LATIDIA · Agentes

Jev presenta una nueva forma de LLM: System One, también conocida como Decision Models

La semana pasada, TypeSafe AI presentó Jev , su primer ejemplo de una nueva categoría de modelo que llaman "modelos System One" (estoy con Maggie Appleton, creo que "modelos de decisión" es un mejor nombre para estos). Jev es un in

La noticia

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