A Developer's Year-Long Research on AI Agents for Security-Critical Software Development
By
Posted by Greg Slepak on July 2, 2026
Summary
A software developer and protocol maintainer shares findings from over a year of research into using AI agents for writing high-quality software in security-critical systems. The author discusses exploring AI agent limits, creating custom AI review tools competitive with multi-billion dollar systems, and maintaining a custom fork of an AI coding agent called Crus. The post focuses on a methodology called "Short Leash AI Coding" for beating the game Fable, emphasizing controlled, security-conscious use of AI in software development.
Source
Hacker NewsA Developer's Year-Long Research on AI Agents for Security-Critical Software Developmentblog.okturtles.orgKey quotes
· 3 pulledThis post is the culmination of over a year of research into how to properly use AI agents to write high-quality software in security-critical systems.
Over the past year I dove deep into AI agents. I have explored their limits, what they can and cannot be relied upon to do.
I've created our own AI review tools that perform just as well as multi-billion dollar AI-review systems.
You might also wanna read
A Field Guide to Production-Ready AI Agents: Context Windows, Security, and Drift Monitoring
Karl Mehta presents a field guide for building production-ready AI agents, focusing on four key engineering challenges: context-window disci
How AI Coding Agents Are Reshaping Software Development: Capabilities, Limitations, and the Future
This article is the fourth in a series examining how AI is changing software development. The author reflects on the evolving capabilities o
Why I won't run the Pi AI coding agent without a safety extension
The article discusses Pi, a powerful AI coding agent, but emphasizes that the author refuses to use it without a specific extension (likely
xda-developers.com·15d ago
How Spec-Driven Development and Living Contracts Prevent Architecture Drift When Using AI Coding Agents
This article discusses the architectural challenges that arise when software teams adopt AI coding agents. The author argues that AI agents,
AI's Impact on Software Engineering: Evolution or Replacement?
The article explores the complex relationship between AI tools like ChatGPT and software engineering, examining whether AI represents the en
The Verge·10mo ago
IBM's CUGA agent harness: building production-ready agentic apps with minimal plumbing
IBM Research introduces CUGA (Configurable Generalist Agent), an open-source agent harness designed to eliminate the plumbing overhead of bu
Comments
Sign in to join the conversation.
No comments yet. Be the first.