Comment on Algorithm based on LLMs doubles lossless data compression rates
skip0110@lemm.ee 2 weeks ago
This is not new knowledge and predates the current LLM fad.
See the Hutter prize which has had “machine learning” based compressors leading the ranking for some time: prize.hutter1.net
It’s important to note when applied to compressors, the model does produce a code (aka encoding) that exactly reproduces the input. But on a different input the same model is unlikely to produce an impressive compression.