Is GitHub Copilot Ruining Code?
Listen now
Description
In this episode we cover "New GitHub Copilot Research Finds 'Downward Pressure on Code Quality'" by Visual Studio Magazine. This is a summary of a research paper put out by GitClear that looked at 153 million lines of code over 4 years to assess the impact of AI usage on code quality. The paper concluded that Copilot usage is steadily reducing code quality overall, and it looks like it's only going to get worse. We discuss the strengths and weaknesses of the paper, our own personal feelings on this, and Evan gets a little too existential. References from the episode: - Why I'm No Longer Using Copilot by Dreams of Code on YouTube - The Primeagen's reaction video
More Episodes
In this episode we cover "Why I'm skeptical of rewriting javascript tools in faster languages" by Nolan Lawson. This is an interesting intersection between tech problems and people problems. There's been a recent wave of venerable JS-based tools being re-written in Rust, Go, Zig, etc. They come...
Published 10/26/24
In this episode, we cover "Pair Programming" written by the inimitable Matt Hamlin. We talk about what pair programming is, why you might do it, and when you maybe shouldn't. In other news, Joe forgets how to intro the show and Evan drank too much coffee before recording.
Published 10/12/24