[HN Gopher] The super effectiveness of Pokemon embeddings using ...
       ___________________________________________________________________
        
       The super effectiveness of Pokemon embeddings using only raw JSON
       and images
        
       Author : minimaxir
       Score  : 91 points
       Date   : 2024-06-29 17:03 UTC (1 days ago)
        
 (HTM) web link (minimaxir.com)
 (TXT) w3m dump (minimaxir.com)
        
       | axpy906 wrote:
       | Nice article. I remember the original work. Can you elaborate on
       | this one Max? > Even if the generative AI industry crashes
        
         | pqdbr wrote:
         | I think the author is implying that even if you can't extract
         | real world value from generative AI, the current AI hype has
         | evolved embeddings to a point they can provide real world value
         | to a lot of projects (like the semantic search demonstrated in
         | the article, where no generative AI was used).
        
         | minimaxir wrote:
         | It's a note that embeddings R&D is orthogonal to whatever
         | happens with generative AI even though both involve LLMs.
         | 
         | I'm not saying that generative AI _will_ crash but if it 's
         | indeed at the top of the S-curve there could be issues,
         | notwithstanding the cost and legal issues that are only
         | increasing.
        
           | qeternity wrote:
           | While there is no real definition of LLM I'm not sure I would
           | say both involve LLMs. There is a trend towards using the
           | hidden state of an LLM as an embedding but this is relatively
           | recent, and overkill for most use-cases. Plenty of embedding
           | models are not large, and it's fairly trivial to train a
           | small domain-specific embedding model that has incredible
           | utility.
        
       | vasco wrote:
       | > man + women - king = queen
       | 
       | Useless correction, it's king - man, not man - king.
        
         | 01HNNWZ0MV43FF wrote:
         | It's also woman not women
        
           | PaulHoule wrote:
           | Also you hear that example over and over again because you
           | can't get other ones to work reliably with Word2Vec; you'd
           | have thought you could train a good classifier for color
           | words or nouns or something like that if it worked but
           | actually you can't.
           | 
           | Because it could not tell the difference between word senses
           | I think Word2Vec introduced as many false positives as true
           | positive, BERT was the revolution we needed.
           | 
           | I use similar embedding models for classification and it is
           | great to see improvements in this space.
        
             | simonw wrote:
             | The other example that worked for me with Word2Vec was
             | Germany + Paris - France = Berlin: https://simonwillison.ne
             | t/2023/Oct/23/embeddings/#exploring-...
        
       | jpz wrote:
       | Great article - thanks.
        
       | flipflopclop wrote:
       | Great post, really enjoyed the flow of narrative and quality deep
       | technical details
        
       | jszymborski wrote:
       | I would be interested in how this might work with just looking
       | for common words between the text fields of the JSON file
       | weighted by e.g. TF-IDF or BM25.
       | 
       | I wonder if you might get similar results. Also would be
       | interested in the comperative computation resources it takes.
       | Encoding takes a lot of resources, but I imagine look-up would be
       | a lot less resource intensive (i.e.: time and/or memory).
        
       | bc569a80a344f9c wrote:
       | Very nice! This took me about 30 minutes to re-implement for
       | Magic: The Gathering cards (with data from mtgjson.com), and then
       | about 40 minutes or so to create the embeddings. It does rather
       | well at finding similar cards for when you want more than a 4-of,
       | or of course for Commander. That's quite useful for weirder
       | effects where one doesn't have the common options memorized!
        
         | minimaxir wrote:
         | I was thinking about redoing this with Magic cards too (I have
         | quite a lot of code for that preprocessing that data already)
         | so it's good to know it works there too! :)
        
       ___________________________________________________________________
       (page generated 2024-06-30 23:00 UTC)