@tante I've tested a number of models ability to summarize works well known to me. Some perform better than others. Many times it's a PICNIC issue with the guidance they're issued if you're experiencing difficulties. You have to direct your expected output format, focus & style when it comes to wholly new material. If it's classic material often you get a collage of other peoples summaries. Which occasionally can make for interesting metanalysis insights by connecting dots between summarizers.
https://mastodon.social/@Beggarmidas/113510857222195036
No replies.
────
────