jevVIDEO
Jev decides instead of writing: 31 checks on a 340-line diff run 20-200x faster
An auth refactor produced a 340-line diff and 31 checks that Claude Code generated in full each time, while Jev returns only a score in 70-500ms at $0.042 per million input tokens, with no output text.
vvtentt
@Vvtentt101Archived 2026.09.25Originally posted 2026.09.25
vvtentt @Vvtentt101Originally posted 2026.09.25
the slow part of your agent is not the hard problem. the problems start after it does the same work several times. JEV DOESN'T WRITE. IT DECIDES. one auth refactor. 340 lines. 31 checks: keep this hunk, reject that file, stop or go again. claude code spent a full generation on each one. jev takes the diff and returns a score. 70-500ms. $0.042 per million in. no output text. output is free because there isn't any. 20-200x faster. 40-400x cheaper. the ceiling is only for loops that decide a lot and write a little.
x.com/vvtentt101/status/2103193709412057564Archived 2026.09.25 10:04