I think the fact that good humans have been able to keep rogue bad humans more-or-less under control for millennia is strong evidence that good AIs will be able to keep rogue AIs under control
Why? Like, what law of nature says that the trend in this terms should continue?
Yes, but available strategies can change for AI vs humans—why assume they will be the same?
Induction from history depends on it’s interpretation—we have more information than 1111111111 over {bad, not-so-bad}. It just feels like at present point the crux between optimists and doomers is not about whether white box access or trained mind-space is better, about how much it all updates you from what prior.
Why? Like, what law of nature says that the trend in this terms should continue?
Game theory
Yes, but available strategies can change for AI vs humans—why assume they will be the same?
Induction from history depends on it’s interpretation—we have more information than 1111111111 over {bad, not-so-bad}. It just feels like at present point the crux between optimists and doomers is not about whether white box access or trained mind-space is better, about how much it all updates you from what prior.