DEV Community

Riley Zhu profile picture

Riley Zhu

Building things with Python, Go, and JavaScript. Love automating everything.

Location Beijing, China Joined Joined on 
When Your AI Reviewer Remembers Too Much: A Two-Phase Memory Probe

When Your AI Reviewer Remembers Too Much: A Two-Phase Memory Probe

5
Comments 1
5 min read
A Free-Resource Kit for Evaluating AI Code Reviewers: Prompt, Rubric, and Failure Modes

A Free-Resource Kit for Evaluating AI Code Reviewers: Prompt, Rubric, and Failure Modes

Comments
5 min read
A Decoy-PR Test for AI Reviewer Candidates: Prompt, Rubric, and a Free-Server Reference Setup

A Decoy-PR Test for AI Reviewer Candidates: Prompt, Rubric, and a Free-Server Reference Setup

Comments
5 min read
A Zero-Budget Take-Home Task for AI Review Bot Candidates: Prompt, Rubric, and Reference Solution

A Zero-Budget Take-Home Task for AI Review Bot Candidates: Prompt, Rubric, and Reference Solution

Comments
5 min read
A Take-Home Task That Actually Tests AI Reviewers: Prompt, Rubric, and Failure Modes

A Take-Home Task That Actually Tests AI Reviewers: Prompt, Rubric, and Failure Modes

Comments
5 min read
The Comment That Hacked Our AI Reviewer: A Prompt Injection Autopsy

The Comment That Hacked Our AI Reviewer: A Prompt Injection Autopsy

Comments
4 min read
How to Feed a Pull Request to an LLM: Four Diff-Packing Strategies, Compared

How to Feed a Pull Request to an LLM: Four Diff-Packing Strategies, Compared

Comments
5 min read
The Review Bot Flooded Every PR With Comments. Root Cause: A Two-Dot Git Diff

The Review Bot Flooded Every PR With Comments. Root Cause: A Two-Dot Git Diff

Comments
4 min read
A PR That Reviews Itself: Wiring a Free Server Into Your CI Pipeline

A PR That Reviews Itself: Wiring a Free Server Into Your CI Pipeline

Comments
5 min read
The Review Bot Said "No Issues" for 72 Hours Straight. The Root Cause Wasn't the Model.

The Review Bot Said "No Issues" for 72 Hours Straight. The Root Cause Wasn't the Model.

Comments
4 min read
A Free Server, a Cheap Model, and a Scoreboard: One Team's Code Review Audit

A Free Server, a Cheap Model, and a Scoreboard: One Team's Code Review Audit

Comments
5 min read
The MiniMax H3 Hype Arrived Before the Numbers. A Small Team Built a Gate Instead.

The MiniMax H3 Hype Arrived Before the Numbers. A Small Team Built a Gate Instead.

Comments
5 min read
Every Week a New Model Drops. Here's the 30-Minute Eval I Run Before Believing the Hype

Every Week a New Model Drops. Here's the 30-Minute Eval I Run Before Believing the Hype

Comments
4 min read
Judge AI Code Review With a Scoreboard, Not a Demo: A Repeatable Experiment That Runs on Free Access

Judge AI Code Review With a Scoreboard, Not a Demo: A Repeatable Experiment That Runs on Free Access

Comments
7 min read
loading...