AI-based code assistants are increasingly popular as a means to enhance productivity and improve code quality. This study compares four AI-based code assistants, GitHub Copilot, Tabnine, ChatGPT, and Google Bard, in method generation tasks, assessing their ability to produce accurate, correct, and efficient code. Results show that code assistants are useful, with complementary capabilities, although they rarely generate ready-to-use correct code.
Corso, V., Mariani, L., Micucci, D., Riganelli, O. (2024). Assessing AI-Based Code Assistants in Method Generation Tasks. In Proceedings - International Conference on Software Engineering (pp.380-381). IEEE Computer Society [10.1145/3639478.3643122].
Assessing AI-Based Code Assistants in Method Generation Tasks
Corso V.;Mariani L.;Micucci D.;Riganelli O.
2024
Abstract
AI-based code assistants are increasingly popular as a means to enhance productivity and improve code quality. This study compares four AI-based code assistants, GitHub Copilot, Tabnine, ChatGPT, and Google Bard, in method generation tasks, assessing their ability to produce accurate, correct, and efficient code. Results show that code assistants are useful, with complementary capabilities, although they rarely generate ready-to-use correct code.
| File | Dimensione | Formato | |
|---|---|---|---|
|
Corso-2024-Proceedings - International Conference on Software Engineering-VoR.pdf
accesso aperto
Tipologia di allegato:
Publisher’s Version (Version of Record, VoR)
Licenza:
Creative Commons
Dimensione
399.66 kB
Formato
Adobe PDF
|
399.66 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
