This is just to state that I’m very far from buying any of the arguments as-written. They seem like dumb arguments. But then, you say you’re not trying to explain your arguments here.
Sure. It seems to me like humans are in a bad spot, with a significant chance of not surviving the next hundred years, depending mainly on whether very weak alignment methods are enough to land us in anything like a corrigibility basin.
This is just to state that I’m very far from buying any of the arguments as-written. They seem like dumb arguments. But then, you say you’re not trying to explain your arguments here.
Would you like to register a counter prediction?
Sure. It seems to me like humans are in a bad spot, with a significant chance of not surviving the next hundred years, depending mainly on whether very weak alignment methods are enough to land us in anything like a corrigibility basin.