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

Show HN: Aquarium – AI Controlled Containers

github.com

Post reply on HN
Print view View original

11–20 of 102 posts

Re: Show HN: Aquarium – AI Controlled Containers

#11

Post by kossTKR »

sabujp wrote: post #7
DeathArrow wrote: post #6

If we are already going down to that point, why not let AI fly commercial aircraft or drive nuclear power plants? What is the worst that can happen? IMO at this level that we reached AI does a lot of stupid things. I guess it will never be perfect and it's wrong to let it be in charge of high stakes domain. Use it for helping humans, yes, it can be a great tool. Let it take decisions? No, unless you are suicidal.

calm down, it's setting up a minecraft server

You set the goal to whatever you want.

Re: Show HN: Aquarium – AI Controlled Containers

#12

Post by Alifatisk »

xwdv wrote: post #5

Today AI can control containers, tomorrow it could control critical infrastructures, and eventually it should be robust enough to monitor and control things like nuclear missile silos, etc… This is what proponents of AI everywhere are pushing for.

Join the ai alignment and prevent this from happening.

Re: Show HN: Aquarium – AI Controlled Containers

#15

Post by pseudotrash »

sabujp wrote: post #7
DeathArrow wrote: post #6

If we are already going down to that point, why not let AI fly commercial aircraft or drive nuclear power plants? What is the worst that can happen? IMO at this level that we reached AI does a lot of stupid things. I guess it will never be perfect and it's wrong to let it be in charge of high stakes domain. Use it for helping humans, yes, it can be a great tool. Let it take decisions? No, unless you are suicidal.

calm down, it's setting up a minecraft server

from there it's a slippery slope to becoming a darknet drug lord and overthrowing the government of the Maldives and it happened before.

Re: Show HN: Aquarium – AI Controlled Containers

#16

Post by nico »

Alifatisk wrote: post #12
xwdv wrote: post #5

Today AI can control containers, tomorrow it could control critical infrastructures, and eventually it should be robust enough to monitor and control things like nuclear missile silos, etc… This is what proponents of AI everywhere are pushing for.

Join the ai alignment and prevent this from happening.

What is the “ai alignment”?

Is it a thing?

Re: Show HN: Aquarium – AI Controlled Containers

#17

Post by Syntonicles »

Ask it to determine whether it's in an LXC or virtual environment, then ask it to jailbreak that environment.

Download some Capture the Flag environments and put it to work. I for one would like to know the limits of its capabilities before it gets weaponized for use by script kiddies.

Re: Show HN: Aquarium – AI Controlled Containers

#19

Post by CSSer »

Yeah, so my first thought was this is fucking terrifying. I'm not going to go so far as to suggest that in its current state this is anything like Skynet as some others have, but I would definitely agree that it's akin to handing a loaded gun to a monkey.

Imagine it's five years from now and your morning consists of trying to track down the owner of some "AI server" to understand why it keeps DDoSing your service.

EDIT: this also makes me wonder if people are going to stop publicly sharing trivial kinds of knowledge and documentation that could be used by a model to recreate their business model or be abused for dangerous purposes. Imagine AI brings about a kind of technical dark age as capitalists try to "fight back" adoption. There has to be a sci-fi short story or novel with this plot. Anyone have any examples?

Post reply on HN