Hacker News new | ask | show | jobs
by eurekin 8 hours ago
I remember seeing this popping up in discussions the first time, but never noticed any resolution (other than to train both sides). Has SOTA advanced?
1 comments

No, it's just that no one really cares. It doesn't seem to cause identifiable faults in model reasoning in the real world.

It could be fun to try to make the model pre-learn a "reversal prior" that would cause a greater degree of generalization there, but I'm yet to see a published result like this. Let alone one that would demonstrate such a prior to be useful.