Upgrade StorageWishful feature request : focus LLMs on annotation data
If the various plugins are a good measure there seems to be a lot of interest in getting the LLMs to do the work of reading papers, books, reports. The machines can do summaries of short texts, but they're hopeless with books, and they don't read with an argument in mind, so that is likely only to make us all stupider. What would be very useful, is automated analysis of our annotation data, ideally based on the colour hierarchy that is part of reading with Zotero. A tool that could show all highlights of a particular colour on a cluster of themes from the annotation data would be invaluable for research.