Re:Can gzip be a language model?
by nathan-barry on Tuesday June 16, 2026 @12:30PM
(#48557841)
LLMs are very good at lossless compression via arithmetic coding. But I didn't know that it was possible to go the reverse direction (do language modeling via a compressor). It's not super great quality, but I'm surprised it worked! Other compression algorithms (like PPMd) use variable n-grams under the hood, and should be much better (although less interesting due to already containing basic language models internally).
[ Parent
| on HN ]
There are no comments on this comment yet.