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.
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.