Get the latest tech news
Test-driven development with an LLM for fun and profit
Welcome to the very first post in a new blog! Here I will discuss software development, SRE work, and other fun stuff. Sometimes an idea is just too good to pass up. I hope this blog will motivate me to turn sparks and little pieces into general knowledge in writing the words down. The other day I was discussing Tabby with a coworker. We talked about whether we should consider AI-autocompleted code harmful and ditch everyone’s newfound habit due to LLM’s inherent unreliability and their tendency toward spaghetti code, throwing traditional software engineering principles like DRY out the window. I disagreed: what if we could have a framework that integrates AI development tooling while also making everything better and more reliable instead? This instantly reminds me of Test-Driven Development, or TDD, which I think is great when combined with the use of a Large Language Model.
With this pattern, not only do we limit the chance of introducing problematic code into production with test coverage by default, but we also encourage aggressive de-coupling and a unit test-first project structure. Because adding additional context to a model incurs some inference (and human-psychological) cost, we are constantly nudged into maintaining our code as nice little chunks, each consuming only a small cognitive load to fully understand. There is a non-zero chance that we wake up tomorrow to a major shift in AI architecture, eliminating the LLM limitations we talked about, and rendering our efforts meaningless.
Or read this on Hacker News
