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?
[ Parent
| on HN ]
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.