From Words to Wires: Generating Functioning Electronic Devices from Natural Language Descriptions
This work addresses the challenge of automating electronic circuit design for engineers and hobbyists, representing a novel application of NLP but with incremental improvements in existing methods.
The paper tackles the problem of generating functioning electronic devices from natural language descriptions using language models, achieving between 60% to 96% Pass@1 on benchmarks for designing circuits and code in the Arduino ecosystem.
In this work, we show that contemporary language models have a previously unknown skill -- the capacity for electronic circuit design from high-level textual descriptions, akin to code generation. We introduce two benchmarks: Pins100, assessing model knowledge of electrical components, and Micro25, evaluating a model's capability to design common microcontroller circuits and code in the Arduino ecosystem that involve input, output, sensors, motors, protocols, and logic -- with models such as GPT-4 and Claude-V1 achieving between 60% to 96% Pass@1 on generating full devices. We include six case studies of using language models as a design assistant for moderately complex devices, such as a radiation-powered random number generator, an emoji keyboard, a visible spectrometer, and several assistive devices, while offering a qualitative analysis performance, outlining evaluation challenges, and suggesting areas of development to improve complex circuit design and practical utility. With this work, we aim to spur research at the juncture of natural language processing and electronic design.