A New Type of LLM on the Block: Decision-Making Models Typesafe.ai released Jev, a new type of model it calls a "system one model" that accepts text input but outputs only floating-point numbers answering user-specified yes/no questions, choice lists and scoring requests, according to a company blog post and a summary by Simon Willison. Jev cannot write a single sentence but is described as extremely fast, ultra-cheap and focused solely on classification and decision-making, and the approach has already spawned community-built variants including Kev and Nimble, with Nimble added as a supported model in Ollama. Large language models LLMs output language, but they are commonly tasked with making a decision or classification of some kind instead of writing an essay or chat reply. An LLM will be provided with input, and asked to classify that content in some way: with a rating, yes/no answer, a best-fit categorization, and so forth. A recent new type of model by the name of Jev https://typesafe.ai/blog/introducing-system-one-models-and-jev was released only weeks ago and it is extremely fast, ultra-cheap, and laser-focused on that decision-making role. It can’t write even a single sentence, but it can classify and categorize very, very quickly. Jev works like this: it still accepts text input, but it outputs only floating-point numbers. Those numbers are the “answers” to user-specified yes/no type questions, lists of choices, and scoring-type requests. Simon Willison provides a concise summary of what Jev does https://simonwillison.net/2026/Sep/21/jev/ , and what makes this new category of model so interesting. To say that the idea has caught on would be a wild understatement. Folks are making their own decision-type models and experiments in a flurry. Kev https://github.com/jaredpalmer/kev and Nimble https://github.com/bespokelabsai/nimble are two examples Nimble was added as a supported model in Ollama https://ollama.com/library/nimble just recently, and is small enough to run locally with relative ease. If this type of local AI model was the missing link you needed to get an idea working, don’t keep it to yourself Tell us all about it on the tips line https://hackaday.com/submit-a-tip/ .