#llm
ls ./tags/llm
2026-05-05~5 min
BugBash 2026, or how the correctness decade has started
A retrospective on BugBash 2026, and why software engineering looks brighter than ever.
2026-01-15~9 min
What I Tell Colleagues About Using LLMs for Engineering
LLMs amplify expertise, they don't replace it. Here's what works: planning, context, feedback loops, and building systems that let AI discover bugs.
2025-12-19~6 min
Specs Are Back, But We're Missing the Tools
LLMs revived specifications. Model checkers like Fizzbee work for algorithms. But for APIs and business logic? The tooling doesn't exist yet.
2025-09-08~6 min
Testing: prevention vs discovery
Most testing prevents old bugs from returning. But what if we built systems where LLMs could actively discover new bugs instead?