Journal.
Writing on AI security, agentic systems, and engineering practice.
Loop Engineering: Designing the Systems That Drive AI Agents
A comprehensive guide to loop engineering — the emerging discipline of designing the systems that drive AI agents — and how it compares with prompt, context, and harness engineering.
Featured — SecurityLLM Jailbreaking & System Vulnerabilities
How jailbreaking techniques reveal deeper architectural vulnerabilities in agentic systems.
Front Lines and Factory Floors: The New Shape of Software Engineering
Practitioner-focused article on forward-deployed engineering and software factories and what they mean for engineering leaders and founders.
Loop Engineering: Designing the Systems That Drive AI Agents
A comprehensive guide to loop engineering — the emerging discipline of designing the systems that drive AI agents — and how it compares with prompt, context, and harness engineering.
Simon Willison on the AI inflection point, dark factories, and the disaster he keeps predicting
A wide-ranging look at where AI-assisted software development stands going into 2026
AI-Assisted Development: Security Gaps and Solutions
The security blind spots introduced when AI writes your code — and how to close them.
AI-native security: why current guardrails are obsolete
Why the security models we built for traditional software fail against LLM-native threats.
Understanding LLM Specialization: RAG vs. Fine-Tuning
When to use RAG and when to fine-tune: a decision framework for engineering teams.
OWASP Top 10 for LLM Applications 2025
A practitioner's breakdown of the OWASP Top 10 for Large Language Models, 2025 edition.
What Is Retrieval-Augmented Generation (RAG)?
RAG explained: architecture, tradeoffs, and implementation patterns for production systems.
ChatGPT Models Guide
A practical guide to the OpenAI ChatGPT model families for engineering teams.
LLM Jailbreaking & System Vulnerabilities
How jailbreaking techniques reveal deeper architectural vulnerabilities in agentic systems.