Ran a dumb experiment last night: used Jev by @typesafeai

Fed Jev the finite set of grammatically valid next tokens in C++ and let it pick one at each step, producing working code without free-form generation.

The original post

Ran a dumb experiment last night: used Jev by @typesafeai (a decision/classifier model, not a text-gen model) to write C++.

At every step I gave it the finite set of grammatically valid next tokens and let it just... pick one. No free-form generation, no hallucinated syntax, purely "choose from this legal set." It's not built for this, that's what made it fun.

Got a working piece of C++ out of a model that fundamentally does not generate text. Not claiming this is how you should write code, and it's slower and dumber than just using an actual code model. But it's a neat proof that a classifier constrained tightly enough can stumble into looking like a generator.

Novelty over utility here, but it's the kind of dumb experiment that tells you more about a model's actual guardrails than the official demos do.

Engagement when collected

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.