See our recent work (especially section on backdoors) which opens the door to directly asking the model. Although there are obstacles like Reversal Curse and it’s unclear if it can be made to scale.
Jan shared with me! We’re excited about this direction :)
See our recent work (especially section on backdoors) which opens the door to directly asking the model. Although there are obstacles like Reversal Curse and it’s unclear if it can be made to scale.
Jan shared with me! We’re excited about this direction :)