Why not just run that experiment?
Thank you for doing this. Would you mind if this is added to the Misalignment Database?
" For the most part, Roko's posts not only fail to engage with any scientific literature on the subject, but employ an extremely naive and ultimately misleading model that does not hold up to empirical and theoretical scrutiny. "
Can be applied generally.
Been doing this. Reading less. Writing a LOT less. Memory has improved a lot.
The alienation is something I felt for a bit, until I started working on my project and working with folk, talking to folk, etc. Also, been very pleasantly surprised how receptive non AI/non-tech folk are when talking to them about AI risk, as long as it's framed in a down to earth, relatable manner, introduced organically, etc.
I disagree with this now.
I think a lot of people think Sydney/Bing Chat is GPT 4
Human can manipulate animals and make them do what they want. So could AI
Any reason not to just run the experiment?