From Words to Wires: Generating Functioning Electronic Devices from Natural Language Descriptions

TL;DR

This paper demonstrates that advanced language models can generate functional electronic circuits from textual descriptions, introducing benchmarks and case studies to evaluate and enhance this emerging capability.

Contribution

It introduces two new benchmarks for evaluating circuit design from language models and provides empirical evidence of their ability to generate complex electronic devices.

Findings

Models like GPT-4 achieve 60-96% Pass@1 on benchmarks.

Six case studies showcase practical applications of language models in circuit design.

Analysis highlights challenges and future directions for improving model utility.

Abstract

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.