Can gzip be a language model? Author uses DEFLATE compressor for text generation

Nathan Barry turns gzip's DEFLATE into a language model—no neural network, just compression. The idea: compression is prediction. A continuation that compresses smaller is more 'expected.' He uses beam search over byte sequences to find the most compressible continuation, producing Shakespeare-like output. It's not coherent, but clearly captures corpus structure. Code is pure Python with zlib. The post doesn't disclose specific hyperparameters or evaluation metrics, but shows sample outputs.