JevMade Sign in
← Back to experiments

Benchmarks & research

typesafe-oracles

typesafe-oracles tests when a typed Jev judgment is more useful than a conventional language-model call.

Source screenshot of typesafe-oracles
SOURCE SCREENSHOTFull screenshot ↗

What it does

Its repeatable harness compares Jev with Claude Haiku and reports accuracy, calibration, confidence separation, and cost.

Maker-reported (not independently measured by JevMade): Haiku-API run; the claude -p arm is ~8x the API arm and exists only to show what CLI harness

Primitives
choice, score, noul
Platform
JavaScript
Added
Project created
GitHub stars
0 (snapshot, not live)

Keep this for later

Sign in to bookmark experiments, guides and videos, and keep notes only you can see.

Continue to sign in

We’ll bring you back to this listing.