Writing C++ with Jev by picking valid next tokens
The author experimented with TypeSafe's Jev decision/classifier model for C++: at each step it was given only grammatically valid next tokens to pick from, avoiding free-form generation.
A developer shares using TypeSafe Jev to quickly classify node types in a graph-based UX, enabling per-type animations without added latency or cost.
Thanks to @typesafeai’s jev, I gave my graph-based UX a real facelift. It classifies which type of node to spawn faster than any model I’ve used before. That let me add gorgeous per-type animations without increasing latency or cost. Now I want to go back to the rest of my old