TypeSafe released Jev, a model that makes typed if-then decisions without generating text. Theodore Lee released SemIf, an open-source version with the same approach. Both cut inference costs by 99% for basic programming logic. They run attention math once and skip full token generation. Jev costs $0.042 per million input tokens with no output cost. On a 2,000-input-token call, Jev is 82 to 209 times cheaper than frontier models. In tests, Jev and SemIf nearly doubled classification accuracy on 98 email threads. They also handled 8 of 31 live emails without errors. The approach suggests other programming primitives may see similar specialization. It also splits AI economics into discovery and production use cases.
What changed
Traditional AI models generated text autoregressively for every decision, including simple if-then logic.
What it unlocks
Running typed, zero-token decisions for basic programming primitives at a fraction of the cost.
- 99% cost reduction for if-then decisions
- 82x to 209x cheaper per classification call
- 47% to 80%+ classification accuracy improvement
- 98 hand-verified production email threads
What you need to act on it
- a workflow with if-then logic
- integration with specialized decider models like Jev or SemIf
Sources