Controlling Context: Generative AI at Work in Integrated Circuit Design and Other High-Precision Domains

TL;DR

This paper investigates how engineers in high-precision fields like integrated circuit design use generative AI tools, emphasizing the importance of controlling interaction context to mitigate errors and improve reliability.

Contribution

It identifies context control as a key challenge in using generative AI for high-precision engineering and offers recommendations to enhance interaction management.

Findings

Context control is a major challenge in AI-assisted engineering workflows.

Errors and trouble in AI use are linked to interaction context issues.

Interactive control of AI context can mitigate potential errors.

Abstract

Generative AI tools have become more prevalent in engineering workflows, particularly through chatbots and code assistants. As the perceived accuracy of these tools improves, questions arise about whether and how those who work in high-precision domains might maintain vigilance for errors, and what other aspects of using such tools might trouble their work. This paper analyzes interviews with hardware and software engineers, and their collaborators, who work in integrated circuit design to identify the role accuracy plays in their use of generative AI tools and what other forms of trouble they face in using such tools. The paper inventories these forms of trouble, which are then mapped to elements of generative AI systems, to conclude that controlling the context of interactions between engineers and the generative AI tools is one of the largest challenges they face. The paper concludes with recommendations for mitigating this form of trouble by increasing the ability to control context interactively.