There was this post a few days ago https://news.ycombinator.com/item?id=49797323

It had this to say in the linked post:

  This led to the natural question: can gzip do language modeling? (...). Here’s some real, unedited output after priming it on tiny Shakespeare:

  gzipt --corpus data/tinyshakespeare.txt --prompt $'MENENIUS:\n' --length 200

  MENENIUS:
  'Though all at once canq

  MARCIUS:
  Pray now, nocamest thou to a morsel.

  LARTIUS:
  Hence, and
  I' the end admire, where G
  again; and after it ag .

The other is what thinking does, it tries to predict the missing sequence of tokens from a high entropy source, the prompt, in order to increase the likelihood of correctly decompressing the desired results from its weights.