ts_zip
Fewer than 5 people recommend it so far, so there's no written verdict. Here is what commenters said.
4recommend
0warn against
Feb 1, 2026first mention
Sep 22, 2026latest mention
Why people recommend it
“Once you understand the connection, things like ts_zip and hutter prize make a lot more sense.”
“still beats xz by a solid margin”
Show 2 more
“ts_zip compresses text at record efficiency”
“For something close to the state of the art see e.g. Fabrice Bellard (of course) ts_zip”
Caveats and dissent
No one in these comments warned against it.
Often compared with
Threads where it came up
- Can gzip be a language model? 2 mentions
- Compression Is Prediction 1 mention
- Newly discovered spider builds spring loaded snare to catch ants 1 mention
- Data Compression Explained 1 mention
- John Carmack on Fabrice Bellard 1 mention
- Show HN: I made a "programming language" looking for feedback 1 mention
Data: ts-zip.json. Quotes are verbatim; the verdict and theme labels are written by a model from these comments, and every clause links to its sources.
All comments 10
“Once you understand the connection, things like ts_zip and hutter prize make a lot more sense.”
“still beats xz by a solid margin”
“Fabrice Bellard published this in 2023”
“ts_zip compresses text at record efficiency”
“For something close to the state of the art see e.g. Fabrice Bellard (of course) ts_zip”
“Bellard has a very interesting project that is `ts_zip`, a compression algorithm powered by LLMs.”
“It beats stuff like .xz etc but of course is much slower.”
“fabrice bellard's ts_zip”
“https://bellard.org/ts_zip/”
“Bellard's tz_zip (https://bellard.org/ts_zip/) or nncp compress really well they are extremely slow”