AI-Driven Development Is Here: Should You Worry?
Open accessThe DOI matches its Crossref record; 8 of the 8 references it cites were found in a registry or an index.
Abstract
Artificial Intelligence Driven Development Environments (AIDEs) integrate the power of modern AI into IDEs like Visual Studio Code and JetBrains IntelliJ. By leveraging massive language models and the plethora of openly available source code, AIDEs promise to automate many of the obvious, routine tasks in programming. At the same time, AIDEs come with new challenges to think about, such as bias, legal compliance, security vulnerabilities, and their impact on learn programming.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“Our participants acknowledged that such over-reliance could hinder their own learning, a concern that has also been expressed by computing educators [32].”
From “It’s Weird That it Knows What I Want”: Usability and Interactions with Copilot for Novice Programmers (2024) · cites this paper as [32]
The cited source says what the claim attributes to it.
In the citing paper
“AI-assisted development tools (AIDTS), such as GitHub Copilot, are transforming the way software is developed by offering real-time code suggestions [2].”
From How do Copilot Suggestions Impact Developers' Frustration and Productivity? (2025) · cites this paper as [2]
The check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“While a number of researchers have looked at how current developers may use LLM-based tools [32,52,81] and how LLM-tools may be incorporated into professional software development tools [84], the participants in these studies have been programmers who learned to code initially without using LLMs.”
From The Robots Are Here: Navigating the Generative AI Revolution in Computing Education (2023) · cites this paper as [84]
Experimental — accuracy not yet measuredThe check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“Ehsan et al. [ 22 ] discovered that users' perceptions and needs in AI are situated in a social, collaborative setting.”
From "It would work for me too": How Online Communities Shape Software Developers' Trust in AI-Powered Code Generation Tools (2024) · cites this paper as [22]
Experimental — accuracy not yet measuredIn the citing paper
“The initial iteration of ChatGPT referred to as GPT-1, was equipped with 117 million parameters and underwent training on a substantial corpus of text data Ernst & Bavota (2022).”
From Decoding ChatGPT: A taxonomy of existing research, current challenges, and possible future directions (2023) · cites this paper as Ernst & Bavota (2022)
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Evaluating Large Language Models Trained on Code
Chen, M., Tworek, J., Jun, H., Yuan, Q., Pinto, H. P. D. O., Kaplan, J., Edwards, H., Burda, Y., Joseph, N., Brockman, G., et al. (2021) · arXiv · doi:10.48550/arxiv.2107.03374 · Cited by 1,436
The promises and perils of mining GitHub
Kalliamvakou, E., Gousios, G., Blincoe, K., Singer, L., German, D. M., & Damian, D. (2014) · Proceedings of the 11th Working Conference on Mining Software Repositories · doi:10.1145/2597073.2597074 · Cited by 770
Evaluating large language models trained on code
Chen, M. (2024) · TIB Data Manager · doi:10.57702/wbv3e61b · Cited by 737
On the naturalness of software
Hindle, A., Barr, E. T., Su, Z., Gabel, M., & Devanbu, P. (2012) · 2012 34th International Conference on Software Engineering (ICSE) · doi:10.1109/icse.2012.6227135 · Cited by 425 · cited 2×
“Codex is the product of: • AI research into deep neural networks and language models; • Software repository mining for extracting data from repositories; • Investigations into the linguistic nature of source code [Hindle et al., 2012]; • Massive amounts of compute and data storage.”
BackgroundOn the naturalness of software
Hindle, A., Barr, E. T., Gabel, M., Su, Z., & Devanbu, P. (2016) · Communications of the ACM · doi:10.1145/2902362 · Cited by 307
From Start-ups to Scale-ups: Opportunities and Open Problems for Static and Dynamic Program Analysis
Harman, M., & O'Hearn, P. (2018) · 2018 IEEE 18th International Working Conference on Source Code Analysis and Manipulation (SCAM) · doi:10.1109/scam.2018.00009 · Cited by 151 · cited 1×
“When Facebook rolled out their automated bug repair approach, one of the biggest challenges was not the technical problem, but rather integrating the repair bot into the humans that worked with them [Harman and O'Hearn, 2018].”
BackgroundSapFix: Automated End-to-End Repair at Scale
Marginean, A., Bader, J., Chandra, S., Harman, M., Jia, Y., Mao, K., Mols, A., & Scott, A. (2019) · 2019 IEEE/ACM 41st International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP) · doi:10.1109/icse-seip.2019.00039 · Cited by 137 · cited 2×
“Intelligent fill in spreadsheets is a close companion, as is program repair such as Facebook’s SapFix [Marginean et al., 2019].”
BackgroundMethodYou Autocomplete Me: Poisoning Vulnerabilities in Neural Code Completion
Schuster, R., Song, C., Tromer, E., & Shmatikov, V. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.02220 · Cited by 61 · cited 2×
“Subtle security holes can easily persist even in high-quality, high-volume repositories (consider the OpenSSH Heartbleed incident), and recent work showed how deep learning models can learn vulnerable code and inject it during autocompletion [Schuster et al., 2020].”
Background
Research works printed but not linked: 3
- snowden, 2020, Cynefin - Weaving sense-making into the fabric of our world
- ziegler, 2021, GitHub Copilot Parrot or crow? a first look at rote learning in GitHub Copilot suggestions
- romero, 2021, GPT-4 will have 100 trillion parameters—500x the size of GPT-3
Cited by
The Robots Are Here: Navigating the Generative AI Revolution in Computing Education
Prather, J., Denny, P., Leinonen, J., Becker, B. A., Albluwi, I., Craig, M., Keuning, H., Kiesler, N., Kohn, T., Luxton-Reilly, A., et al. (2023) · Proceedings of the 2023 Working Group Reports on Innovation and Technology in Computer Science Education · doi:10.1145/3623762.3633499 · Cited by 396
“2 Position papers and surveys/interviews (17): Twelve papers were surveys or position papers, summarising or discussing research conducted by others [24, 34, 50, 72, 80, 87, 102, 124, 139, 154, 183, 185].”
BackgroundDenny, P., Kumar, V., & Giacaman, N. (2023) · Proceedings of the 54th ACM Technical Symposium on Computer Science Education V. 1 · doi:10.1145/3545945.3569823 · Cited by 287
“Just how students will embrace and make use of tools like Copilot is unclear [10], but it seems certain they will play an increasing role inside and outside the classroom.”
BackgroundPrather, J., Reeves, B. N., Denny, P., Becker, B. A., Leinonen, J., Luxton-Reilly, A., Powell, G., Finnie-Ansley, J., & Santos, E. A. (2024) · ACM Transactions on Computer-Human Interaction · doi:10.1145/3617367 · Cited by 256
“Our participants acknowledged that such over-reliance could hinder their own learning, a concern that has also been expressed by computing educators [32].”
BackgroundOn the Robustness of Code Generation Techniques: An Empirical Study on GitHub Copilot
Mastropaolo, A., Pascarella, L., Guglielmi, E., Ciniselli, M., Scalabrino, S., Oliveto, R., & Bavota, G. (2023) · 2023 IEEE/ACM 45th International Conference on Software Engineering (ICSE) · doi:10.1109/icse48619.2023.00181 · Cited by 138
“This new generation of code recommender systems has the potential to change the way in which developers write code [18] and comes with a number of questions concerning how to effectively exploit them to maximize developers’ productivity.”
Self-citationNavigating the Complexity of Generative AI Adoption in Software Engineering
Russo, D. (2024) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3652154 · Cited by 217
“Ernst and Bavota [28], although also discussing the complexities of AI integration, differ by highlighting additional challenges related to legal compliance and bias.”
BackgroundAssessing the quality of GitHub copilot’s code generation
Yetistiren, B., Ozsoy, I., & Tuzun, E. (2022) · Proceedings of the 18th International Conference on Predictive Models and Data Analytics in Software Engineering · doi:10.1145/3558489.3559072 · Cited by 143
“GitHub Copilot generates the code and presents the results of the OpenAI Codex Model by adjusting the generated code to the current workspace of the programmer [4].”
MethodSohail, S. S., Farhat, F., Himeur, Y., Nadeem, M., Madsen, D. Ø., Singh, Y., Atalla, S., & Mansoor, W. (2023) · Journal of King Saud University - Computer and Information Sciences · doi:10.1016/j.jksuci.2023.101675 · Cited by 192
How Effective Are Neural Networks for Fixing Security Vulnerabilities
Wu, Y., Jiang, N., Pham, H. V., Lutellier, T., Davis, J., Tan, L., Babkin, P., & Shah, S. (2023) · Proceedings of the 32nd ACM SIGSOFT International Symposium on Software Testing and Analysis · doi:10.1145/3597926.3598135 · Cited by 100
“Much work also discusses the implication of LLMs for software developers [23, 27, 51] and current limitations of LLMs [9, 20, 68].”
BackgroundTaking Flight with Copilot: Early insights and opportunities of AI-powered pair-programming tools
Bird, C., Ford, D., Zimmermann, T., Forsgren, N., Kalliamvakou, E., Lowdermilk, T., & Gazit, I. (2022) · Queue · doi:10.1145/3582083 · Cited by 158
“If you are interested in reading more about the topic, there are some recent papers and studies, organized in two main categories: (1) how programmers are using Copilot; and (2) the effectiveness of Copilot.”
BackgroundAI-driven innovations in software engineering: a review of current practices and future directions
Alenezi, M., & Akour, M. (2025) · Applied Sciences · doi:10.3390/app15031344 · Cited by 121
Generative AI in Education: A Study of Educators' Awareness, Sentiments, and Influencing Factors
Ghimire, A., Pather, J., & Edwards, J. (2024) · 2024 IEEE Frontiers in Education Conference (FIE) · doi:10.1109/fie61694.2024.10892891 · Cited by 88
Investigating and Designing for Trust in AI-powered Code Generation Tools
Wang, R., Cheng, R., Ford, D., & Zimmermann, T. (2024) · The 2024 ACM Conference on Fairness, Accountability, and Transparency · doi:10.1145/3630106.3658984 · Cited by 87
“A review paper highlights that trust in AI is subjective and should be studied as an attitude [56], distinguishing from reliance or compliance, which are often studied as a behavior [54].”
BackgroundCopiloting the future: How generative AI transforms Software Engineering
Banh, L., Holldack, F., & Strobel, G. (2025) · Information and Software Technology · doi:10.1016/j.infsof.2025.107751 · Cited by 67
DreamCodeVR: Towards Democratizing Behavior Design in Virtual Reality with Speech-Driven Programming
Giunchi, D., Numan, N., Gatti, E., & Steed, A. J. (2024) · IEEE Conference on Virtual Reality and 3D User Interfaces (VR) · doi:10.1109/vr58804.2024.00078 · Cited by 77
“Consequently, numerous commercial and open-source LLM-based code generation tools are now available [25, 32].”
Bird, C., Ford, D., Zimmermann, T., Forsgren, N., Kalliamvakou, E., Lowdermilk, T., & Gazit, I. (2023) · Communications of the ACM · doi:10.1145/3589996 · Cited by 40
Cheng, R., Wang, R., Zimmermann, T., & Ford, D. (2024) · ACM Transactions on Interactive Intelligent Systems · doi:10.1145/3651990 · Cited by 47
“These tools have been considered revolutionary for the workflow of software developers that is long considered complex and highly demanding [21, 44], as they are designed to augment developers’ productivity by auto-completing lines of”
MethodHuman-Written vs. AI-Generated Code: A Large-Scale Study of Defects, Vulnerabilities, and Complexity
Cotroneo, D., Improta, C., & Liguori, P. (2025) · Proceedings/Proceedings - International Symposium on Software Reliability Engineering · doi:10.1109/issre66568.2025.00035 · Cited by 62
“The emergence of AI-assisted programming has triggered a paradigm shift in software engineering, redefining not only how code is written but also who , or rather what , is writing it [1].”
Lost at C: A User Study on the Security Implications of Large Language Model Code Assistants
Sandoval, G., Pearce, H., Nys, T., Karri, R., Garg, S., & Dolan-Gavitt, B. (2022) · arXiv · doi:10.48550/arxiv.2208.09727 · Cited by 52
Generative AI for Test Driven Development: Preliminary Results
Mock, M., Melegati, J., & Russo, B. (2025) · Lecture notes in business information processing · doi:10.1007/978-3-031-72781-8_3 · Cited by 31
Assessing the Readability of ChatGPT Code Snippet Recommendations: A Comparative Study
Dantas, C., Rocha, A. M., & Maia, M. D. A. (2023) · Brazilian Symposium on Software Engineering · doi:10.1145/3613372.3613413 · Cited by 34
“One such tool is GitHub Copilot, which utilizes the OpenAI Codex Model to generate code and adapt the generated code to the programmer’s current workspace [11].”
MethodThe Fault in our Stars: Quality Assessment of Code Generation Benchmarks
Siddiq, M. L., Dristi, S., Saha, J., & Santos, J. C. S. (2024) · IEEE International Working Conference on Source Code Analysis and Manipulation (SCAM) · doi:10.1109/scam63643.2024.00028 · Cited by 44
“Memorization refers to a model’s ability to preserve and A type 1 clone occurs when two code snippets have identical A type 2 clone arises when there are syntactically A type 3 clone means that there are”
Insights from the Frontline: GenAI Utilization Among Software Engineering Students
Choudhuri, R., Ramakrishnan, A., Chatterjee, A., Trinkenreich, B., Steinmacher, I., Gerosa, M. A., & Sarma, A. (2025) · IEEE International Conference on Software Engineering Education and Training (CSEE&T) · doi:10.1109/cseet66350.2025.00007 · Cited by 38
“How students should adopt genAI tools remains unclear [44], but their increasing role inside and outside the classroom seems certain.”
Shormani, M. Q. (2025) · Artificial Intelligence Review · doi:10.1007/s10462-025-11332-5 · Cited by 20
“Its first version is GPT-1, having 117 million parameters, and has been trained on massive amounts of data (Ernst and Bavota 2022; Sohail et al. 2023).”
Hliš, T., Četina, L., Beranič, T., & Pavlič, L. (2023) · Applied Sciences · doi:10.3390/app132413061 · Cited by 23
“These assistants outperform traditional ones by using machine learning to detect patterns in extensive source code databases [4].”
BackgroundStudents' Perspectives on AI Code Completion: Benefits and Challenges
Takerngsaksiri, W., Warusavitarne, C., Yaacoub, C., Keng Hou, M. H., & Tantithamthavorn, C. (2024) · 2024 IEEE 48th Annual Computers, Software, and Applications Conference (COMPSAC) · doi:10.1109/compsac61105.2024.00252 · Cited by 18
“Ernst and Bavota [7].”
BackgroundTrust Dynamics in AI-Assisted Development: Definitions, Factors, and Implications
Sabouri, S., Eibl, P., Zhou, X., Ziyadi, M., Medvidović, N., Lindemann, L., & Chattopadhyay, S. (2025) · ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion) · doi:10.1109/icse55347.2025.00199 · Cited by 33
“Nonetheless, generating production-quality code suggestions for complex software systems remains a difficult task, especially in fast-paced and stressful work environments [16], [17].”
Student's Use of Generative AI as a Support Tool in an Advanced Web Development Course
Alpizar-Chacón, I., & Keuning, H. (2025) · ACM Conference on Innovation and Technology in Computer Science Education (ITiCSE) · doi:10.1145/3724363.3729106 · Cited by 24
Quality In, Quality Out: Investigating Training Data's Role in AI Code Generation
Improta, C., Tufano, R., Liguori, P., Cotroneo, D., & Bavota, G. (2025) · IEEE International Conference on Program Comprehension (ICPC) · doi:10.1109/icpc66645.2025.00056 · Cited by 21
“AI-assisted software development is nowadays a reality [1].”
Self-citationManaging expectations towards AI tools for software development: a multiple-case study
Jensen, V. V., Alami, A., Bruun, A., & Persson, J. S. (2025) · Information Systems and e-Business Management · doi:10.1007/s10257-025-00704-7 · Cited by 20
“Similar challenges have been described in other research (Kruse et al. 2019; Ernst and Bavota 2022).”
State of the Art of the Security of Code Generated by LLMs: A Systematic Literature Review
Ramírez, L. C., Limón, X., Sánchez-García, Á. J., & Pérez-Arriaga, J. C. (2024) · International Conference in Software Engineering Research and Innovation (CONISOFT) · doi:10.1109/conisoft63288.2024.00050 · Cited by 30
Kohn, T. (2025) · Journal of Computer Assisted Learning · doi:10.1111/jcal.70043 · Cited by 15
INSPECT: Intrinsic and Systematic Probing Evaluation for Code Transformers
Karmakar, A., & Robbes, R. (2023) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2023.3341624 · Cited by 15
“More generally, the increasing availability of these AI-based development tools has triggered discussions of their promises and concerns [14].”
BackgroundExploring AI Integration in Software Development: Case Studies and Insights
Udoidiok, I., Reza, H., & Zhang, J. (2024) · IEEE National Aerospace and Electronics Conference (NAECON) · doi:10.1109/naecon61878.2024.10670347 · Cited by 10
“…users in debugging code, diagnosing issues, and understanding error messages by providing guidance on possible causes and suggesting solutions to fix the problem. in [12], AIDEs promise to automate routine tasks in programming by leveraging massive language models and openly available source code.”
BackgroundPwnPilot: Reflections on Trusting Trust in the Age of Large Language Models and AI Code Assistants
Horne, D. (2023) · Congress in Computer Science, Computer Engineering, and Applied Computing (CSCE) · doi:10.1109/csce60160.2023.00396 · Cited by 15
“Despite the significant potential, there are also downsides and risks to consider, particularly when adopting generative AI technologies like AI code assistants in a corporate/commercial environment [7].”
BackgroundThe Robots are Here: Navigating the Generative AI Revolution in Computing Education
Prather, J., Denny, P., Leinonen, J., Becker, B. A., Albluwi, I., Craig, M., Keuning, H., Kiesler, N., Kohn, T., Luxton-Reilly, A., et al. (2023) · arXiv · doi:10.48550/arxiv.2310.00658 · Cited by 9
“2 Position papers and surveys/interviews (17): Twelve papers were surveys or position papers, summarising or discussing research conducted by others [24, 34, 50, 72, 80, 87, 102, 124, 139, 154, 183, 185].”
BackgroundUma análise do uso de ferramentas de geração de código por alunos de computação
Lira, W. A. L., Neto, P. D. A. D. S., & Osório, L. F. M. (2024) · doi:10.5753/educomp.2024.237427 · Cited by 10
“Pesquisadores exploraram: automação de tarefas rotineiras [6], aumento da pro-dutividade percebida [17] e ajuda no aprendizado de uma nova linguagem de programação [17] [6].”
BackgroundEarly Results from a Study of GenAI Adoption in a Large Brazilian Company: The Case of Globo
Pereira, G. V., Prikladnicki, R., Jackson, V., van der Hoek, A., Fortes, L., & Macaubas, I. (2024) · Springer eBooks · doi:10.1007/978-3-031-55642-5_13 · Cited by 8
On the Generalizability of Deep Learning-based Code Completion Across Programming Language Versions
Ciniselli, M., Martin-Lopez, A., & Bavota, G. (2024) · IEEE International Conference on Program Comprehension (ICPC) · doi:10.1145/3643916.3644411 · Cited by 9
Self-citationHyrynsalmi, S. M., Tuape, M., & Knutas, A. (2025) · ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE) · doi:10.1145/3696630.3727235 · Cited by 8
Architecting open, accountable, and trustworthy AI-IDEs
Contreras, A., Guerra, E., & de Lara, J. (2026) · Automated Software Engineering · doi:10.1007/s10515-026-00608-x · Cited by 5
What Developers Ask to ChatGPT in GitHub Pull Requests? an Exploratory Study
Silva, J. R., Dantas, C. E. C., & Maia, M. D. A. (2024) · doi:10.5753/vem.2024.3913 · Cited by 5
“For example, developers can ask ChatGPT for code to solve a specific programming task or provide a detailed explanation of some concept [Ernst and Bavota 2022].”
Investigating the Role of Machine Leaning and Blockchain for Forecasting Stock Market Trends
Dhakar, R. J. D. S. (2024) · Journal of Electrical Systems · doi:10.52783/jes.1569 · Cited by 4
Case Study: Using Artificial Intelligence as a Tutor for a Programming Course
Timčenko, O. (2024) · International Conference on Information Technology Based Higher Education and Training (ITHET) · doi:10.1109/ithet61869.2024.10837624 · Cited by 4
“Already in March 2022, [1] was presented on a conference, discussing potential advantages and disadvantages of such platforms in education.”
(2025) · Issues in Information Systems · doi:10.48009/2_iis_127 · Cited by 3
Software Reuse in the Generative AI Era: From Cargo Cult Towards Systematic Practices
Mikkonen, T., & Taivalsaari, A. (2025) · Asia-Pacific Symposium on Internetware · doi:10.1145/3755881.3755981 · Cited by 3
“In general, such techniques help less experienced developers act like true professionals, albeit there are also identified downsides [7, 29].”
Who Pilots the Copilots? Mapping a Generative AI’s Actor-Network to Assess Its Educational Impacts
Balzan, F., Munarini, M., & Angeli, L. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-64299-9_42 · Cited by 8
Devadas, R. M., Hiremani, V., Praveen Gujjar, J., Preethi, P., & Sapna, R. (2024) · Advances in web technologies and engineering book series · doi:10.4018/979-8-3693-3703-5.ch005 · Cited by 3
Why Personalizing Deep Learning-Based Code Completion Tools Matters
Giagnorio, A., Martin-Lopez, A., & Bavota, G. (2025) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3725732 · Cited by 3
Self-citation“No Free Lunch” when using Large Language Models to Verify Self-Generated Programs
Zilberman, S., & Cheng, H. C. B. (2024) · IEEE International Conference on Software Testing, Verification and Validation Workshops (ICSTW) · doi:10.1109/icstw60967.2024.00018 · Cited by 4
“Recent advances in Artificial Intelligence (AI), specifically Large Language Models (LLMs), have led to techniques for automatically generating software, documentation, test cases, and other development artifacts [1].”
BackgroundHow do Copilot Suggestions Impact Developers' Frustration and Productivity?
Guglielmi, E., Arnoudova, V., Bavota, G., Oliveto, R., & Scalabrino, S. (2025) · arXiv · doi:10.48550/arxiv.2504.06808 · Cited by 1
“AI-assisted development tools (AIDT S ), such as GitHub Copilot, are transforming the way software is developed by offering real-time code suggestions [2].”
Self-citationCausal mapping of the risks of using generative AI in software development
Hein, D. K., Persson, J. S., Jensen, V. V., Bruun, A., & Jaatun, M. G. (2026) · Information and Software Technology · doi:10.1016/j.infsof.2026.108202 · Cited by 2
The Performance and Reliability of Generative AI Models in Software Development: A C# Based Analysis
Kaynarpınar, H., & Şeker, A. (2025) · MANAS Journal of Engineering · doi:10.51354/mjen.1784716 · Cited by 1
Fine-tuning LLMs for answer set programming
Coppolillo, E., Calimeri, F., Manco, G., Perri, S., & Ricca, F. (2026) · Journal of Intelligent Information Systems · doi:10.1007/s10844-025-01017-4 · Cited by 2
State of the Art of the Security of Code Generated by LLMs: A Multivocal Literature Review
Ramírez, L. C., Limón, X., Sanchéz-García, Á. J., & Pérez-Arriaga, J. C. (2025) · Programming and Computer Software · doi:10.1134/s0361768825700446 · Cited by 2
“• Outdated packages, APIs, and algorithms: Due to training data containing older or poorly maintained projects, LLMs often generate code using deprecated libraries or insecure APIs [22, 23].”
Fathahillah, Lestari, A., Yahya, M., Fardan, M., & Sari, P. N. (2026) · Journal of Vocational Informatics and Computer Education · doi:10.66053/voice.v4i2.990 · Cited by 1
“The development of Artificial Intelligence (AI) technology has brought revolutionary changes across various sectors, including the programming domain (Alenezi & Akour, 2025; Ernst & Bavota, 2022; Păvăloaia & Necula, 2023; Rashid & Kausik, 2024).”
VADER-SC: A Model Agnostic Tool for Large Scale, AI Driven Automated Source Code Summarization
Horne, D., Pierson, A., Hedary, E., Freddo, G., Trejo, L., Matis, M., & Mask, L. (2023) · Congress in Computer Science, Computer Engineering, and Applied Computing (CSCE) · doi:10.1109/csce60160.2023.00416 · Cited by 1
Colaboração com Assistente de Codificação Baseado em IA: Benefícios e Desafios
Mendes, W., Souza, S., & de Souza, C. R. B. (2024) · Simpósio Brasileiro de Sistemas Colaborativos (SBSC) · doi:10.5753/sbsc.2024.237964
Gorbatovski, A., Razin, A. D., Aliev, A., & Kovalchuk, S. V. (2024) · Scientific and technical journal of information technologies mechanics and optics · doi:10.17586/2226-1494-2024-24-6-1024-1034
Ceccucci, W., Peslak, A. R., & Jones, K. G. (2025) · Journal of Information Systems Applied Research and Analytics · doi:10.62273/oemc9700
The Effect of Generative AI on Creating Software Complements for Digital Platforms
Rochholz, D., & Beimborn, D. (2025) · Lecture notes in business information processing · doi:10.1007/978-3-032-04512-6_3
The Impact of Generative AI on Code Expertise Models: An Exploratory Study
Cury, O., & Avelino, G. A. (2025) · Simpósio Brasileiro de Engenharia de Software (SBES) · doi:10.5753/sbes.2025.11074
How Can Copilot Assist in Creating Accessible Websites? An Empirical Study
Teran, L. A., da Rocha, T. A., da Silva, I. M. M., de Salles, R. B., Melo, G. L. N., Mota, M. P., & de Souza, C. R. B. (2025) · Simpósio Brasileiro de Fatores Humanos em Sistemas Computacionais (IHC) · doi:10.5753/ihc.2025.10811
“Previews studies have focused on the advantages of the coding assistants (see for instance Bird et al. 2023, Ernst and Bavota 2022, and Liang et al. 2024).”
109PwnPilot: could an adversary be pair programming with our most trusted software engineers?
Horne, D. (2025) · De Gruyter eBooks · doi:10.1515/9783111436548-006
Dias Bahmed, B. M. (2024) · AMS Laurea Institutional Research Repository (University of Bologna) · Cited by 3
Tekoälyn käyttö pelinkehityksen tukena: kokemuksia pelialalta Suomessa
Krats, M. (2025) · Jyväskylä University Digital Archive (University of Jyväskylä)
AI Integration in Software Development : Current trends and future perspectives
Nasser Hameed, M., & Olsson, S. (2023) · DiVA - University of Borås (Högskolan i Borås)
Front Matter, Table of Contents, Preface, Conference Organization
Artale, A., Bienvenu, M., García, Y. I., & Murlak, F. (2025) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/oasics.rw.2024/2025.0
OASIcs, Volume 138, RW 2024 & RW 2025, Complete Volume
Artale, A., Bienvenu, M., García, Y. I., & Murlak, F. (2025) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/oasics.rw.2024/2025
The ILASP system for Inductive Learning of Answer Set ProgramsPreprint
Law, M., Russo, A. M., & Broda, K. B. (2020) · arXiv (Cornell University) · doi:10.4230/oasics.rw.2024/2025.8 · Cited by 72
“While numerous benchmarks assess LLMs on imperative and web-oriented languages (e.g., C++, Java, HTML)[31], attempts to systematically evaluate declarative paradigms like ASP remain relatively scarce [12, 43, 18].”
Software Design for Physical Rehabilitation in Patients with Musculoskeletal Injuries
Suarez-Sotelo, J., Guillen-Ladera, D., Marrujo-Ingunza, C., Ramos-Cosi, S., & Romero-Alva, V. N. (2026) · International Journal of Online and Biomedical Engineering (iJOE) · doi:10.3991/ijoe.v22i02.55573
Fudge, M. (2026) · Syracuse University Libraries (Syracuse University)
Caret: A conversational assistant for Java development within Eclipse
Contreras, A., Guerra, E., & de Lara, J. (2026) · SoftwareX · doi:10.1016/j.softx.2026.103076
TimeArch: A Multi-agent Approach for Software Architecture Design
Waseem, M., Abbasi, M. A., Järvinen, V., Lipsanen, P., Arora, N., Kulonen, K., Mäkelä, K., Mikkonen, T., & Abrahamsson, P. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-39236-7_39
Lightweight Language Models for Encoding ASP from Natural Language
Kareem, I., Borroto, M., Ricca, F., & Vitale, M. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-38320-4_18
BLAST: Benchmarking LLMs with ASP-Based Structured Testing
Borroto, M., Coppolillo, E., Calimeri, F., Manco, G., Perri, S., & Ricca, F. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-38320-4_8
"It's Weird That it Knows What I Want": Usability and Interactions with Copilot for Novice Programmers
Prather, J., Reeves, B. N., Denny, P., Becker, B. A., Leinonen, J., Luxton-Reilly, A., Powell, G., Finnie-Ansley, J., & Santos, E. A. (2023) · arXiv
“Our participants acknowledged that such over-reliance could hinder their own learning, a concern that has also been expressed by computing educators [32].”
Background
Metadata
- Authors
- Ernst, N. A., & Bavota, G.
- Affiliations
- University of Victoria (CA)
- Venue
- IEEE Software
- Published
- 2022-03
- Volume
- 39
- Issue
- 2
- Pages
- 106-110
- ISSN
- 0740-7459 (ISSN-L)
- 1937-4194
- OpenAlex
- W4213241976
- Cited by
- 62
- References
- 7
- Citations by year
- 2026: 6 · 2025: 21 · 2024: 20 · 2023: 13 · 2022: 2
- FWCI
- 13.87
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE Software (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University) (cc-by)
- Topics
- Physical Sciences › Computer Science › Information Systems › Software Engineering Research
- Physical Sciences › Computer Science › Information Systems › Software Engineering Techniques and Practices
- Physical Sciences › Computer Science › Artificial Intelligence › Artificial Intelligence Applications
- Keywords
- large language models, programming automation, Visual Studio Code, IntelliJ IDEA, algorithmic bias, legal compliance, security vulnerabilities, learning to program, developer productivity
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.