← All projects
decisions-demo
vecten/decisions-demo MIT Python Eval & Align
rank#400
Decision models (TypeSafe's Jev) vs Claude on the same typed questions: three demos measuring agreement, latency, cost and calibration.
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last push
- today
Star history starts building from the first daily refresh.
ai-agentsanthropicclaudedecision-modelsjevllmllm-evaluationpydanticpydantic-aistructured-outputtypesafe