Forem

Kang profile picture

Kang

Principal Engineer at Microsoft. Building open source tools for AI agent security, testing, and financial intelligence.

Joined Joined on  github website
I Scanned 50 AI Agents for Security Vulnerabilities — 94% Failed

I Scanned 50 AI Agents for Security Vulnerabilities — 94% Failed

Comments
4 min read
Your AI Agent Has No Tests — Here's How to Fix That in 5 Minutes

Your AI Agent Has No Tests — Here's How to Fix That in 5 Minutes

Comments
2 min read
Your Backtest Is Lying to You — Walk-Forward Validation Catches Overfitting
Cover image for Your Backtest Is Lying to You — Walk-Forward Validation Catches Overfitting

Your Backtest Is Lying to You — Walk-Forward Validation Catches Overfitting

Comments
5 min read
I Let an Algorithm Evolve Trading Strategies for 127 Generations — Here's What Happened
Cover image for I Let an Algorithm Evolve Trading Strategies for 127 Generations — Here's What Happened

I Let an Algorithm Evolve Trading Strategies for 127 Generations — Here's What Happened

2
Comments
6 min read
Why Genetic Algorithms Beat Deep RL for Trading (At Least for Me)
Cover image for Why Genetic Algorithms Beat Deep RL for Trading (At Least for Me)

Why Genetic Algorithms Beat Deep RL for Trading (At Least for Me)

Comments
5 min read
Testing AI Agents Is Hard — Here's a Framework That Makes It Practical

Testing AI Agents Is Hard — Here's a Framework That Makes It Practical

Comments
2 min read
Your AI Agent Has Security Holes — Here's How to Find Them

Your AI Agent Has Security Holes — Here's How to Find Them

Comments
2 min read
loading...