JevMade

Sign in
← Back to experiments

Benchmarks & research

Jev Does Not Play Dice

What does a probability model do when the answer is genuinely random? These experiments found out, and the answer is not flattering.

Source screenshot of Jev Does Not Play Dice
SOURCE SCREENSHOTFull screenshot ↗

What it does

Asked to bet on a hidden fair die roll, Jev picked a side at near-chance accuracy while claiming high confidence. Noul did much better on the same rolls. Every raw response is in the repo.

How you can use it

Before building, gather sample documents that already state exact risk percentages, like inventory shortage forecasts. A developer can borrow this project's test setup to check how the AI scores those known numbers. Your developer can preview the test questions offline without using a paid access key.

Never let the AI recalculate or replace percentages already written in your original business documents. The tests showed that Jev pushes moderate chances to extreme highs or lows. Have your developer directly copy and save the original reported numbers for your app to follow.

Maker-reported (not independently measured by JevMade)

Fair die Choice: 82.9% mean reported probability at 19.0% accuracy across 400 rolls (maker-reported)

Primitives
choice, noul
Platform
JavaScript
Added
Project created

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.