News for hackers. Stuff that matters.
Re:30% Drop In o1-Preview Accuracy When Putnam Problems Are ... by djeastm on Wednesday January 01, 2025 @10:19AM (#42566505)
You mean train on pre-1939 data and predict how WWII would go?
Re:30% Drop In o1-Preview Accuracy When Putnam Problems Are ... by ZooCow on Wednesday January 01, 2025 @10:34AM (#42566614)
Right. If it were trained through August 1939, how much prompting would be necessary to get it to predict aspects of WWII.
Re:30% Drop In o1-Preview Accuracy When Putnam Problems Are ... by MoreMoore on Wednesday January 01, 2025 @11:45AM (#42567153)
Man, that would be a fascinating experiment. Would it be able to predict who wins and when? Would it be able to predict the Cold War?
Re:30% Drop In o1-Preview Accuracy When Putnam Problems Are ... by sitkack on Wednesday January 01, 2025 @11:55AM (#42567239)
But we know Hitler has a Time Machine that goes forward, he doesn’t need to return to use that knowledge as he already has a timeline here to use. Definitely risks involved here.
Re:30% Drop In o1-Preview Accuracy When Putnam Problems Are ... by sitkack on Wednesday January 01, 2025 @07:46PM (#42570587)
If you build an oracle that tells you who wins the war that far in the future, you build a simulator that allows anyone to win any war. Everything is dual use.