Recent advances in large language models (LLMs) have given rise to vibe coding, a style of software development where developers rely on AI coding assistants to generate, modify, and refactor code using natural language instructions. While this paradigm accelerates software development and lowers barriers to entry, it introduces new challenges for quality assurance (QA). AI-generated code can appear correct but often contains hidden logical errors and inconsistencies, creating an urgent need for novel QA approaches. In this vision paper, we propose the VibeContract paradigm as a missing piece in vibe coding. In this approach, high-level natural-language intent is decomposed into explicit task sequences, and task-level contracts are generated to capture expected inputs, outputs, constraints, and behavioral properties. Developers validate these contracts, and traceability is maintained between tasks, contracts, and generated code. Contracts then guide LLMs for testing, runtime verification, and debugging, enabling QA to occur continuously and proactively alongside code generation. We demonstrate how the VibeContract paradigm can substantially improve the correctness, robustness, and
Large language models generate code from natural language prompts, enabling "vibe coding," which allows non-programmers to develop computational solutions. Vibe coding for teachers amplifies the value of teachers-as-designers, improving technology integration while fostering AI literacy. However, structured guidance on supporting this process is lacking. We propose GAIDE (A Guiding Framework for AI-Integrated Design for Educators), a framework that supports K-12 teachers in creating AI-powered learning technologies through vibe coding. The initial framework, built on Design Thinking and INTERACT, was validated through a CORDTRA interaction analysis of three teachers and four faculty mentors in an eight-week workshop to derive the final framework. Additionally, the qualitative analysis of pre- and post-interviews found an enhancement of teachers' AI literacy. Findings highlight the potential of learning-by-creating for professional development.
Clinicians often face workflow problems that are perceived as either too bespoke or low stakes to attract commercial attention. Historically, most do not have the technical knowledge to address these problems, but the recent emergence of "vibe coding" presents a transformative opportunity. Vibe coding refers to the co-development of software using natural language prompts to large language models. It offers a pathway to create simple tools that address these real-world pain points, or to prototype more complex ideas. In this review, written by a group of early adopter clinicians with a range of programming expertise, we introduce vibe coding for clinicians (especially those with no or minimal coding experience) as a way of democratising innovation from the front lines. We discuss foundational skills, outline some common challenges, provide a practical step-by-step playbook, and illustrate this approach with some case examples, taking care to consider caveats and guardrails for deployment. We propose that vibe coding is more than a technical shortcut for beginners and is not a replacement for professional software developers. Instead, it can bridge the gap between clinical insight a
Evaluating LLMs is challenging, as benchmark scores often fail to capture models' real-world usefulness. Instead, users often rely on ``vibe-testing'': informal experience-based evaluation, such as comparing models on coding tasks related to their own workflow. While prevalent, vibe-testing is often too ad hoc and unstructured to analyze or reproduce at scale. In this work, we study how vibe-testing works in practice and then formalize it to support systematic analysis. We first analyze two empirical resources: (1) a survey of user evaluation practices, and (2) a collection of in-the-wild model comparison reports from blogs and social media. Based on these resources, we formalize vibe-testing as a two-part process: users personalize both what they test and how they judge responses. We then introduce a proof-of-concept evaluation pipeline that follows this formulation by generating personalized prompts and comparing model outputs using user-aware subjective criteria. In experiments on coding benchmarks, we find that combining personalized prompts and user-aware evaluation can change which model is preferred, reflecting the role of vibe-testing in practice. These findings suggest tha
Writing code has been one of the most transformative ways for human societies to translate abstract ideas into tangible technologies. Modern AI is changing this process by enabling experts and non-experts alike to generate code without actually writing it, instead using natural language instructions or "vibe coding". While increasingly popular, the impact of vibe coding on productivity and collaboration, and the role of humans in this process, remains unclear. Here, we introduce a controlled experimental framework for studying collaborative vibe coding and use it to compare human-led, AI-led, and hybrid groups. Across 20 experiments involving 737 human participants, we show that people provide uniquely effective high-level instructions for vibe coding, whereas AI-provided instructions often result in performance collapse. We further demonstrate that hybrid systems perform best when humans lead by providing instructions while evaluation is delegated to AI. Although AI systems can rapidly optimize performance for specific tasks, our work highlights the importance of human guidance in shaping future hybrid societies.
In distributed Mixture-of-Experts (MoE) inference, input-dependent token routing interacts with GPU performance variability to create persistent stragglers under synchronized execution, where the slowest GPU determines layer latency. This performance variability is inherent to modern accelerators: manufacturing variation, power limits, and thermal conditions introduce measurable execution-time differences across nominally identical GPUs. The core challenge is that MoE execution-time imbalance arises from the interaction of workload skew and hardware asymmetry. Token routing produces uneven and layer-varying expert loads, while GPU throughput depends on device-specific operating characteristics and workload intensity. Prior work mitigates routing skew but assumes homogeneous hardware, optimizing token balance rather than execution latency. As a result, even balanced token assignments can leave hardware-induced stragglers unaddressed. Thus, we propose Variability-Informed Binning of Experts (ViBE), a hardware-aware expert placement framework that minimizes execution-time imbalance across GPUs. ViBE combines per-GPU performance modeling with expert activation profiling to assign high-
Rules files (e.g., AGENTSmd, CLAUDEmd) are the primary mechanism for human-agent alignment when developers vibe code. However, they remain passive: it is not immediately apparent when rules are being used or followed, or how to improve them. To transform rules from passive text into active controls, we introduce ZORO, an interactive interface that integrates directly with a coding agent and anchors rules to every step of the coding process. After an agent generates an initial plan, ZORO enriches the plan with rules, enforces the rules during implementation by requiring the agent prove that each rule was followed, and allows users to provide in-situ feedback when they are unsatisfied with a rule application to evolve the ruleset. A technical evaluation shows that coding agents follow rules more with ZORO than without. A user study demonstrates a change in people's behavior and cognitive strategies when rules are at the forefront of vibe coding. We discuss how making rules active in agentic systems unlocks broader opportunities for human-agent alignment in coding settings and beyond.
In this paper, we propose a robust real time detection and tracking method for detecting ships in a coastal video sequences. Since coastal scenarios are unpredictable and scenes have dynamic properties it is essential to apply detection methods that are robust to these conditions. This paper presents modified ViBe for moving object detection which detects ships and backwash. In the modified ViBe the probability of losing ships is decreased in comparison with the original ViBe. It is robust to natural sea waves and variation of lights and is capable of quickly updating the background. Based on geometrical properties of ship and some concepts such as brightness distortion, a new method for backwash cancellation is proposed. Experimental results demonstrate that the proposed strategy and methods have outstanding performance in ship detection and tracking. These results also illustrate real time and precise performance of the proposed strategy.
Recent advances in large language models (LLMs) have enabled vibe coding, an emerging software development paradigm in which users create applications primarily through natural-language interactions with AI agents. Due to its low barrier to entry, vibe coding is rapidly gaining adoption in practice. Unlike conventional AI-assisted programming, where developers remain responsible for implementation and code review, vibe coding delegates a substantial portion of development to AI systems. This shift raises a fundamental question: how (in)secure are applications developed through vibe coding? In this paper, we conduct a systematic study of the security of vibe-coded applications. We collect a large corpus of real-world applications developed using popular AI agents and design a vulnerability analysis framework that combines agent-assisted code auditing with human validation. Using this framework, we examine the prevalence, severity, and root causes of vulnerabilities in the deployed vibe-coded applications. Our study reveals several key findings: (1) vibe-coded applications exhibit recurring vulnerability patterns that differ from those commonly observed in conventional software devel
Thanks to rapid developments in generative AI, we are in the midst of a paradigm shift that may change how we interact with computers forever. We have observed a growth in the use of natural language prompts to build applications and coding infrastructures without underlying knowledge of the field, and this practice has been dubbed `vibe coding.' It arguably represents what the field of programming has been building towards since the beginning, with every higher level of abstraction that is conceived. Vibe coding promises to be the endpoint for the meta of high-level programming as far as method of input is concerned: eliminating a human's use of code syntax entirely in favour of programming in their mother tongue. This paper aims to evaluate the viability of vibe coding for greenfield software engineering tasks, as well as analyse the benchmarks that have been used to measure its software engineering prowess. To this end, we have developed an evaluation suite for analysing an LLM's proficiency in carrying out simple, isolated greenfield programming tasks in Python to provide scoped insight on the matter.
Vibe coding inherently assumes iterative refinement of LLM-generated code through feedback loops. While effective for conventional software tasks, its reliability in runtime-adaptive systems is unclear -- especially when generated code is not manually inspected. This paper studies feedback-based automated verification of LLM-generated adaptation managers in Collective Adaptive Systems (CAS). We focus on the key challenges of verification in the loop: how to detect failures of generated code at runtime and how to report them precisely enough for an LLM to fix them. We combine the adaptation loop with a vibe-coding feedback loop where correctness is checked against (i) generic architectural constraints and (ii) functional constraints formalized in Functional Constraints Logic (FCL), a novel first-order temporal logic over potentially finite traces. Conducting the Dragon Hunt CAS case study, we show that fine-grained constraint violations provide actionable feedback that typically yields a valid adaptation manager within a few iterations, while simple coarse metric-based feedback often stalls. Our findings suggest that feedback precision is the dominant factor for reliable vibe coding
Molecular Vibe Coding, a paradigm where chemists interact with LLMs to generate executable programs for molecular tasks, has emerged as a flexible alternative to chemical agents with predefined tools, enabling chemists to express arbitrarily complex, customized workflows. Unlike general coding tasks, molecular coding imposes a distinctive challenge that LLMs should jointly equip programming, molecular understanding, and domain-specific reasoning capabilities. However, existing benchmarks remain disconnected. General code generation benchmarks such as HumanEval and SWE-bench require no chemistry knowledge, while chemistry-focused benchmarks such as S^2-Bench and ChemCoTBench evaluate knowledge recall or property prediction rather than executable code generation. To bridge this gap, we introduce MolViBench, the first benchmark tailored for Molecular Vibe Coding. MolViBench comprises 358 curated tasks across five cognitive levels, ranging from single-API recall to end-to-end virtual screening pipeline design, spanning 12 real-world drug discovery workflows. To rigorously assess generated code, we also propose a multi-layered evaluation framework that combines type-aware output compari
Code generation has emerged as one of AI's highest-impact use cases, yet existing benchmarks measure isolated tasks rather than the complete "zero-to-one" process of building a working application from scratch. We introduce Vibe Code Bench, a benchmark of 100 web application specifications (50 private validation, 50 held-out test) with 964 browser-based workflows comprising 10,131 substeps, evaluated against deployed applications by an autonomous browser agent. Across 16 frontier models, the best achieves 61.8% accuracy on the test split, revealing that reliable end-to-end application development remains a frontier challenge. We identify self-testing during generation as a strong performance predictor (Pearson r=0.72), and show through a completed human alignment study that evaluator selection materially affects outcomes (31.8-93.6% pairwise step-level agreement). Our contributions include (1) a novel benchmark dataset and browser-based evaluation pipeline for end-to-end web application development, (2) a comprehensive evaluation of 16 frontier models with cost, latency, and error analysis, and (3) an evaluator alignment protocol with both cross-model and human annotation results.
Generative AI is changing how software is produced and used. In vibe coding, an AI agent builds software by selecting and assembling open-source software (OSS), often without users directly reading documentation, reporting bugs, or otherwise engaging with maintainers. We study the equilibrium effects of vibe coding on the OSS ecosystem. We develop a model with endogenous entry and heterogeneous project quality in which OSS is a scalable input into producing more software. Users choose whether to use OSS directly or through vibe coding. Vibe coding raises productivity by lowering the cost of using and building on existing code, but it also weakens the user engagement through which many maintainers earn returns. When OSS is monetized only through direct user engagement, greater adoption of vibe coding lowers entry and sharing, reduces the availability and quality of OSS, and reduces welfare despite higher productivity. Sustaining OSS at its current scale under widespread vibe coding requires major changes in how maintainers are paid.
While feminist and critical data theories have long critiqued the use of data to uphold a positivist-informed view about science, few examples offer alternative methods to display scientific constructs. In response, we present Data and Me: an exhibit informed by feminist and critical data theories, which we designed and launched at a local science museum. Data and Me introduces museum visitors to data using a [AT]:hugging_face: vibe -- a vibe that signals that data can be [hashtag]slow, [hashtag]handmade, and [hashtag]personal. We designed this vibe to be noticeably different than the [AT]Science vibe in the rest of the museum. Throughout our design process, we adapted visualization vibes as an analytic and generative tool in the context of a science museum. We present four design choices that enable the design of a vibe: visual, topical, material, and crediting. We discuss how our exhibit aligns with ongoing discussions about alternative research outcomes and calls for plurality in HCI.
Generative AI is known for its tendency to homogenize, often reproducing dominant style conventions found in training data. However, it remains unclear how these homogenizing effects extend to complex structural tasks like web design. As lay creators increasingly turn to LLMs to 'vibe-code' websites -- prompting for aesthetic and functional goals rather than writing code -- they may inadvertently narrow the diversity of their designs, and limit creative expression throughout the internet. In this paper, we interrogate the possibility of design homogenization in web vibe coding. We first characterize the vibe coding lifecycle, pinpointing stages where homogenization risks may arise. We then conduct a sociotechnical risk analysis unpacking the potential harms of web vibe coding and their interaction with design homogenization. We identify that the push for frictionless generation can exacerbate homogenization and its harms. Finally, we propose a mitigation framework centered on the idea of productive friction. Through case studies at the micro, meso, and macro levels, we show how centering productive friction can empower creators to challenge default outputs and preserve diverse expr
Recent generative models have achieved remarkable progress in image editing. However, existing systems and benchmarks remain largely text-guided. In contrast, human communication is inherently multimodal, where visual instructions such as sketches efficiently convey spatial and structural intent. To address this gap, we introduce VIBE, the Visual Instruction Benchmark for Image Editing with a three-level interaction hierarchy that captures deictic grounding, morphological manipulation, and causal reasoning. Across these levels, we curate high-quality and diverse test cases that reflect progressively increasing complexity in visual instruction following. We further propose a robust LMM-as-a-judge evaluation framework with task-specific metrics to enable scalable and fine-grained assessment. Through a comprehensive evaluation of 17 representative open-source and proprietary image editing models, we find that proprietary models exhibit early-stage visual instruction-following capabilities and consistently outperform open-source models. However, performance degrades markedly with increasing task difficulty even for the strongest systems, highlighting promising directions for future res
AI coding agents allow software developers to generate code quickly, which raises a practical question for project managers and open source maintainers: can vibe coders with less development experience substitute for expert developers? To explore whether developer experience still matters in AI-assisted development, we study $22,953$ Pull Requests (PRs) from $1,719$ vibe coders in the GitHub repositories of the AIDev dataset. We split vibe coders into lower experience vibe coders ($\mathit{Exp}_{Low}$) and higher experience vibe coders ($\mathit{Exp}_{High}$) and compare contribution magnitude and PR acceptance rates across PR categories. We find that $\mathit{Exp}_{Low}$ submits PRs with larger volume ($2.15\times$ more commits and $1.47\times$ more files changed) than $\mathit{Exp}_{High}$. Moreover, $\mathit{Exp}_{Low}$ PRs, when compared to $\mathit{Exp}_{High}$, receive $4.52\times$ more review comments, and have $31\%$ lower acceptance rates, and remain open $5.16\times$ longer before resolution. Our results indicate that low-experienced vibe coders focus on generating more code while shifting verification burden onto reviewers. For practice, project managers may not be able
Many software development platforms now support LLM-driven programming, or "vibe coding", a technique that allows one to specify programs in natural language and iterate from observed behavior, all without directly editing source code. While its adoption is accelerating, little is known about which skills best predict success in this workflow. We report a preregistered cross-sectional study with tertiary-level students (N = 100) who completed measures of computer-science achievement, domain-general cognitive skills, written-communication proficiency, and a vibe-coding assessment. Tasks were curated via an eight-expert consensus process and executed in a purpose-built, vibe-coding environment that mirrors commercial tools while enabling controlled evaluation. We find that both writing skill and CS achievement are significant predictors of vibe-coding performance, and that CS achievement remains a significant predictor after controlling for domain-general cognitive skills. The results may inform tool and curriculum design, including when to emphasize prompt-writing versus CS fundamentals to support future software creators.
When software artifacts are generated by AI models ("vibe coding"), human engineers assume responsibility for validating them. Ideally, this validation would be done through the creation of a formal proof of correctness. However, this is infeasible for many real-world vibe coding scenarios, especially when requirements for the AI-generated artifacts resist formalization. This extended abstract describes ongoing work towards the extraction of analyzable, semi-formal rationales for the adequacy of vibe-coded artifacts. Rather than deciding correctness directly, our framework produces a set of conditions under which the generated code can be considered adequate. We describe current efforts towards implementing our framework and anticipated research opportunities.