Vercel's fx may switch safety reviewer to Jev: 5-18x faster than GPT Luna

thesaraharminta · x · 2026-09-17

Vercel CEO Guillermo Rauch confirmed that typesafeai's Jev benchmarked 5-18x faster and more accurate than GPT Luna as the safety classifier in fx's auto mode, which analyzes every command. Jev is coming to Vercel AI Gateway and will likely become the new default reviewer.

Related event: Vercel fx to adopt Jev safety classifier, 5-18x faster than GPT Luna(2 posts)→

Original post →

More from coding & agent

coding & agent channel →