Logical direction, but the real killer feature would be for an LLM to read every page you bookmark and not just categorize it once for you, but add it to a queryable knowledge-base that you can reference at any point in future conversations.
I tried to use it, and it just does not work very well, I don't it's because implementation is bad, it's just RAG (retrieval based generation) does not work well outside of some simple use cases.
But for a use case where you want to retrieve something from browsing history you would mainly use a short search query, just few words. in this case embeddings are too ambiguous and relevance of retrieved content is not great.
You’re right in saying there’s not enough semantic meaning in the text of the query. The domain of queries and the domain of documents are very different. That’s why a real retrieval system will train the query encoder and doc encoder to be closer in their embedding space using click data. This is what Google is doing.
https://pytorch.org/docs/stable/generated/torch.nn.TripletMa...
Triplet loss takes an anchor, positive, and negative. In this case the anchor is your query, the positive is a similar doc, and the negative is a dissimilar doc. When you train, backpropagate the loss to both the doc and the query encoder.
nowadays I expect browsers to incorporate small LLMs like Mistral out of the box
also: https://bugs.chromium.org/p/chromium/issues/detail?id=297648
> Shouldn't this be left to users to decide whether they want a feature or not.
Yes, those were good times. Nowadays, it's anathema to software vendors, and increasingly even to open source devs.