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.
Developer Jason Alco shares a head-to-head comparison between Jev and 5.6 Sol on a text categorization step in a platform he's building. The surprising outcome leads him to question whether text-based judgements are exactly what Jev is designed for.
I put Jev vs 5.6 Sol head-to-head on a text categorization step in a platform I’m building. Surprised by the outcome. Aren’t text-based judgements the exact use case Jev is made for?