TypeSafe AI released a model last week called Jev. It does something narrower than the large language models most developers use today – it makes decisions without generating much text.
You give Jev information about a situation and specify the possible answers. It returns its choice along with probabilities and confidence scores.
(Note: you can also check out “Openjev” here)
TypeSafe calls Jev its first “System One Model,” borrowing the name from the distinction between fast, intuitive judgment and slower reasoning. The company says Jev uses a new architecture, a parallel sampler and a training method called Reinforcement Learning for Calibrated Decisions, or RLCD.
The easiest way to understand the idea is to look at work developers already give to LLMs.
Suppose a customer writes that they were charged twice and plan to dispute the charge with their bank. A support system might send the message to an LLM and ask whether it belongs in billing, fraud, technical support or sales.
