Back to Devoured - June 23, 2026
DEVOURED
You should use AI for reviewing code especially when the diff is huge

You should use AI for reviewing code especially when the diff is huge

Tech aidevops Bearblog
Human reviewers should stop nitpicking syntax and instead use AI to handle large diffs, focusing their expertise only on high-level design and context-specific constraints.
What: The author argues that modern LLMs reliably handle vulnerability and style checks, meaning human reviewers should offload massive code changes to AI while contributing only 'out-of-distribution' knowledge like architectural intent.
Why it matters: Code review is evolving from a gatekeeping function to a knowledge transfer function; human bottlenecks in reviewing massive AI-generated diffs are avoidable if engineers shift their focus to architectural oversight.
Takeaway: When reviewing massive AI-generated diffs, ignore nitpicks and instead prompt the AI to focus on architectural context or specific team-known deprecated APIs.
Decoder
  • Diff: The difference between two versions of source code, usually generated during a commit or pull request.
  • Out-of-distribution (OOD) knowledge: Information or context that is not present in the training data of an AI, such as recent team meetings, proprietary architectural decisions, or company-specific code standards.
Original article

You should use AI for reviewing code especially when the diff is huge

I often hear that AI is resulting in 10k LOC reviews and this is creating a bottleneck. I don't think you should waste time reviewing every single line of code in here and just use AI to review it!

What you contribute as a reviewer

You need to know what you contribute as a reviewer.

As a reviewer, you contribute your Out Of Distribution knowledge that the author or the LLM might not have

Its a mistake thinking you can outsmart an LLM into nitpicking few lines of code here and there. This is not worth your time because LLM's have far surpassed these kind of issues. Lets remember that these LLM's are now catching high severity vulnerabilities -- your line by line reviews have no place here.

What kind of knowledge can you bring in as the reviewer?

What you bring is the knowledge that the author nor the LLM doesn't know.

Examples

  1. That meeting you had last week with the architect where you discussed using service_A getting deprecated? The author doesn't know this.
  2. You also probably have some general principles in your codebase - don't add fields to the main huge object or don't add metrics in this particular way. These are the things you bring to the review.
  3. Some high level design smells that only you know as the codebase expert

The way I use AI for reviews is to point AI to the change and contribute my Out Of Distribution knowledge in terms of prompts and questions.

Caveats

This workflow works in places where each line of code is not sacred. There are places where each line may be sacred, like in embedded systems.

Explore all 42 articles in today's digest

Fresh dev news, AI-digested daily. Never miss a trend at devoured.fyi