This article explains key concepts that come up in the context of AI alignment.
if we can't still clearly define consciousness and values how then can we align AI to this values?
this defination of alignment seems more factual for me "making AI systems try to do what their creators intend them to do"
Saw this on the archives. Thought I’d share a response: https://substack.com/@postalignment/note/p-181670306?utm_source=notes-share-action&r=6xa8hc
if we can't still clearly define consciousness and values how then can we align AI to this values?
this defination of alignment seems more factual for me "making AI systems try to do what their creators intend them to do"
Saw this on the archives. Thought I’d share a response: https://substack.com/@postalignment/note/p-181670306?utm_source=notes-share-action&r=6xa8hc