On average, AI-generated pull requests (PRs) include about 10.83 issues each, compared with 6.45 issues in human-generated PRs. That’s about 1.7x more when AI is involved, meaning longer code reviews and increased risk of defects.
Problems caused by AI-generated PRs also tend to be more severe than human-made messes. AI-authored PRs contain 1.4x more critical issues and 1.7x more major issues on average than human-written PRs, the report says.
cross-posted from: https://programming.dev/post/42624268
You must log in or # to comment.
Who woulda thunk… Btw, it’s machine-learning, not AI.
This is a losing battle. Just like developers calling multiplayer tests ‘alphas’.
I’ll forevermore consider it a basic IQ test…