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.
Jev benchmarked on state machine programming
Dorian Smiley shares a state machine programming benchmark: Gemini Flash Lite 3.1 scores 75.6% overall, while Jev reaches 72.2% overall, 100% on canonical tasks, and runs ~6× faster, with misses mostly in novel compositions.
New state machine programming benchmark: Gemini Flash Lite 3.1: 75.6% overall, 66.7% generalization. Jev: 72.2% overall, 61.4% generalization, but 100% on canonical tasks and ~6× faster. Jev’s misses are concentrated in specific novel compositions, not broad task failure. It is
· 1 likesOpen on X
More like this
Using Jev for Code Review
The author thinks code review is a really good use case for using Jev.
Fascin: A Jev-Powered PR Triage Tool
A developer shares Fascin, a PR triage tool built with Jev that assesses urgency, change type, and merge readiness, noting Jev handles the actual reasoning.
