LLM

github repo There is a growing interest in using LLMs to generate unit tests. They have shown potential to create tests that look natural and resemble those written by developers, including sane variable names and typical assertions. However, despite some initial success and praise from AI enthusiasts, generating tests with LLMs involves challenges that differ from general code generation. Junjie Wang et.al [1] describes some of these challenges much better than I could....

Many were caught by surprise when OpenAI revealed the coding capabilities of their model (and ofc SWEs started to panic they will lose their jobs). However, there was a significant body of research indicating the eventual creation of an intelligent code generation tool…it’s just that most of us were not aware of it. This is not a technical post, but rather aims to be (or at least, I hope so) an interesting exploration of studies from over a decade ago that highlighted the deterministic characteristics of software code....