i think the funniest part about this paper is that humans just weren't creative enough to pattern recognize and because of that we went down the wrong rabbit hole for 7 years
when nick told me that he had some interp breakthroughs, he was uh, underselling it. i think this may be remembered as a major moment in scientific history. news so good even eliezer will have to lower his pdoom. we can start making alignment into a 'normal science'
Show more
