As they achieve in reputation, AI coding assistants reminiscent of GitHub Copilot might seem like boosting productiveness. But in actuality, they may very well be inflicting general code high quality to say no.
That’s the top-line discovering from a brand new report launched by software program engineering platform GitClear, which analyzed 211 million code traces from 2020 to 2024. According to GitClear’s evaluation, there was a exceptional decline in code reuse final yr — a possible trigger for concern, provided that code reuse is a typical observe to assist construct redundant methods.
Several latest surveys have proven that AI coding assistants have a tendency to provide blended outcomes.
One from software program vendor Harness discovered the vast majority of devs spend extra time debugging AI-generated code and safety vulnerabilities in comparison with human-written contributions. A Google report, in the meantime, discovered that AI can quicken code evaluations and profit documentation, however at the price of supply stability.
