Post #2547550
2026-05-04 16:03 UTC
@ingorohlfing@mastodon.social @philipncohen@mastodon.social Wasn't this perhaps an "easy" target? These associations have been tested many times, so I guess someone working on these questions could have predicted these results, too?
Replies (1)
-
@ingorohlfing@mastodon.social 2026-05-04 17:47
@druedin@sciences.social @philipncohen@mastodon.social Interesting point. It is probably correct because, as the post notes, the model likely has been trained on similar research. Would then be interesting to let an LLM produce results for a more or less completely new phenomenon that is not part of the training data. The challenge then may be that no one has a good benchmark for evaluating the LLMs results, except for plausibility, which maybe good enough as a starting point.