RSS

paulfchristiano(Paul Christiano)

Karma: 12,266

A naive al­ign­ment strat­egy and op­ti­mism about generalization

paulfchristiano10 Jun 2021 0:10 UTC
41 points
3 comments3 min readLW link
(ai-alignment.com)

Teach­ing ML to an­swer ques­tions hon­estly in­stead of pre­dict­ing hu­man answers

paulfchristiano28 May 2021 17:30 UTC
35 points
13 comments16 min readLW link
(ai-alignment.com)

De­cou­pling de­liber­a­tion from competition

paulfchristiano25 May 2021 18:50 UTC
56 points
14 comments9 min readLW link
(ai-alignment.com)