Jev introduces a new shape of LLM - System One, aka Decision Models
TypeSafe AI introduces Jev, a new LLM category that returns numeric decisions for yes/no questions, ratings, and confidence scores.
TypeSafe AI introduced Jev, a new category of LLM called System One models, which returns floating point numbers for categories, yes/no questions, ratings, and confidence scores.
- Jev is a new category of LLM called System One models
- Jev returns floating point numbers for yes/no, ratings, and confidence scores
- Jev is fast and cheap
Last week TypeSafe AI unveiled Jev , their first example of a new category of model that they are calling "System One models" (I'm with Maggie Appleton, I think "decision models" is a better name for these). Jev is an interesting variant on the usual LLM format: it still accepts text inputs, but instead of text output it returns floating point numbers corresponding to categories, yes/no questions, ratings, and associated confidence scores. TypeSafe describe Jev like this: Think of Jev as a frontier-intelligence function call: unstructured state in, typed probabilistic decisions out. It's also very fast, and really cheap . Regular LLMs are priced in terms of input and output tokens, with…
This source does not provide full text. Read it at simonwillison.net.