We know Jev . jevchat turns that into a chat model. At every step it asks Jev one question: Given the user's question and the reply written so far, which symbol comes next? The options are an alphabet plus an option to stop emitting. Jev returns a probability for each one, and the sampler draws the next symbol from that normalised distribution. Append, repeat, and stop when STOP is drawn. There are several alphabets (including truncated token lists) and sampling strategies available. The idea is for fun, the cost is somewhat impractical, and the results are hilarious. This was a Claude accelerated experiment. I described the sampling algorithms, strategies, and so on, and it implemented them. Setup Put your Jev key in .env next to pyproject.toml (git-ignored): JEV_API_KEY and TYPESAFE_API_KEY are also accepted. Values in .env win over exported ones, so editing the file is enough to switch keys. Use poetry run jevchat # interactive chat poetry run jevchat ask " do people need water?…