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.
The user says Jev is still not fully implemented, while they are trying out Opus 5.5 and motion-graphics libraries, and is amazed by yet another new AI model.
belum juga beres implementasi Jev, baru juga asyik-asyiknya nyobain Opus 5.5 ama motion-graphics libraries... eh, udah keluar lagi AI model baru yang bikin bengong