NeuralNine tests Jev in the TypeSafe console and Python, using binary probabilities, categories, and ordered scores. The examples cover prompt routing, guardrail checks, sentiment, and game decisions, with speed kept separate from decision quality.
Original by NeuralNineGetting startedIntermediate22 min 21 secPublished
The console examples distinguish yes-or-no probabilities, categorical choices, and ordered rating scales.
The routing example assigns prompt complexity before selecting a text model; guardrail checks are demonstrated rather than certified as protection.
The game discussion contrasts rapid actions with strategic competence: a faster move can still be a poor move.
Worth knowing
Jev evaluates pre-specified options rather than generating text, and high confidence or fast response times do not ensure factually correct or optimal decisions.