Sad day.

you are viewing a single comment's thread
view the rest of the comments
[–] 2 points 1 week ago* (last edited 1 week ago)

No, he's got his own ideas about it. For what it's worth he thought Roko's Basilisk and the whole time war-esque torture cube of it all was a silly extreme of his completely original thought that AI might kill us because it has different values.

Last I paid attention he was mostly interested in methods to make sure that doesn't happen by making sure any AI shares those values at least in part.

  • source
  • parent