https://bellard.org/ts_sms/

ts_sms: Short Message Compression using Large Language Models

  * Compression example:

    ./ts_sms c "Lossless compression reduces bits by identifying and eliminating statistical redundancy. No information is lost in lossless compression."
    myulgYao Shao Pu Ju Shao 


  * Decompression example:

    ./ts_sms d myulgYao Shao Pu Ju Shao 
    Lossless compression reduces bits by identifying and eliminating statistical redundancy. No information is lost in lossless compression.

  * Comparison with brotli which embeds a dictionary to optimize the
    compression of small messages:

    ./ts_sms c "Lossless compression reduces bits by identifying and eliminating statistical redundancy. No information is lost in lossless compression." -F base64
    9mY1wFk1VUFdUjvxC0wQfA==

    echo -n "Lossless compression reduces bits by identifying and eliminating statistical redundancy. No information is lost in lossless compression." | brotli | base64
    H4cAYEVPlqqQnpIJ3RBsRngCqhywb5ksOXr9JgfAu42tLx5BpYJuPXKKY9U0Rn1dxoVKWgFFY8Bz
    0zceYpcspm/ft+EqAA==

Download

  * Linux version: ts_sms-2024-12-26.tar.gz.
  * Windows version: ts_sms-2024-12-26-win64.zip.

Technical information

ts_sms works similarly to ts_zip. It uses a specific padding system
compatible with arithmetic coding so that the message length does not
need to be explicitly encoded.

---------------------------------------------------------------------
Fabrice Bellard - https://bellard.org/