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

Ever since the launch of ChatGPT in 2022, a rising concern is whether ChatGPTwill replace programmers and kill jobs. Motivated by this widespread concern,we conducted an empirical study to systematically compare ChatGPT againstprogrammers in question-answering and software-maintaining. We reused a datasetintroduced by prior work, which includes 130 StackOverflow (SO) discussionthreads referred to by the Java developers of 357 GitHub projects. We mainlyinvestigated three research questions (RQs). First, how does ChatGPT comparewith programmers when answering technical questions? Second, how do developersperceive the differences between ChatGPT's answers and SO answers? Third, howdoes ChatGPT compare with humans when revising code for maintenance requests?  For RQ1, we provided the 130 SO questions to ChatGPT, and manually comparedChatGPT answers with the accepted/most popular SO answers in terms ofrelevance, readability, informativeness, comprehensiveness, and reusability.For RQ2, we conducted a user study with 30 developers, asking each developer toassess and compare 10 pairs of answers, without knowing the information source(i.e., ChatGPT or SO). For RQ3, we distilled 48 software maintenance tasks from48 GitHub projects citing the studied SO threads. We queried ChatGPT to revisea given Java file, and to incorporate the code implementation for anyprescribed maintenance requirement. Our study reveals interesting phenomena:For the majority of SO questions (97/130), ChatGPT provided better answers; in203 of 300 ratings, developers preferred ChatGPT answers to SO answers; ChatGPTrevised code correctly for 22 of the 48 tasks. Our research will expandpeople's knowledge of ChatGPT capabilities, and shed light on future adoptionof ChatGPT by the software industry.

An empirical study of ChatGPT-3.5 on question answering and code maintenance