Communications of the ACM
Study Suggests AI Puts Downward Pressure on Code Quality
AI that boosts code quantity doesn't always lead to better quality.
Credit: Shutterstock
While generative AI may boost code development, it could also be detrimental to overall code quality, according to new research from GitClear, a provider of developer analytics tools.
The study analyzed 153 million changed lines of code, comparing changes done in 2023 versus prior years, when AI was not as relevant for code generation.
The findings show that "code churn," or the percentage of lines thrown out less than two weeks after being authored, is on the rise and expected to double in 2024. The study notes that more churn means higher risk of mistakes being deployed into production.
The percentage of "copy/pasted code" is increasing faster than "updated," "deleted," or "moved" code, the study says. "In this regard, the composition of AI-generated code is similar to a short-term developer that doesn't thoughtfully integrate their work into the broader project," says GitClear founder Bill Harding.
From GeekWire
View Full Article
No entries found