REVIEW 5 cited by
Learn to Code Sustainably: An Empirical Study on LLM-based Green Code Generation
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
The increasing use of information technology has led to a significant share of energy consumption and carbon emissions from data centers. These contributions are expected to rise with the growing demand for big data analytics, increasing digitization, and the development of large artificial intelligence (AI) models. The need to address the environmental impact of software development has led to increased interest in green (sustainable) coding and claims that the use of AI models can lead to energy efficiency gains. Here, we provide an empirical study on green code and an overview of green coding practices, as well as metrics used to quantify the sustainability awareness of AI models. In this framework, we evaluate the sustainability of auto-generated code. The auto-generate codes considered in this study are produced by generative commercial AI language models, GitHub Copilot, OpenAI ChatGPT-3, and Amazon CodeWhisperer. Within our methodology, in order to quantify the sustainability awareness of these AI models, we propose a definition of the code's "green capacity", based on certain sustainability metrics. We compare the performance and green capacity of human-generated code and code generated by the three AI language models in response to easy-to-hard problem statements. Our findings shed light on the current capacity of AI models to contribute to sustainable software development.
Forward citations
Cited by 5 Pith papers
-
Beyond the Need for Speed: Energy-Aware Code Generation via Simulation-Guided Reinforcement Learning
Simulation-in-the-loop GRPO on energy-labeled C++ pairs yields 12.63% CARET and beats human energy efficiency on 58.4% of valid held-out outputs, while IPC misranks energy on 67.8% of problems.
-
From Chaos to Automation: Enabling the Use of Unstructured Data for Robotic Process Automation
A hybrid pipeline that layers fuzzy regex, NER, and an LLM lets RPA tools extract fields from unstructured invoices and resumes, but the evaluation is too small and in-sample to fully support the effectiveness claim.
-
Evaluating the Energy-Efficiency of the Code Generated by LLMs
LLM-generated Python solutions typically consume more energy than canonical human-written solutions, with DeepSeek-v3 and GPT-4o the most efficient LLMs and worst-case gaps near 450 times on certain problems.
-
AI-Powered, But Power-Hungry? Energy Efficiency of LLM-Generated Code
On a 53-problem LeetCode benchmark, LLM-generated Python code matches or beats human energy use, while LLM-generated C++ code uses much more energy and Java sits in between.
-
Energy-Aware Code Generation with LLMs: Benchmarking Small vs. Large Language Models for Sustainable AI Programming
On 150 LeetCode problems, GPT-4.0 and DeepSeek-Reasoner beat three 3B-parameter models on correctness and speed; the 52% energy-efficiency claim counts any of three SLMs on correct outputs, not a per-model advantage.
Discussion (0). Continue with ORCID to comment.