Assessing AI-Based Code Assistants in Method Generation Tasks
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909106170757120 |
|---|---|
| author | Corso, Vincenzo Mariani, Leonardo Micucci, Daniela Riganelli, Oliviero |
| author_facet | Corso, Vincenzo Mariani, Leonardo Micucci, Daniela Riganelli, Oliviero |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_09022 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Assessing AI-Based Code Assistants in Method Generation Tasks Corso, Vincenzo Mariani, Leonardo Micucci, Daniela Riganelli, Oliviero Software Engineering 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. |
| title | Assessing AI-Based Code Assistants in Method Generation Tasks |
| topic | Software Engineering |
| url | https://arxiv.org/abs/2402.09022 |