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 Model Outperforms GPT Luna 6 on Codebase Checks
Tessl ran about 2,725 verifier checks on its own production code: GPT Luna 6 took 436s, Jev only 32s at 2.7x lower cost. The two judges agreed on 85.9% of decisions. Method and commands are available.
What if your review rules ran across your whole codebase in 32 seconds? We ran about 2,725 verifier checks on our own production code. GPT Luna 6: 436s. Jev: 32s, at 2.7x lower cost. The two judges agreed on 85.9% of decisions. Method and commands: https://tessl.io/blog/jev-is-136x-faster-and-27x-cheaper-than-gpt-luna-6-for-tessl-verifiers-try-it-yourself…
· 0 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.
