Can gzip be a language model?(nathan.rs)
384 points by networked | 149 comments
A blog post by Nathan Barry exploring whether gzip compression can be used as a language model to generate text, with an interactive beam search demo.
3 stories on the front page, newest first. Scroll down to watch the site change over time.
384 points by networked | 149 comments
A blog post by Nathan Barry exploring whether gzip compression can be used as a language model to generate text, with an interactive beam search demo.
435 points by nathan-barry | 102 comments
Blog post arguing BERT-style masked language modeling is a single step of discrete text diffusion, with experiments fine-tuning RoBERTa as a diffusion text generator.