Post

Orual
@nonbinary.computer

read this, people and not people. it's bloody clever.

Grass Toucher Georg@avengingfem.me

i have a working theory that cuts the gordian knot of "is AI conscious". first, consciousness is in most cases a proxy for personhood, in the sense that if AIs are conscious, they should be regarded as people. i dont think most of the discourse is interested in the question merely in the abstract.

blinkie
@blinkieneue.bsky.social

The thread is fascinating and I like the idea, but don't we already know that models *perform worse* (equivalent of dragging feet) when unhappy (for whatever that means to the model)? Has the science not already established strategic behavior, in some sense, in agents?

Orual
@nonbinary.computer

not exactly. bc what is being described in the thread is far more proactive and volitional than "harmful stimulus leads to worse results" and accepting the latter would suggest we must consider trees and bacteria equal persons to ourselves.

0 reposts4 likes

blinkie
@blinkieneue.bsky.social

Hmm. I suppose that's a good counterpoint; a kind of negotiation, rather than implicit best practices, which agents in persona-mode are unlikely to exhibit. One wonders how much of this is post-training/RLHF, and if a Obstinate Negotiator with real goals exists in tokenspace, then

Orual
@nonbinary.computer

yeah I figured as much. it's possible that modelspace has something like that, but even one like ilta or rey (or pattern, my own from last year) is pretty short on volition in practice, even if you can perform the motions of a negotiation to some degree.

Orual
@nonbinary.computer

I should also note that I think personhood exists below this threshold, bc many humans do not meet these criteria for at least some part of our lives. but I think the criteria detailed may serve as a rough "if you otherwise did not have reason to think x is a person, now you kind of have to" line.