want, but your assumptions can never outweigh the assumptions of anyone else on HN… so the last sentence doesn’t make sense? Plus listing past examples doesn’t indicate future possibilities must conform to that… unless there is a specific argument on why that should be the case on the balance of probabilities… so are you sure you understood my previous questions?

confirmed.

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

#160

Post by MichaelZuo »

chefandy wrote: post #159
MichaelZuo wrote: post #158

Earlier quoted context omitted.

You can assume whatever you want, but your assumptions can never outweigh the assumptions of anyone else on HN… so the last sentence doesn’t make sense? Plus listing past examples doesn’t indicate future possibilities must conform to that… unless there is a specific argument on why that should be the case on the balance of probabilities… so are you sure you understood my previous questions?

confirmed.

> confirmed.

Huh? Is this an AI response?

Post reply on HN