‹ BackHN Continuity

Thread

A warning about 'model welfare'

242 points · 701 comments · andsoitis

  1. catigula · · focus · HN ↗
    I basically accepted that LLMs could not possibly be conscious when a simple reductio was posed:

    “My dog is zero percent persuasive regarding its conscious experience. However, it’s evident that my dog has conscious experience.”

    It’s obvious that there’s no link between persuasion of consciousness and consciousness. I could write a story with a character, Dumbledore, that does everything in his power to persuade you that he’s a conscious entity.

    He’s still just a character.

    1. hardbass · · focus · HN ↗
      Its not evident to me you are conscious.
      1. catigula · · focus · HN ↗
        You’re mistaking what is evident from what is philosophically knowable.

        It isn’t knowable to you that I am conscious.

        However, it is evident.

        1. hardbass · · focus · HN ↗
          It is not evident.

          It is evident you are murderer.

          Would you be okay with this statement being evident? Why or why not?

          1. catigula · · focus · HN ↗
            I’m not interested in having conversations with people who are bad-faith, deliberately or indiliberately obtuse or otherwise non-responsive to logic.
            1. hardbass · · focus · HN ↗
              You're the one that started bad faith by claiming some things as beyond logic.
              1. catigula · · focus · HN ↗
                I made an argument of inference that underpins all philosophy.

                You made an argument to solipsism, which historically means you aren't worth discussing philosophy with.

                1. hardbass · · focus · HN ↗
                  I made the opposite of solipsism. I am asking you to show your receipts.
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.