Prompt wording alone cut energy use of generated code by up to 25% in Python and 17% in C++ across 10 models. You can apply these strategies to coding agents without changing models.
Key takeaways · AI-distilled
The authors screened 21 prompting strategies for energy-efficient code, then tested 8 of them across 10 open weightsA model whose trained parameters are published for anyone to download and run — unlike API-only models you can access but never possess.Full definition → and proprietary LLMs on Python and C++ against a baseline prompt.
Across models, the selected prompts cut energy use of the generated code by up to 25% for Python and up to 17% for C++, measured relative to the baseline prompt.
Effects vary sharply by model and language: Python reductions reached 50% for Granite-4.0-H-Small and 39% for Claude 4.5 Haiku, while the best C++ result for Qwen3-Coder-480B was only 7%, so no single prompt is a universal fix.
Terms in this piece · Glossary
LLM — A large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.
open weights — A model whose trained parameters are published for anyone to download and run — unlike API-only models you can access but never possess.
articleDo Influence Tactics Matter? Investigating Prompt Framing Effects in LLM Code GenerationAlex Deaconu, Anubhav Gupta, Manaal Basha, Nicholas Haydu, Gema Rodr\'iguez-P\'erez
articleA Study on the Impact of Natural Language Differences in Prompts on Automatic Code Generation Using LLMsHaruka Tokumasu, Masanari Kondo, Alexander Serebrenik, Dong Wang, Kei Koyanagi, Kotaro Noguchi, Naoyasu Ubayashi, Yasutaka Kamei
articleHow Do Prompt Variations Affect Energy Consumption in On-Device LLMs?Wei Hu, Xiaolong Tu, Dawei Chen, Yitao Chen, Kyungtae Han, Haoxin Wang