Yes, code review is the bottleneck, no you're not doing it right

Re:Yes, code review is the bottleneck, no you're not doing i... by rednafi on Wednesday January 21, 2026 @04:45PM (#46712015)

I’m all in for building more intuitive UIs to make the review process less cumbersome. But with the current capabilities of LLMs, under no circumstances should we allow AI to be the final judge of whether something should be merged into trunk.

Code review is the last line of defense we have against our systems being invaded by the massive amount of slop that’s getting generated left and right.

Instead of trying to automate the code review process, maybe we should spend more energy on making the scaffolding around it better: better diff tools, semantically grouped files (as Devin mentioned), and better UI for large diffs (GitHub’s UI is horrible for anything beyond a thousand lines).

[ Parent | on HN ]

Re:Yes, code review is the bottleneck, no you're not doing i... by ninjha on Wednesday January 21, 2026 @04:57PM (#46712167)

(I work at Cognition, opinions my own etcetc)

True! Devin Review doesn’t make the kind of judgements you mention, it just does its best to find bugs and help you understand the code faster. I managed to review a PR on an airplane (without starlink) with it earlier this week lol

[ Parent | on HN ]

Re:Yes, code review is the bottleneck, no you're not doing i... by rednafi on Wednesday January 21, 2026 @05:09PM (#46712302)

Yeah, I wasn’t alluding to Devin reviewing and merging the changelog. This was more of a general statement, since a lot of code review tools seem to get this part wrong.

A lot of energy is being spent on making reviews faster, when reviews are intentionally meant to scale sublinearly. The goal should be: how can we make the process more convenient and less error-prone?

[ Parent | on HN ]

Re:Yes, code review is the bottleneck, no you're not doing i... by gaodrew on Wednesday January 21, 2026 @04:57PM (#46712160)

Agreed!

[ Parent | on HN ]