They imitate humans. Alignment is about shaping their behavior towards safety.

Alignment is a myth. Safety of whom? Humanity couldn't agree on common set of values for thousands of years and we're not gonna suddenly do that in the next ten.

▲

esafak 11 hours ago | parent [-]

Safety of humans!!! Simple things like not getting killed or enslaved. We could start there...

▲

sick_of_slop an hour ago | parent | next [-]

The atomic bombings of Japan killed hundreds of thousands of people but most likely "saved" millions.

What should the AI do when asked if it should nuke a country?

▲

nradov 11 hours ago | parent | prev | next [-]

But what if I want certain other humans to get killed?

▲

sejje 11 hours ago | parent [-]

Then we should still prioritize the safety of humans

	▲	sm-silversight 11 hours ago \| parent \| next [-]
		What if I want to smoke cigarettes? Or sell tobacco I grew artisinally to enthusiast tobacco smokers?
	▲	drdaeman 11 hours ago \| parent \| prev [-]
		Which ones?

▲

comboy 11 hours ago | parent | prev | next [-]

Which ones? Because many humans kill other humans rationalizing it by safety of other humans.

I mean I know it seems simple, let's just be excellent to each other. Christianity got pretty far on a decent basic set of values. But it's never simple[1]

1. All the history books

▲

mcintyre1994 9 hours ago | parent | prev | next [-]

Surely all the AI companies working with the US Department of War shows this is nonsense though? Even if they have accepted Anthropic’s red line of no autonomous lethal weapons, which seems to be the strictest anyone tried to impose, that’s still leaving tonnes of room where they intend AI to help target and kill humans.

▲

watwut 9 hours ago | parent | prev [-]

But Thiel wants people enslaved and Musk wants then killed. Altman wants them "obsolete" which means desolation.

AfD wants people dead. Right wing men wants women without rights and docile. I could go on ...

▲

codys 10 hours ago | parent | prev | next [-]

Despite all the fancy language, its more about aligning the AI behavior with the corporation's interests.

ie: the corporation wants the AI to behave a certain way for various reasons: to make it easier for them to avoid regulation, to make the corporation more money via different tiers of AI offerings, to ensure that the corporations products are hard for competitors to use, etc. And those are just the easy ones.

Every product is shaped this way. AI is not different.

▲

catoc 8 hours ago | parent | prev [-]

If they do, they imitate the way humans are portrayed online, in the media. That is a very distorted view of humanity