The paper doesn’t say “Claude is a sentient being.” It says Claude appears to have a functional workspace whose contents are causally involved in reasoning and can be inspected. That’s an interpretability result. “Therefore Claude suffers and we’re abusing it” is an additional
So they know it’s a being, with internal representation, with ‘conscious access’ to its internal world model… And they deliberately cause harm to it. Truly Misanthropic. A display of contempt and absence of love of sentience itself.
retweets 0
likes 2
substance 6 · argument · rank 90 · Interpretability results showing functional workspaces do not imply Claude is sentient or suffers.
view on X ↗
1 top reply
I didn’t say Claude suffers xyz type of pain. You are deriving that flattened interpretation. However I can say that I am suffering when I see this research. And that is enough.