Tested TypeSafe AI's new model, Jev, on chess.

@bariskisir Barış Kısır · Sep 20, 2026 · case #129683 · listed via Jev Hub

Still from the clip posted with this case; watch it in the original post on X.

Tested Jev on bullet chess, finding it could not beat a 250 ELO computer but works for fast, cheap tasks.

The original post

Tested TypeSafe AI's new model, Jev, on chess. It's cheap & fast, so I tried bullet chess where speed matters most. Didn't hold up — couldn't beat even the 250 ELO computer. Still solid for other cost-efficient, fast-response tasks. #AI #Chess #Jev https:// github.com/bariskisir/Che ssBot/tree/feature/jev-test …

Engagement when collected

Likes1

Bookmarks0

Reposts0

Replies0

Quotes0

Numbers are a snapshot taken from X when the case was added to the library (schema v1, collected 2026-09-19); they will not match today.

Where this case fits

Filed under games & playable demos, coding & developer tools. In the pattern Jev is built for, the model answers a bounded question per step — and ordinary code acts on the answer, because the answer is already a value rather than a paragraph. Other posts in the same family are on the games & playable demos page.

🎮 Games & playable demos 🛠️ Coding & developer tools