Jev is not an LLM: a decision model that outputs only choice, score or boolean
An introduction to TypeSafe's System One model Jev: trained with RLCD, it outputs only three value types your code can branch on, is hundreds to thousands of times more efficient than an LLM, and you should use an LLM only when text needs to be written.
Heard about @typesafeai ‘s new System One model: JEV ?! NOT an LLM… 👀 An LLM is trained and used to produce language. Jev is trained (RLCD) and used to produce values your code can branch on. Outputs are one of three types ton specific in advance: - choice from a closed list - score against a rubric - boolean (yes/no) Because it’s finely tuned and purpose built to specifically NOT be able to produce text responses, the evaluations it does are INCREDIBLY in terms of both speed and cost - think hundreds or thousands of times more efficient. Use an LLM when you need something written. Use Jev when the answers already exist and you just need a fast judgment. This will be a total paradigm shift as harnesses begin to drive token spend down this way. Thoughts? Checked it out yet??