We investigate the potential of GPT-4~\cite{gpt4} to perform Neural Architecture Search (NAS) -- the task of designing effective neural architectures. Our proposed approach, \textbf{G}PT-4 \textbf{E}nhanced \textbf{N}eural arch\textbf{I}tect\textbf{U}re \textbf{S}earch (GENIUS), leverages the generative capabilities of GPT-4 as a black-box optimiser to quickly navigate the architecture search space, pinpoint promising candidates, and iteratively refine these candidates to improve performance. We assess GENIUS across several benchmarks, comparing it with existing state-of-the-art NAS techniques to illustrate its effectiveness. Rather than targeting state-of-the-art performance, our objective is to highlight GPT-4's potential to assist research on a challenging technical problem through a simple prompting scheme that requires relatively limited domain expertise\footnote{Code available at \href{https://github.com/mingkai-zheng/GENIUS}{https://github.com/mingkai-zheng/GENIUS}.}. More broadly, we believe our preliminary results point to future research that harnesses general purpose language models for diverse optimisation tasks. We also highlight important limitations to our study, and note implications for AI safety.

翻译：我们探究了GPT-4~\cite{gpt4}执行神经架构搜索（NAS）——即设计高效神经架构的任务——的潜力。我们提出的方法——**G**PT-4 **E**nhanced **N**eural arch**I**tect**U**re **S**earch（GENIUS）——利用GPT-4作为黑盒优化器的生成能力，快速导航架构搜索空间、定位有前景的候选方案，并迭代优化这些候选方案以提升性能。我们在多个基准上评估GENIUS，并与现有最先进的NAS技术进行比较，以展示其有效性。我们的目标并非追求最先进的性能，而是通过一个需要相对有限领域专业知识的简单提示方案，突显GPT-4在解决具有挑战性的技术问题中辅助研究的潜力\footnote{代码见\href{https://github.com/mingkai-zheng/GENIUS}{https://github.com/mingkai-zheng/GENIUS}。}。更广泛而言，我们认为初步结果指向了未来利用通用语言模型完成多样化优化任务的研究方向。同时，我们强调本研究的局限性，并指出对人工智能安全的影响。