Code Smarter, Not Harder: Uncovering the Energy Footprint of LLM-Generated Code

Organisatsiooni nimi
Software Engineering Analytics
Kokkuvõte
While Large Language Models (LLMs) transform how code is generated, their environmental impact remains unexplored. This thesis dives into the energy efficiency of LLM-generated code compared to traditional human-written code. By profiling and measuring CPU, memory, and power consumption during execution in a specific context(s), we aim to identify inefficiencies in AI-generated code and highlight areas for optimization. We seek to bridge the gap between code automation and sustainable software development, offering insights into how LLMs can speed up coding and make it greener. The exact details of the thesis topic depend on the student's previous knowledge and interests.
Lõputöö kaitsmise aasta
2024-2025
Juhendaja
Hina Anwar
Suhtlemiskeel(ed)
inglise keel
Nõuded kandideerijale
Tase
Magister
Märksõnad
#SEA, #Software_Quality, #GreenAI, #Sustainable_Software, #Green_Software

Kandideerimise kontakt

 
Nimi
Hina Anwar
Tel
E-mail
hina.anwar@ut.ee