AI 코딩 에이전트는 연구 소프트웨어를 현대화할 수 있지만, 그 과학이 옳은지는 판단하지 못한다
OpenAI와 학계 파트너들의 현장 보고서에 따르면, AI 코딩 에이전트는 낡은 연구 소프트웨어를 업데이트하고 속도를 높일 수 있지만, 작업의 상당 부분이 코드 작성에서 결과 검증으로 옮겨갑니다.
a field report from openai and academic partners details eight projects where ai coding agents modernized legacy scientific software, ranging from simple build updates to full gpu-native rewrites in rust. results showed dramatic performance gains, with rustqc combining 15 tools to cut runtime from over 15 hours to under 15 minutes, and a gpu-based rewrite running nearly 100 times faster than its cpu predecessor. despite these successes, researchers found that agents like gpt-5.5 and claude code often presented errors with full confidence and lacked the capacity to verify scientific accuracy. this suggests that while ai can handle the heavy lifting of code migration, researchers must still rely on expert guidance and independent testing to ensure scientific validity.