How Can Large Language Models Help Humans in Design And Manufacturing? Part 1: Elements of The LLM-Enabled Computational Design and Manufacturing Pipeline

Abstract

The advancement of Large Language Models (LLMs), including GPT-4, provides exciting new opportunities for generative design. We investigate the application of this tool through sequential steps of the computational design and manufacturing workflow. In particular, we examine how LLMs can aid in tasks including: converting a text-based prompt into a quantitative design specification, transforming a design into manufacturing instructions, producing a design space and variations within that space, computing the performance of a given design, and optimizing for designs predicated on performance goals. Through a series of examples, we highlight overarching capabilities and limitations of the current LLMs. By exposing these aspects, we aspire to catalyze the continued improvement and progression of these models, providing a roadmap to build on their strengths and reduce their weaknesses.

https://hdsr.mitpress.mit.edu/pub/15nqmdzl/release/1