Thanks Ben. I actually suggested both in my original comment: both
(a) that there is market incentive for the companies to do this themselves so ?did AI Safety movement really move the dial on this?,
and also
(b) that I’m skeptical of the value of interpretability research (based only on not having seen anything impressive come from it, but I’m very ignorant of the field)
Thanks Ben. I actually suggested both in my original comment: both
(a) that there is market incentive for the companies to do this themselves so ?did AI Safety movement really move the dial on this?,
and also
(b) that I’m skeptical of the value of interpretability research (based only on not having seen anything impressive come from it, but I’m very ignorant of the field)