Jev Based Code Review
by namanbhulawat on 9/25/2026, 4:49:23 AM
https://github.com/egma-ai/jev-code-reviewer
Comments
by: gatapia2
I don't understand Jev. Its a generic classifier right? Like the classifiers we were building 15 years ago with random forrests and logistic regressions, but just generic. What's so revolutionary? And how can the accuracy be any better than a custom trained classifier that can be built in a day (an hour using Claude).<p>I don't understand the hype.
9/25/2026, 9:13:55 AM
by: lm2s
I think your engineering process is fundamentally broken if you are generating PRs with 230 files changed so regularly that you need to bolt on more AI. You’re solving the wrong problem.
9/25/2026, 7:49:34 AM
by: gdorsi
It would be actually nice to build a simple classifier that marks noise from PRs (stuff like formatting changes for example)<p>For the rest, I wouldn't trust an AI to pick what's important.<p>We can already do AI reviews, and while helpful, we know we can't trust them too much
9/25/2026, 9:46:26 AM
by: bvrmn
Yey! Let's speedup project downfall to crap abyss even more!<p>You either care about project and do reviews. Or yolo vibe code. This middle ground has little sense.
9/25/2026, 9:55:50 AM
by: docheinestages
Jev has good use cases that require speed. But speed is not all. Tasks like code review need quality, which costs time. If you just want speed, you might as well go with a non-reasoning model like Haiku.
9/25/2026, 9:40:34 AM
by: kushbhuwalka
jev is not good at reasoning, its a generic low-level classifier. for reviewing / classifying code, i would strongly suggest not using jev.
9/25/2026, 9:42:42 AM
by: namanbhulawat
Most PRs that are generated by agents today get YOLO merged because its hard for human mind to comprehend when your agent just suddenly shows up with 230 file changes. This is an attempt to reduce the mental burden by classifying each change in a review to P0, P1, P2. Only P0 are shown by default. The priorities are configurable. The diffs are also show using a natural language. The original code is one toggle away.
9/25/2026, 4:49:23 AM
by: yube01
confidence score really feels like real machine learning project which we test to check the confusion matrix
9/25/2026, 8:55:59 AM
by: adityamishra241
Nice idea. This could make large agent-generated PRs much easier to review.
9/25/2026, 5:28:25 AM
by: thiago_fm
You still review code?<p>Maybe improve your development process, learn how to use AI better so you don't have to.<p>Maybe only if you are writing OS or some very specific kind of software you have to do this.<p>For all the other kinds of software, you likely don't need to.
9/25/2026, 9:40:41 AM
by: manojlds
Slop projects to solve slop
9/25/2026, 8:17:13 AM
by: egecant
I have a better idea, what about stop spamming slop PRs to projects?
9/25/2026, 9:23:16 AM
by: segersniels
[dead]
9/25/2026, 7:49:36 AM