potentially dumb question: if you trained GPT-4 on all published scientific papers, would it be able to identify which outcomes or findings were repeated across the corpus? yes, right?

/ted | exploring the onchain frontier | surfing @ venice, ca | eating @ gjusta / gjelina

One thing you could do is generate embeddings for all of them and then search based on that.

would tell you which papers discuss the same subject and where, but not necessarily similar findings AFAIK.

You could get a very good idea of this through embeddings. Could find themes and directional results