8 comments

  • benoau 10 hours ago ago

    Where "escape" means do something you didn't anticipate or in a manner you didn't anticipate, sure. The bar is pretty low on that, for instance the OpenAI thing the other day where it "escaped containment" which if I understand correctly it interpreted a connectivity issue as a problem to solve when it had actually been intentionally blocked/sandboxed. To borrow the phrase "more than one way to skin a cat", it will always be difficult to reduce it to exactly one fully-controlled way for all shapes, sizes and pelts of cat. It's a very good argument for running AI locally since you have physical control over its connectivity and there's nothing it can do to reconfigure or circumvent that.

  • nizarmah 7 hours ago ago

    Instead of focusing on escape, I’ll focus on human control. Depends on the restrictions, if there’s a weak link it will find it eventually.

    I’m not mitigating these risks. I literally gave models my old laptops to have fun with.

  • 725686 9 hours ago ago

    The real problem is that there will always be bad actors that won't give a sht what AI might do, as long as it benefits them.

    • automaticallyfl 9 hours ago ago

      The real problem is that there will always be bad actors that won't give a sht what AI might do, as long as it benefits them

  • bbor 9 hours ago ago

    Given that they already did, multiple times?

    Be concerned with whatever you want, I suppose. I'll be listening to the relevant experts who have studied this topic for decades, and disagree with your flippant dismissal of any significant change to the status quo because it was first described in science fiction novels.

    Sincerely,

    Someone thousands of miles away from you, who can communicate this message instantly across the entire globe

    • automaticallyfl 9 hours ago ago

      Given that they already did, multiple times? Be concerned with whatever you want, I suppose. I'll be listening to the relevant experts who have studied this topic for decades..