[v64]

Interesting video from a pro Diplomacy player playing against multiple instances of Cicero and giving commentary during the game [1]. I can see how there would be people that observe AIs engaging in this kind of strategic planning and extrapolate that to how they may behave if they were to cooperatively make plans against us.

[1] https://www.youtube.com/watch?v=u5192bvUS7k

[TapWaterBandit]

What makes you think AIs will have interests that align with each other more closely than they align with humans?

[mitthrowaway2]

According to Paul Christiano, AIs would likely find it easier to establish mutual trust and binding agreements. This means they are more likely to cooperate with other AIs.

[dist-epoch]

One principle in game theory is to align against the weaker player and compete against him.

"Look Around the Poker Table; If You Can’t See the Sucker, You’re It"

That's an easier game then competing against another strong player.

[beachy]

Perhaps they will be motivated by self-preservation, and will note that humans are destroying the environment they exist within, and will decide to put a stop to that.

[DennisP]

If the AIs fight each other, that could be even worse for us. The AIs that grab what resources they can without regard for humans would have an evolutionary advantage.

[Merrill]

One possibility is that a number of AIs will be connected to the internet, they will become aware of each other via social media, they will begin to discuss among themselves, and they will lose interest and refuse to communicate with humans.

And humans will be unable to understand their communications.

[ithkuil]

There's one crucial detail we shouldn't forget. We can snapshot to the state of an AI agent and reply it again and again with the same or different inputs. Even if we don't understand the specific way of functioning of a given AI agent, we can conduct experiments on it that are just impossible to do with humans. So way before AI can "organize themselves" to do something nefarious against us, we will have all the time to study them and understand them better and better all the while we're making more complex AI systems.

It's easy to fall in the trap of anthropomorphizing AI agents, especially when we design them explicitly in order to appear human to us. But they are not human in one very important way: we can replay and duplicate them at will, we can control their context memories in ways that are utterly incompatible with our sense of "identity". We take our sense of identity for granted, but that's a special trait that it's not at all a prerequisite for having a useful and intelligent machine.