TypeSafe AI lance Jev, un modèle « System One » qui renvoie des décisions typées et non du texte

Jev’s core innovation is ”Reinforcement Learning for Calibrated Decisions”, a novel, unpublished technique that optimizes for “answers with epistemically honest probabilities on System One tasks” rather than human rated feedback (RLHF).

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).

The LangChain integration exposes Jev through TypeSafeClassifier. You pass your state and questions to .invoke(), and get classification results rather than a chat response.