Author: JesterXL

2 1/2 years ago, I wanted to work with my favorite technologies, work with people in person, and deliver software every day to users. I achieved those goals, learned a ton, and at the cost of massive salary/bonus cuts. I’ve thought about, “could I have just paid that amount of money for training/schooling instead” and I don’t think so.

Choice quotes from this Copilot research on GitHub:

• using Copilot is strongly correlated with mistake code being pushed to the repo
• current implementation of AI Assistants discourages code reuse
• we have entered an era where code lines are being added faster than ever before. The better question for 2024: who’s on the hook to clean up the mess afterward
• code generated during 2023 more resembles an itinerant contributor, prone to violate the DRY-ness of the repos visited

https://visualstudiomagazine.com/articles/2024/01/25/copilot-research.aspx

CodeScene’s latest whitepaper, Refactoring vs Refuctoring, has some interesting findings, quotes, and improvements for AI / LLM assisted coding.

You don’t negotiate with Product Owners on time on technical debt vs. time on features. You refactor all the time, while building the features. Product Owners not giving you time aren’t the ones at fault for the technical debt, you the coder are, for allowing the code to become a mess over time.