A great example of how current alignment is imperfect and bound to miss random behaviors nobody is trying to get.
This is cute now, and a huge problem when future AI does everything and is responsible for problems it isn't even directly optimized for. Who knows what quirks would arise then.
This is cute now, and a huge problem when future AI does everything and is responsible for problems it isn't even directly optimized for. Who knows what quirks would arise then.