ai-code-generation

GitHub has added Rubber Duck to Copilot CLI, a feature that provides alternative suggestions by consulting different AI model families. The feature lets developers get a second opinion on code suggestions directly from the command line.

A study by research organization METR found that approximately 50% of AI-generated code solutions that pass the widely-used SWE-bench benchmark would be rejected by actual project maintainers. The finding exposes a significant gap between industry-standard code generation benchmarks and real-world code review standards.