[HN Gopher] Experimenting with LLMs to Research, Reflect, and Plan
       ___________________________________________________________________
        
       Experimenting with LLMs to Research, Reflect, and Plan
        
       Author : gk1
       Score  : 64 points
       Date   : 2023-04-12 18:53 UTC (4 hours ago)
        
 (HTM) web link (eugeneyan.com)
 (TXT) w3m dump (eugeneyan.com)
        
       | tudorw wrote:
       | I think something akin to a mashup between Engleberts
       | augmentation, Nelson's Xanadu (r) and Bucky's tensegrity system
       | would make a great accompanying knowledge management system to
       | manage branching conversations with AI, after a while handling
       | the content generated becomes a task in itself. Visualising the
       | created data would be ace.
        
         | tudorw wrote:
         | 'Sparks of AGI' https://youtu.be/qbIk7-JPB2c
        
       | summarity wrote:
       | > One solution is to ensemble semantic search with keyword
       | search. BM25 is a solid baseline when we expect at least one
       | keyword to match. Nonetheless, it doesn't do as well on shorter
       | queries where there's no keyword overlap with the relevant
       | documents--in this case, averaged keyword embeddings may perform
       | better. By combining the best of keyword search and semantic
       | search, we can improve recall for various types of queries.
       | 
       | Oh hey I have a demo of that here: https://findsight.ai
       | 
       | For it I wrote a custom search engine, and KNN index
       | implementation, which ranks and merges results across three
       | stages (labels, full-text, embedding) effectively. To speed up
       | retrieval, OpenAI embeddings are stored instead as SuperBit
       | signatures. Rank merging turned out to be a really hard problem.
        
         | motoboi wrote:
         | Wait. What!?! This is amazing. Did you write about that?
        
       ___________________________________________________________________
       (page generated 2023-04-12 23:01 UTC)