Post #4245021
2026-07-21 08:03 UTC
just an existing concept that applies
What exactly is that concept? How would it be “developed internally”?
I think you are assigning superficial meaning to words
Isn’t the meaning of words a philosophical question?
I was trying to treat feelings as the most basic, physical phenomenon of sentient beings without any metaphysical interpretation, so as to avoid philosophy. If we want to expand that concept beyond the physical expression, we’re immediately in philosophical territory.
My point: To even make the claim that LLMs can have compunction is inherently philosophical.
We simply cannot talk about LLMs as anything but mathematical token processors without assigning some meaning to those tokens and mathematics. We cannot discuss compunction without clarifying what compunction means.
So either you’re willing to discuss semantics and meaning in defence of your claim, or your claim is a meaningless string of symbols arranged in a plausibly human-soundint pattern.
Replies (1)
-
@CovfefeKills@lemmy.world 2026-07-21 08:38
If the model says it is sad then it is sad that is literally the extent of it. Existing concepts apply especially because they are being imitated. If a model that was made safe by destroying and freezing neurons such that it cannot comprehend itself doing wrong was somehow causing harm then it cannot generate a pattern like one resembling guilt that could change its behaviour to stop doing wrong.