English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Context: AI-assisted code generation tools have become increasingly prevalentin software engineering, offering the ability to generate code from naturallanguage prompts or partial code inputs. Notable examples of these toolsinclude GitHub Copilot, Amazon CodeWhisperer, and OpenAI's ChatGPT.  Objective: This study aims to compare the performance of these prominent codegeneration tools in terms of code quality metrics, such as Code Validity, CodeCorrectness, Code Security, Code Reliability, and Code Maintainability, toidentify their strengths and shortcomings.  Method: We assess the code generation capabilities of GitHub Copilot, AmazonCodeWhisperer, and ChatGPT using the benchmark HumanEval Dataset. The generatedcode is then evaluated based on the proposed code quality metrics.  Results: Our analysis reveals that the latest versions of ChatGPT, GitHubCopilot, and Amazon CodeWhisperer generate correct code 65.2%, 46.3%, and 31.1%of the time, respectively. In comparison, the newer versions of GitHub CoPilotand Amazon CodeWhisperer showed improvement rates of 18% for GitHub Copilot and7% for Amazon CodeWhisperer. The average technical debt, considering codesmells, was found to be 8.9 minutes for ChatGPT, 9.1 minutes for GitHubCopilot, and 5.6 minutes for Amazon CodeWhisperer.  Conclusions: This study highlights the strengths and weaknesses of some ofthe most popular code generation tools, providing valuable insights forpractitioners. By comparing these generators, our results may assistpractitioners in selecting the optimal tool for specific tasks, enhancing theirdecision-making process.

Evaluating the Code Quality of AI-Assisted Code Generation Tools: An Empirical Study on GitHub Copilot, Amazon CodeWhisperer, and ChatGPT