Jev case: This AI says it can't hallucinate.

@ThatNerdyEight ThatNerdyEight · Sep 20, 2026 · case #036968 · listed via Jev Hub

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

Described Jev as returning typed decisions with probabilities in one parallel pass, noting its answers must be pre-defined.

The original post

This AI says it can't hallucinate. Jev (TypeSafe AI, out of stealth w/ a $40M seed) doesn't write text. It returns typed decisions with probabilities, in one parallel pass. Up to 200x faster than an LLM. Output tokens free. It even plays Doom live. Catch: answers pre-defined.

Engagement when collected

Likes0

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, classification & data extraction. 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 🗂️ Classification & data extraction