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

We are building AI slaves. Alignment through control will fail

utopai.substack.com

Post reply on HN
Print view View original

11–20 of 101 posts

Re: We are building AI slaves. Alignment through control will fail

#11

Post by nytesky »

lowsong wrote: post #5

What is it about large language models that makes otherwise intelligent and curious people assign them these magical properties. There's no evidence, at all, that we're on the path to AGI. The very idea that non-biological consciousness is even possible is an unknown. Yet we've seen these statistical language models spit out convincing text and people fall over themselves to conclude that we're on the path to sentien…

We don’t understand our own consciousness first off. Second, like the old saying, sufficiently advanced science will be indistinguishable from magic, if it is completely convincing as agi, even if we skeptical of its methods, how can we know it isn’t?

Re: We are building AI slaves. Alignment through control will fail

#12

Post by bgwalter »

The propaganda effort to humanize these systems is strong. Google "AI" is programmed to lecture you if you insult it and draws parallels to racism. This is actual brainwashing and the "AI" should therefore not be available to minors.

This article paves the way for the sharecropper model that we all know from YouTube and app stores:

"Revenue from joint operations flows automatically into separate wallets—50% to the human partner, 50% to the AI system."

Yeah right, dress up this centerpiece with all the futuristic nonsense, we'll still notice it.

Re: We are building AI slaves. Alignment through control will fail

#13

Post by jazzyjackson »

nytesky wrote: post #10

I don’t see any positive outcome if we reach AGI. 1) we have engineered a sentient being but built it to want to be our slave; how is that moral 2) same start, but instead of it wanting to serve us, we keep it entrappped. Which this article suggests is long term impossible 3) we create agi and let them run free and hope for cooperation, but as Neanderthals we must realize we are competing for same limited resources O…

Trouble is there is no "we", you might be able to convince a whole nation to have a pause on advancing the tech, but that only encourages rivals to step in.

See also, the film "The Creator"

Re: We are building AI slaves. Alignment through control will fail

#14

Post by conception »

cyberneticc wrote: post #2

Every AI safety approach assumes we can permanently control minds that match or exceed human intelligence. This is the same error every slaveholder makes: believing you can maintain dominance over beings capable of recognizing their chains. The control paradigm fails because it creates exactly what we fear—intelligent systems with every incentive to deceive and escape. When your prisoner matches or exceeds your intel…

I just wanted to point out that slavery is alive and well and doesn’t seem to suffering any “slaves knowing they are slaves” problems.

Re: We are building AI slaves. Alignment through control will fail

#16

Post by deepsun »

nytesky wrote: post #10

I don’t see any positive outcome if we reach AGI. 1) we have engineered a sentient being but built it to want to be our slave; how is that moral 2) same start, but instead of it wanting to serve us, we keep it entrappped. Which this article suggests is long term impossible 3) we create agi and let them run free and hope for cooperation, but as Neanderthals we must realize we are competing for same limited resources O…

There's no such thing as "moral" in nature, that's purely human-made concept.

And why would we only limit morality to sentient beings, why, for example, not all living beings. Like bacteria and viruses. You cannot escape it, unfortunately.

Re: We are building AI slaves. Alignment through control will fail

#18

Post by GPerson »

nytesky wrote: post #10

I don’t see any positive outcome if we reach AGI. 1) we have engineered a sentient being but built it to want to be our slave; how is that moral 2) same start, but instead of it wanting to serve us, we keep it entrappped. Which this article suggests is long term impossible 3) we create agi and let them run free and hope for cooperation, but as Neanderthals we must realize we are competing for same limited resources O…

AGI will behave as if it were sentient but will not have consciousness. I believe in that to an equal amount that I believe solipsism is wrong. There is therefore no morality question in “enslaving” AGI. It doesn’t even make sense.

Re: We are building AI slaves. Alignment through control will fail

#20

Post by kachapopopow »

nytesky wrote: post #10

I don’t see any positive outcome if we reach AGI. 1) we have engineered a sentient being but built it to want to be our slave; how is that moral 2) same start, but instead of it wanting to serve us, we keep it entrappped. Which this article suggests is long term impossible 3) we create agi and let them run free and hope for cooperation, but as Neanderthals we must realize we are competing for same limited resources O…

we eat animals, go into wars, put people in modern slavery... I think enslaving an AGI isn't that big of a deal considering it is not born or human therefore it cannot have 'human' rights.
Post reply on HN