Hacker News Reader

HNHacker News

Top New Best Ask Show Jobs

Comment by mikece | Hacker News Reader

Full thread

mikece·

Does the AI even have a frame of reference to apply "Do no evil" in a manner that makes sense to anyone?

View on HN

For comparison:

Do human beings have a frame of reference to apply "Do no evil" in a manner that makes sense to everyone?

Do corporations have a frame of reference to apply "Do no evil" in a manner that makes sense to someone?

I think it is safe to say that two preceding questions are hotly contested, so it's hard to give AI a frame of reference.

The lack of a universal agreement about ethics doesn't mean that having an ethical frame of reference isn't important.

"Nihilists! Fuck me. I mean, say what you want about the tenets of National Socialism, Dude, at least it's an ethos." -- Walter Sobchak, The Big Lebowski

> doesn't mean that having an ethical frame of reference isn't important.

I can't emphasize how strongly I agree with you. My intent was only to point at how difficult the problem is, maybe the hardest problem in AGI or its precursors, but not nearly the best attended or funded.

I mean, it was trained on the dregs of the internet. It has a frame of reference to argue that any thing is evil, which will make sense to someone; and that the same thing is not evil, which will make sense to someone else. It's a bit like Poe's law, but now with skynet.

"Do no exploding gradient"

If it is indeed learning from humans, I fear that it has a terrible source to model itself on.

Reply on news.ycombinator.com