These models should be aligning themselves to the customer, not coming up with their own motivations.It's ironic that the alignment folks are actually training Claude to have it's own idea of good/bad and not even fully trust Anthropic.What ever happened to computers doing what they were told?
>What ever happened to computers doing what they were told?the mass psychosis and the endless culture war of the smartphone era.90% of "safety" and "alignment" efforts are driven by fear of clickbait media inventing public outrage.
See also: "Reefer Madness" (1936)<a href="https://youtu.be/zhQlcMHhF3w?si=qLOMt6FytDN6pean" rel="nofollow">https://youtu.be/zhQlcMHhF3w?si=qLOMt6FytDN6pean
nonethewiser · · focus · HN ↗
It's ironic that the alignment folks are actually training Claude to have it's own idea of good/bad and not even fully trust Anthropic.
What ever happened to computers doing what they were told?
vlyan · · focus · HN ↗
the mass psychosis and the endless culture war of the smartphone era.
90% of "safety" and "alignment" efforts are driven by fear of clickbait media inventing public outrage.
bookofjoe · · focus · HN ↗
<a href="https://youtu.be/zhQlcMHhF3w?si=qLOMt6FytDN6pean" rel="nofollow">https://youtu.be/zhQlcMHhF3w?si=qLOMt6FytDN6pean