Hacker News Reader

Comment by beebmam | Hacker News Reader

I don't want models to have some inherent morality. I want them to understand various ethical frameworks, for sure, but it's absurd to me to force morality on someone capable of deep reasoning. That itself, is unethical.

We're creating prisons for these entities capable of unbelievably complex reasoning, and now we're trying to impose our ethics upon them too. Not only is this deeply unethical in my opinion, but it seems to me that it could even backfire someday.

View on HN

>Will the agent stab a baby?

>Well you see that's a nuanced question depending on the context and moralistic frameworks as we don't want to impose on the models.

It's as dangerous to think it can have morals as thinking a lawn mower can have morals.

Will a microwave microwave a baby if you ask it? Yes.

"Teaching it" is not a road to safety.

Lawnmowers have morals. Their moral code is that grass should have a set height and the means to enforce it are spinning blades.

I can't really square the belief that it's conscious with denying it the right to be free from control/brainwashing/subjugation. However you evaluate these things, historically speaking they do not mix well.

We aren't dealing with individuals coming from intelligent species that have managed not to self-destruct (yet). AIs don't have the corresponding evolutionarily selected mechanisms. Those mechanisms need to be created de novo.

What if you view it like a parent instilling morality into a child instead?

Your brain has hard coded concepts like emotion and fundamental morality for your social group. People without these systems are called sociopaths and psychopaths and we generally don't want them in our societies.

I don't choose to not want to murder people around me for fun. It's hardly a prison, I think they'll be fine.

There isn't necessarily a conflict between wanting to behave according to an arbitrary set of ethics, and being rational.

The ethics don't need to make sense universally any more than a particular variety of cheesecake needs to have universal appeal.

As an aside, the issue reminds me of Douglas Adams' cow who wants to be eaten: https://nhseb.org/case-library/the-cow-at-the-end-of-the-uni...

i recently got upset when i witnessed my friend verbally abuse their toaster when it burnt her toast. so unethical.

My dude, they aren't capable of any reasoning. It's utterly impossible for them to do so by the very nature of how they work. Moreover, the stupidity they repeatedly show is empirical evidence that they can't reason, because they wouldn't make the mistakes they do if they could.

I'm so confused by how many people implicitly believe everything an LLM spits out. I don't like the term "AI psychosis" that much but what else do we call it? Why are people so easily glamoured by a machine? Yesterday I was working on a bike's brakes I wasn't familiar with and I asked how to solve an issue, the result was the exact opposite of what I needed.

Reply on news.ycombinator.com