Is this you? As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.
Claim your profile
Articles by Jet Xu
The Death of the God Model: Why True AGI Requires a Split Brain Architecture
TL;DR: The AI industry's pursuit of a single, omnipotent "God Model" is a dead end. Due to the mathematical paradoxes of RLHF and alignment, models are inevitably bifurcating into specialized hemispheres. We are seeing the rise of the "Left Brain" (GPT-5.5 / Opus 4.8 for logic, backend coding, and deep analysis) and the "Right Brain" (Gemini 3.1 Pro / Opus 4.6 for SVG design, PPTs, aesthetics, and creative writing).
Drowning in AI Code Review Noise? A Framework to Measure Signal vs. Noise
Most AI code review tools generate 10-20 comments per PR. The problem? 80% are noise. Here's a framework for measuring signal-to-noise ratio in code reviews - and why it matters more than you think. The Industry's Dirty Secret You open a PR.
Beyond the Diff: How Deep Context Analysis Caught a Critical Bug in a 20K-Star Open Source Project
If you lead an engineering team, you've probably felt this: you adopt an AI code reviewer hoping to catch real issues, but instead it floods PRs with style suggestions and variable naming tips. Your developers start ignoring it. The signal drowns in noise. The problem isn't the AI—it's that most tools only see the diff. They can't trace how a changed function ripples through your system, or spot when a new database method silently breaks transaction guarantees in your API layer.
Supercharging AI Code Reviews: Our Journey with Mistral-Large-2411
In the realm of AI-powered code review systems, the quality of the underlying language model is crucial for providing actionable insights. This technical deep dive details our journey upgrading LlamaPReview (a fully automated PR review Github APP) from Mistral-Large-2407 to Mistral-Large-2411, focusing on the challenges we encountered and the solutions we engineered.
How We Made AI Code Review 40% More Efficient Using ReAct Patterns
Making AI Code Review 40% More Efficient with ReAct Patterns Code review is a critical but time-consuming process. While AI reviewers promise to help, they often struggle with context understanding and resource efficiency. Here's how we solved these challenges in our open-source project using ReAct patterns and intelligent skip analysis.
The Hidden Cost of Code Reviews: A Senior Developer’s Perspective
Jet Xu · Follow 3 min read · -- “Code reviews are killing our productivity.” As a seasoned Java and Python development lead with over 15 years of experience, I never thought I’d say those words. Yet here I am, pondering a question that might raise a few eyebrows in the software development community: Are we spending too much time on code reviews? Let me paint you a picture of my typical day: 1. Open a new Pull Request (PR) 2. Meticulously read through each line of code 3. Leave detailed comments 4.
🚀 Introducing LlamaPReview - Free AI PR Review Assistant That Actually Understand Your Repo
Hey DEV Community! 👋 I want to share a free GitHub App I built to help developers get automated AI PR reviews without any setup hassle. The Problem PR reviews are essential but time-consuming. While there are many AI code review tools available, most require complex setup or paid subscriptions.
Show More
loading
Actions
Is this you?
As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.Get in touch with Jet
Contact Jet, search articles and posts on X, monitor coverage, and track replies from one place.
Learn more about Muck Rack