This doesn’t seem like it’d do much unless you ensured that there were training examples during RLAIF which you’d expect to cause that kind of behavior enough of the time that there’d be something to update against. (Which doesn’t seem like it’d be that hard, though I think separately that approach seems kind of doomed—it’s falling into a brittle whack-a-mole regime.)
Indeed, we should get everyone to make predictions about whether or not this change would be sufficient, and if it isn’t, what changes would be suffficient. My prediction would be that this change would not be sufficient but that it would help somewhat.
This doesn’t seem like it’d do much unless you ensured that there were training examples during RLAIF which you’d expect to cause that kind of behavior enough of the time that there’d be something to update against. (Which doesn’t seem like it’d be that hard, though I think separately that approach seems kind of doomed—it’s falling into a brittle whack-a-mole regime.)
Indeed, we should get everyone to make predictions about whether or not this change would be sufficient, and if it isn’t, what changes would be suffficient. My prediction would be that this change would not be sufficient but that it would help somewhat.