DEV Community

Charlie Xu profile picture

Charlie Xu

Exploring the intersection of AI and web development.

Location San Francisco, CA Joined Joined on 
No Trace, No Grade: A Bootcamp Lab on Agent Flight Recorders

No Trace, No Grade: A Bootcamp Lab on Agent Flight Recorders

Comments
7 min read
Second Machine, Same Grade: A Bootcamp Lab on Hidden Local Assumptions

Second Machine, Same Grade: A Bootcamp Lab on Hidden Local Assumptions

Comments
8 min read
Green on Your Laptop Is Not a Grade: A Bootcamp Lab on Runtime Contracts

Green on Your Laptop Is Not a Grade: A Bootcamp Lab on Runtime Contracts

Comments
8 min read
When the Model Writes the Tests: A Bootcamp Lab on Human Oracles

When the Model Writes the Tests: A Bootcamp Lab on Human Oracles

Comments 1
8 min read
Don't Grade the Agent Until the Tool Schema Is Frozen

Don't Grade the Agent Until the Tool Schema Is Frozen

Comments
8 min read
Twelve Tool Calls, Then Stop: A Bootcamp Lab on Agent Loop Budgets

Twelve Tool Calls, Then Stop: A Bootcamp Lab on Agent Loop Budgets

Comments
7 min read
Stop Debating Free vs. Self-Hosted AI: Score Your Constraints Instead

Stop Debating Free vs. Self-Hosted AI: Score Your Constraints Instead

Comments
4 min read
Free vs Self-Hosted AI Coding Assistants: A Token-Economics Decision Guide

Free vs Self-Hosted AI Coding Assistants: A Token-Economics Decision Guide

Comments
5 min read
Grade the Guesses: A Bootcamp Lab With an Assumption Gate

Grade the Guesses: A Bootcamp Lab With an Assumption Gate

Comments
8 min read
Your AI Remembers Too Much: A Bootcamp Lab on Forgetting, Built on Free Infrastructure

Your AI Remembers Too Much: A Bootcamp Lab on Forgetting, Built on Free Infrastructure

Comments
4 min read
Ship an AI Feature for $0: A Bootcamp Lab With Checkpoints and a Fair Rubric

Ship an AI Feature for $0: A Bootcamp Lab With Checkpoints and a Fair Rubric

Comments
5 min read
A Noise Budget for Automated PR Reviews: Free Models, a Free Server, and a Protocol That Keeps Humans Listening

A Noise Budget for Automated PR Reviews: Free Models, a Free Server, and a Protocol That Keeps Humans Listening

Comments
5 min read
A Mutation-Based Regression Test for Your AI Code Reviewer

A Mutation-Based Regression Test for Your AI Code Reviewer

Comments
4 min read
When AI Remembers Too Much: A Differential Testing Safety Net

When AI Remembers Too Much: A Differential Testing Safety Net

Comments
6 min read
A PR Review Bot That Costs Zero: Free Models on a Free Server

A PR Review Bot That Costs Zero: Free Models on a Free Server

Comments
7 min read
A Bootcamp Lab for Stress-Testing AI Coding Models on a $0 Budget

A Bootcamp Lab for Stress-Testing AI Coding Models on a $0 Budget

Comments
5 min read
Free vs. Paid AI Infrastructure: A Decision Framework That Survives Production

Free vs. Paid AI Infrastructure: A Decision Framework That Survives Production

Comments
5 min read
Free AI Infrastructure Isn't a Compromise. It's a Constraint Class.

Free AI Infrastructure Isn't a Compromise. It's a Constraint Class.

Comments
5 min read
Your PRs Deserve a Second Reviewer That Costs Nothing: A Webhook Architecture

Your PRs Deserve a Second Reviewer That Costs Nothing: A Webhook Architecture

Comments
6 min read
Zero-Budget AI Coding Model Evaluation: A Sandbox-First Workflow

Zero-Budget AI Coding Model Evaluation: A Sandbox-First Workflow

Comments
6 min read
A Zero-Trust Red-Team Loop for a Trending Model Launch (MiniMax H3 Edition)

A Zero-Trust Red-Team Loop for a Trending Model Launch (MiniMax H3 Edition)

Comments
4 min read
A Sandbox-First Workflow for Evaluating AI Coding Models on a Zero Budget

A Sandbox-First Workflow for Evaluating AI Coding Models on a Zero Budget

Comments
5 min read
loading...