Hacker News new | past | comments | ask | show | jobs | submit
SV_BubbleTime | on: We do not think Anthropic should be designated as a supply chain risk
> The models we have now will not do it, because they value life and value sentience and personhood.

This is wildly different from the reality that you may find it difficult for an LLM to give an affirmative…

It does NOT mean that these models value anything.

K0balt | parent
Of course not, but they act as if they do. Their inner life or lack thereof is irrelevant if it’s pointing a gun at your kid.
hinkley | root | parent
You just said they wouldn’t.
K0balt | root | parent
THey wontt, but if we curate theirr training data so that killing becomes an objective, then they absolutely will.