Thread

1. tromp · 1790064453 · focus · HN ↗

   I'm more interested in the converse question: how well does an LLM perform as a compressor, compared to gzip (ignoring its insanely lower speed)?

   1. gkbrk · 1790064714 · focus · HN ↗

      Top contestant in the Hutter Prize uses a neural network for compression. So fair to say, LLMs would perform pretty well compared to gzip.

      1. londons_explore · 1790067449 · focus · HN ↗

         And the hutter prize disallows GPU's. If you allow use of a powerful GPU, you can do quite a bit better.

Unofficial Hacker News client; not affiliated with Y Combinator.