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.
Roko’s basilisk? That’s not in the story, but one of the ‘great’ outputs from the forum that the author created.
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.