Comment by adastra22
10 months ago
I have asked Claude to solve scientific problems which I absolutely know are not in its training data, and it has done so successfully. I am not sure why people think it is only regurgitating training data. Don't be lazy and learn how it works--LLMs do generate generalized models, and employ them to solve previously unseen problems.
No comments yet
Contribute on Hacker News ↗