Comparative Analysis of Carbon Footprint in Manual vs. LLM-Assisted Code Development

TL;DR

This paper compares the environmental impact of manual versus LLM-assisted software development, finding that LLM assistance increases carbon footprint by approximately 33%, with complexity influencing the difference.

Contribution

It provides a quantitative comparison of energy consumption between manual and LLM-assisted coding, highlighting environmental implications and factors affecting carbon footprint.

Findings

LLM-assisted coding results in 32.72 times higher carbon footprint than manual coding.

Task complexity significantly correlates with the difference in environmental impact.

The study offers strategies to reduce the carbon footprint of AI-assisted software development.

Abstract

Large Language Models (LLM) have significantly transformed various domains, including software development. These models assist programmers in generating code, potentially increasing productivity and efficiency. However, the environmental impact of utilising these AI models is substantial, given their high energy consumption during both training and inference stages. This research aims to compare the energy consumption of manual software development versus an LLM-assisted approach, using Codeforces as a simulation platform for software development. The goal is to quantify the environmental impact and propose strategies for minimising the carbon footprint of using LLM in software development. Our results show that the LLM-assisted code generation leads on average to 32.72 higher carbon footprint than the manual one. Moreover, there is a significant correlation between task complexity and the difference in the carbon footprint of the two approaches.