Can gzip be a language model?

Automated excerpt

So:A continuation that gzip “expected”, because it echoes text already in its window, compresses to almost nothing. That gives us a score. At each step, the current context is:corpus window + recent tail of (prompt + generated bytes)Then gzipt tries possible next bytes. Show gzip the corpus window plus the recent tail of the prompt/generated text. Search.

Selected automatically from source text; not independently written or fact-checked. Read the original for full context.