Re:GPT-6 Astra covertly underperforms on safety research
by root_axis on Thursday November 05, 2026 @07:48PM
(#50386736)
> Assuming that "tools" are the result of imperative programming, LLMs are not "tools"
I don't see any reason to assume that.
> if one treats it as a form of alignment, then LLMs certainly do have something resembling a moral(-like) framework
This is just stretching metaphor to fulfill a pedantic definition. LLMs are tools, they're no more moral a csam classifier.
Re:GPT-6 Astra covertly underperforms on safety research
by pizza234 on Tuesday November 10, 2026 @03:03PM
(#50445535)
> I don't see any reason to assume that.
In order to see that, you need to understand the concept of neural networks as opposed to imperative programming; you can start from here: https://en.wikipedia.org/wiki/Neural_network_(machine_learni....
And anthropomorphism is actually a precise way to describe the behavior (mind, not the structure) of LLMs.
As a matter of fact, LLMs are not configured, they're "trained".
"Moralization" is quit vague in this context, but if one treats it as a form of alignment, then LLMs certainly do have something resembling a moral(-like) framework, which is actually an important topic in modern AI research.
Antropomorphism also applies here: morals not in the human structural sense, but, as a set of norms etc., then behaviorally similar.