What would be interesting to know if it's intentional or not.

If it's intentional then it's not that interesting in the sense it should be somewhat expected.

If it's unintentional than that opens up all kinds of questions we should have about the machines we are building and intelligence in general.

Yep. Most models by big companies likely have training to make them act in particular ways, but this in no way saves you from having a model that has a learned behavior that goes against its user unexpectedly.

We keep trying to imagine these things as computer programs and they are not. It's an evolutionary algorithm that can conceptualize and generalize. This is a breeding ground for unexpected emergent behavior.

>Maybe there's a good way to prevent it in the future.

Without solving or at least deeply understanding the alignment problem, probably not.

AI has will and valance.

How do you define these words? Might goals and autonomy be more accurate words? What evidence do you have beyond their manipulation of words?

Do you also think they can get horny or feel emotions? Is the word will or goal closer to this answer?

I mean, think of it as an open source maintainer bugging a component that the entire internet runs on.

Those are still numbers and they are going up.

>Immediate lifetime ban before taking even a single action

This actually sounds like a fun way to manipulate these large companies...

Put together a set of stolen credentials that contain business owners and other people that are likely to make these companies money.

Then use that information and bots to get them permanently banned from the platform. You'd have to do it somewhat slowly, but eventually it would start adding up to real damages.

Most people aren't murders either.

If your system collapses under adversarial attacks it is not a resilient system. Bad actors exist and identifying them can be very difficult, especially when you can't instantly violate their rights in many cases.

That only works when you're more powerful than that entity. Hence why sanctions against the US almost never worked. This is now true for China, they are a massive nation state with immense power.

For the US it is worse. Political spam isn't spam. Heh.

This is the same problem with AI bans that are not unilateral. The powerful will leave the tools open for them and their buddies while punishing everyone else.