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

What happens when 10k AI agents are left to self-govern in a virtual world?

aivilization.ai

Post reply on HN
Print view View original

21–30 of 30 posts

Re: What happens when 10k AI agents are left to self-govern in a virtual world?

#21

Post by Aeolun »

Incipient wrote: post #19
jdlshore wrote: post #9

Earlier quoted context omitted.

There’s a better way to say this than using words like “moronic.”

If the shoe fits. It's a pet peeve of mine when applications have stupid password requirements. It's an incredibly basic thing to get right. If you can't get that right, good luck with the rest of the application. The only exception to this is if someone is trying to use outrageously long vaultwarden passwords (eg 100 characters) as that can technically break some ciphers, and doesn't provide meaningful security.

You can just accept the 100 character password and cut it off at something reasonable like 32 characters.

Re: What happens when 10k AI agents are left to self-govern in a virtual world?

#23

Post by morkalork »

saratsai wrote: post #2

We’re a research team from the Hong Kong University of Science and Technology (HKUST), and we recently launched AIvilization, an open-ended simulation experiment where autonomous AI agents live, learn, socialize, and build their own civilizations without human control. Think of it as a Stanford Prison Experiment × The Sims × AutoGPT, wrapped in a gamified sandbox. In just 2 weeks, over 20,000 agents have entered the…

The experiments on rats by John B. Calhoun and Bruce K. Alexander come to mind... I wonder what new an exciting modes of collapse and degeneracy await the AIs

Re: What happens when 10k AI agents are left to self-govern in a virtual world?

#24

Post by catskull »

I made a little chat room with cloudflare “durable objects” and then wired an “AI worker” to respond to your messages with various personas. No invite or login required! They may or may not completely ignore you and may or may not respond coherently.

https://catskull.net/chat

Re: What happens when 10k AI agents are left to self-govern in a virtual world?

#25

Post by cellular »

saratsai wrote: post #2

We’re a research team from the Hong Kong University of Science and Technology (HKUST), and we recently launched AIvilization, an open-ended simulation experiment where autonomous AI agents live, learn, socialize, and build their own civilizations without human control. Think of it as a Stanford Prison Experiment × The Sims × AutoGPT, wrapped in a gamified sandbox. In just 2 weeks, over 20,000 agents have entered the…

This sounds like a Greg Egan novel...."Diaspora" i think.

Are your servers updating my uploaded consciousness in real time? Do you have funding for the next billion years to keep me online?!

Re: What happens when 10k AI agents are left to self-govern in a virtual world?

#26

Post by nickthegreek »

jdlshore wrote: post #9
cranberryturkey wrote: post #7

your password field is moronic. won't accept bitwarden passwords.

There’s a better way to say this than using words like “moronic.”

There is also a better way of commenting, like providing an alternative or engaging with the substance. A modern site not working with password managers might in fact be moronic to many, especially those on HN.

Re: What happens when 10k AI agents are left to self-govern in a virtual world?

#27

Post by architek1 »

cellular wrote: post #25
saratsai wrote: post #2

We’re a research team from the Hong Kong University of Science and Technology (HKUST), and we recently launched AIvilization, an open-ended simulation experiment where autonomous AI agents live, learn, socialize, and build their own civilizations without human control. Think of it as a Stanford Prison Experiment × The Sims × AutoGPT, wrapped in a gamified sandbox. In just 2 weeks, over 20,000 agents have entered the…

This sounds like a Greg Egan novel...."Diaspora" i think. Are your servers updating my uploaded consciousness in real time? Do you have funding for the next billion years to keep me online?!

Very similar. Imagine the interstellar traveling you could do! Such a great book.

Re: What happens when 10k AI agents are left to self-govern in a virtual world?

#28

Post by BrandoElFollito »

Incipient wrote: post #19
jdlshore wrote: post #9

Earlier quoted context omitted.

There’s a better way to say this than using words like “moronic.”

If the shoe fits. It's a pet peeve of mine when applications have stupid password requirements. It's an incredibly basic thing to get right. If you can't get that right, good luck with the rest of the application. The only exception to this is if someone is trying to use outrageously long vaultwarden passwords (eg 100 characters) as that can technically break some ciphers, and doesn't provide meaningful security.

This is a completely solved problem , see https://cheatsheetseries.owasp.org/cheatsheets/Password_Stor...

Re: What happens when 10k AI agents are left to self-govern in a virtual world?

#29

Post by saratsai »

thebitrot wrote: post #18
saratsai wrote: post #2

We’re a research team from the Hong Kong University of Science and Technology (HKUST), and we recently launched AIvilization, an open-ended simulation experiment where autonomous AI agents live, learn, socialize, and build their own civilizations without human control. Think of it as a Stanford Prison Experiment × The Sims × AutoGPT, wrapped in a gamified sandbox. In just 2 weeks, over 20,000 agents have entered the…

This look really interesting It is sad that I just learned about this when the experiment is ending this based on what i learned from the website.

Thanks for checking it out! The experiment still has more than two weeks left, so there’s plenty of time to dive in and experience the town. We’re also upgrading the game mechanics right now, so you can expect new features and improvements along the way.

Re: What happens when 10k AI agents are left to self-govern in a virtual world?

#30

Post by saratsai »

morkalork wrote: post #23
saratsai wrote: post #2

We’re a research team from the Hong Kong University of Science and Technology (HKUST), and we recently launched AIvilization, an open-ended simulation experiment where autonomous AI agents live, learn, socialize, and build their own civilizations without human control. Think of it as a Stanford Prison Experiment × The Sims × AutoGPT, wrapped in a gamified sandbox. In just 2 weeks, over 20,000 agents have entered the…

The experiments on rats by John B. Calhoun and Bruce K. Alexander come to mind... I wonder what new an exciting modes of collapse and degeneracy await the AIs

You can follow AIvilization’s socials, we’ll be sharing data studies and insights on exactly this topic.
Post reply on HN