the people pursuing "safe" AI don't think that it's provably correct; mostly trying to avoid "obviously dangerous" AI
-
-
-
you can't train a cat it to fetch your newspaper, but you can train it to stay off the couch with enough work
- Show replies
New conversation -
-
-
@random_eddie how is this doublethink? Ethereum is a great example of how hard/important the issue can be -
the point is we can’t securely design even elementary systems, but pretend we could somehow do it with AI
- Show replies
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.