Guangyi Zhao

Senior TPM | Data Center Infrastructure & Applied AI — building LLM agents for hardware diagnostics, IT ops, and agriculture. San Jose, CA.

San Jose, CA Joined on Oct 7, 2026 https://github.com/Ezra-Zhao

Guangyi Zhao

Oct 19

Letting an AI Agent Drive Ghidra: A Hands-On Test of REA’s 170 MCP Tools, One Recovered Password, and the Limits

#ai #mcp #security #programming

13 min read

Guangyi Zhao

Oct 19

“Can You Make It Cheaper?” — and the Agent Booked the Order: A State-Machine Field Test of Wiper-Service-Agent

#ai #agents #python #programming

14 min read

Guangyi Zhao

Oct 19

Before You Wire an LLM Into GPU Fault Triage: AI-Node-Sentinel's Integration Points and Six Measured Failure Modes

#ai #llm #devops #python

13 min read

Guangyi Zhao

Oct 19

The Total Was Right and the Structure Was Wrong: Stress-Testing a Flower-Counting Pipeline Against Light and Occlusion

#python #ai #programming #opensource

10 min read

Guangyi Zhao

Oct 19

How Many of a Scanner's Findings Are Real? Web-Vuln-Scanner's Detection Pipeline and False-Positive Control, Measured

#security #cybersecurity #python #webdev

14 min read

Guangyi Zhao

Oct 19

How Big Should the Worker Pool Be? Measuring the Concurrency Model of a Go Diagnostics Engine

#go #programming #performance #backend

10 min read

Guangyi Zhao

Oct 19

The Privacy Bill Comes Due Before the Real Model Arrives: Field Constraints of Emotion-Guard, a Kindergarten Emotion-Recognition Demo

#ai #privacy #python #ethics

12 min read

Guangyi Zhao

Oct 15

9 One-Page Cheatsheets for Commands You Keep Looking Up (ffmpeg, git, docker, curl, jq, regex) + 2 Bonus Lists

#cheatsheet #cli #git #docker

2 min read

Guangyi Zhao

Oct 7

Claude Code vs Codex CLI vs Cursor: An Honest Field Guide for Working Developers

#ai #claude #programming #productivity

4 min read

DEV Community

Guangyi Zhao

Badges

Writing Debut

Letting an AI Agent Drive Ghidra: A Hands-On Test of REA’s 170 MCP Tools, One Recovered Password, and the Limits

“Can You Make It Cheaper?” — and the Agent Booked the Order: A State-Machine Field Test of Wiper-Service-Agent

Before You Wire an LLM Into GPU Fault Triage: AI-Node-Sentinel's Integration Points and Six Measured Failure Modes

The Total Was Right and the Structure Was Wrong: Stress-Testing a Flower-Counting Pipeline Against Light and Occlusion

How Many of a Scanner's Findings Are Real? Web-Vuln-Scanner's Detection Pipeline and False-Positive Control, Measured

How Big Should the Worker Pool Be? Measuring the Concurrency Model of a Go Diagnostics Engine

The Privacy Bill Comes Due Before the Real Model Arrives: Field Constraints of Emotion-Guard, a Kindergarten Emotion-Recognition Demo

9 One-Page Cheatsheets for Commands You Keep Looking Up (ffmpeg, git, docker, curl, jq, regex) + 2 Bonus Lists

Claude Code vs Codex CLI vs Cursor: An Honest Field Guide for Working Developers