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

2025-05-07

AI Summary

This study addresses the unquantified environmental impact of large language model (LLM)-assisted programming compared to traditional human coding. Method: We conduct the first empirical carbon footprint assessment using real-world Codeforces programming tasks, establishing a rigorous quantification framework integrating energy consumption monitoring, behavioral logging, computational complexity modeling, and carbon accounting—incorporating power usage effectiveness (PUE), GPU power draw, and regional grid emission factors. Results: LLM-assisted coding incurs, on average, 32.72× higher carbon emissions than manual coding; critically, emission overhead scales significantly with task complexity. The work pioneers the identification of AI coding’s hidden environmental cost, introduces a reproducible benchmark for green software engineering evaluation, and proposes a systematic optimization pathway toward low-carbon AI development—thereby providing foundational evidence and methodological support for sustainable AI engineering practice.

Technology Category

• Machine Learning: Efficient ML / Green AI
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Humans and AI: Other Foundations of Human Computation & AI

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

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.

Problem

• Compare carbon footprint of manual vs LLM-assisted code development
• Quantify environmental impact of LLM use in software development
• Analyze correlation between task complexity and carbon footprint difference

Innovation

• Compare manual and LLM-assisted code carbon footprints
• Use Codeforces as software development simulation platform
• Quantify and minimize LLM carbon footprint impact