Re:Data Compression Explained
by Bnjoroge on Saturday June 20, 2026 @12:53PM
(#48610751)
I wonder what if anything has changed ever since this article. Is llm-based compression more mainstream?
[ Parent
| on HN ]
Fabrice Bellard did something with neural nets and a transformer model [1] that was very successful.
I suspect that LLMs wouldn't be ideal to use as compressors, because they are large, consume a lot of resources, and are constantly changing. You need the model to produce exactly the same output at encoding and decoding time, or else you get gibberish.