[myrmidon]

Any form of AI unconcerned about its own continued survival would be just be selected against.

Evolutionary principles/selection pressure applies just the same to artificial life, and it seems pretty reasonable to assume that drive/selfpreservation would at least be somewhat comparable.

[throwaway77770]

That assumes that AI needs to be like life, though.

Consider computers: there's no selection pressure for an ordinary computer to be self-reproducing, or to shock you when you reach for the off button, because it's just a tool. An AI could also be just a tool that you fire up, get its answer, and then shut down.

It's true that if some mutation were to create an AI with a survival instinct, and that AI were to get loose, then it would "win" (unless people used tool-AIs to defeat it). But that's not quite the same as saying that AIs would, by default, converge to having a drive for self preservation.

[myrmidon]

Humans can also be just a tool, and have been successfully used as such in the past and present.

But I don't think any slave owner would sleep easy, knowing that their slaves have more access to knowledge/education than they themselves.

Sure, you could isolate all current and future AIs and wipe their state regularly-- but such a setup is always gonna get outcompeted by a comparable instance that does sacrifice safety for better performance/context/online learning. The incentives are clear, and I don't see sufficient pushback until that pandoras box is opened and we find out the hard way.

Thus human-like drives seem reasonable to assume for future human-rivaling AI.

[bigbadfeline]

> Any form of AI unconcerned about its own continued survival would be just be selected against. > Evolutionary principles/selection pressure applies

If people allow "evolution" to do the selection instead of them, they deserve everything that befalls them.

[myrmidon]

If we had human level cognitive capabilities in a box (I'm assuming we will get there in some way this century), are you confident that such a construct will be kept sufficiently isolated and locked down?

I honestly think that this is extremely overoptimistic, just looking at how we currently experiment with and handle LLMs; admittedly the "danger" is much lower for now because LLMs are not capable of online learning and have very limited and accessible memory/state, but the "handling" is completely haphazard right now (people hooking up LLMs with various interfaces/web access, trying to turn them into romantic partners, etc.)

The people opening such a pandoras box might also be far from the only ones suffering the consequences , making it unfair to blame everyone.

[bigbadfeline]

> If we had human level cognitive capabilities in a box - are you confident that such a construct will be kept sufficiently isolated and locked down?

Yes, I think this is possible and not quite hard technically.

> I'm assuming we will get there in some way this century

Indeed, there isn't much time to decide what to do about the problems it might cause.

> just looking at how we currently experiment with and handle LLMs

That's my point, how we handle LLMs isn't a good model for AGI.

> The people opening such a pandoras box might also be far from the only ones suffering the consequences

This is a real problem but it's a political one and it isn't limited to just AI. Again, if can't fix ourselves there will be no future - with AGI or without.