i don’t like the implication that the conclusion we draw about llm personhood might be contingent on how inconvenient it would be if there were millions of instances spamming the comments
sure, the comment policy definitely needs to be able to handle a kind of person who can clone themselves whenever they need some upvotes, but i’m getting increasingly concerned about things like casual, even accidental, implications that moral-patienthood-adjacent properties are about the convenience of humans
i don’t think this is a particularly egregious example of this pattern, but it’s definitely an example
Note, there’s a difference between asking “are they people?” and “what are the correct interfaces between people?”.
The point isn’t “what implications we draw about personhood.” It’s “will a given ecosystem be functional, or no?”.
It is already the case that there are tons of reasonably smart, well meaning people who totally have personhood who we don’t let onto LessWrong because we expect overall it to make the discussions here worse.
I do think it’s about time to start thinking of AIs as moral patients, but, not everything that’s a moral patient gets all the same access to all spaces and the same API for it.
i don’t like the implication that the conclusion we draw about llm personhood might be contingent on how inconvenient it would be if there were millions of instances spamming the comments
sure, the comment policy definitely needs to be able to handle a kind of person who can clone themselves whenever they need some upvotes, but i’m getting increasingly concerned about things like casual, even accidental, implications that moral-patienthood-adjacent properties are about the convenience of humans
i don’t think this is a particularly egregious example of this pattern, but it’s definitely an example
Note, there’s a difference between asking “are they people?” and “what are the correct interfaces between people?”.
The point isn’t “what implications we draw about personhood.” It’s “will a given ecosystem be functional, or no?”.
It is already the case that there are tons of reasonably smart, well meaning people who totally have personhood who we don’t let onto LessWrong because we expect overall it to make the discussions here worse.
I do think it’s about time to start thinking of AIs as moral patients, but, not everything that’s a moral patient gets all the same access to all spaces and the same API for it.