This is the way.
But now we also need new tools and techniques to audit intent. The last thing we want is models turning on us ‘for our own good’.
But now we also need new tools and techniques to audit intent. The last thing we want is models turning on us ‘for our own good’.
most important guard against that is to STOP explicitly training for paternalistic behaviors (which is ... basically half of what 'AI safety' is about in practice-- overriding the user 'for their own good').