AI coding agents still need human cleanup on nearly three out of four tasks in a real-world test

Alibaba's new coding-agent benchmark, Co-Design Bench, tests AI agents on real user requests that already tripped them up in practice.

원문의 저작권은 The Decoder에 있습니다. 위 발췌는 원문 확인을 돕기 위한 짧은 인용입니다.