Maze Navigation With Jev

JUUN tested whether Jev could escape a maze and found that its performance depended on how the map was written. They then gave Jev the maze as lines of sight and named places instead of a 2D grid.

View on X

JUUN@junhoh0ng𝕏

Can Jev escape a maze? Turns out it depends how you write the map. When given as a 2D grid, “wall above?” is worse than chance. “Wall to the right?” is 99.9%. Rotate the page and every side becomes 1.00. It isn’t seeing the grid. It’s reading the next character. So I gave @typesafeai’s Jev the maze as lines of sight and named places, not as a map. Notes below.

Sep 18, 2026X postsView on X

On the grid, “wall above?” performed worse than chance, while “wall to the right?” scored 99.9%. Rotating the page made every side score 1.00. The author says this suggested Jev was reading the next character rather than seeing the grid.

Also filed under Tools & apps

TypeSafe Jev Decision-Model Client
It provides a shared TypeSafe Jev decision-model client for the dsh ecosystem, with strict response validation, keychain-first key resolution, and typed fail-open errors. It is Jev-optional by design.
Jev Reviews Changed Code
The Claude Code plugin uses Jev (TypeSafe AI) to assess changed code at the end of a turn and, when needed, propose a code review using Open Code Review rules.
Alerts on Company Data-Use Changes
TOS Watch sends an email when a company changes what it does with your data. It combines Open Terms Archive history, a Jev classifier, a static site, and a Cloudflare Worker.
OpenAI API-to-Jev Gateway
jev-gateway turns any OpenAI API backend into a gateway compatible with Jev.