Patterns for Building Cybersecurity Evals
A sandboxed target, inputs that influence task difficulty, tools, and a grader.
Eugene Yan18 min read
2 stories
A sandboxed target, inputs that influence task difficulty, tools, and a grader.
Learning to automate simple agentic workflows with Amazon Q CLI, Anthropic MCP, and tmux.
Showing 2 of 2 stories
You're all caught up.
Get the top AI news and tools straight to your inbox every week.
Weekly · AI news from Eugene Yan
Join 15,000+ AI enthusiasts