AI RESEARCH

Smart Paste: Automatically Fixing Copy/Paste for Google Developers

arXiv CS.LG

ArXi:2510.03843v2 Announce Type: replace-cross Manually editing pasted code is a long-standing developer pain point. In internal software development at Google, we observe that code is pasted 4 times often than it is manually typed. These paste actions frequently require follow-up edits, ranging from simple reformatting and renaming to complex style adjustments and cross-language translations. Prior work has shown deep learning can be used to predict these edits.