Vibe coding (alsovibecoding) is anAI-dependentprogramming technique where a person describes a problem in a few sentences as aprompt to a large language model (LLM) tuned for coding. The LLM generatessoftware, shifting the programmer's role from manual coding to guiding, testing, and refining the AI-generatedsource code.[1][2][3] Vibe coding is claimed by its advocates to allow evenamateur programmers to produce software without the extensive training and skills previously required forsoftware engineering.[4] The term was introduced byAndrej Karpathy in February 2025[5][2][4][1] and listed in theMerriam-Webster Dictionary the following month as a "slang & trending" noun.[6]
Computer scientistAndrej Karpathy, a co-founder ofOpenAI and former AI leader atTesla, introduced the termvibe coding in February 2025.[5][2][4][1] The concept refers to a coding approach that relies onLLMs, allowing programmers to generate working code by providing natural language descriptions rather than manually writing it.[1] Karpathy described his approach as conversational, using voice commands while AI generates the actual code.[2] "It's not really coding - I just see things, say things, run things, and copy-paste things, and it mostly works."[4] Karpathy acknowledged that vibe coding has limitations, noting that AI tools are not always able to fix or understand bugs, requiring him to experiment with unrelated changes until the problems are resolved.[2] He concluded that he found the technique "not too bad for throwaway weekend projects" and described it as "quite amusing."[5]
The concept of vibe coding elaborates on Karpathy's claim from 2023 that "the hottest newprogramming language is English", meaning that the capabilities of LLMs were such that humans would no longer need to learn specific programming languages to command computers.[7]
A key part of the definition of vibe coding is that the user accepts code without full understanding.[1] AI researcherSimon Willison said: "If an LLM wrote every line of your code, but you've reviewed, tested, and understood it all, that's not vibe coding in my book—that's using an LLM as a typing assistant."[1]
New York Times journalistKevin Roose, who is not a professional coder, experimented with vibe coding to create several small-scale applications.[3] He described these as "software for one", referring to personalised AI-generated tools designed to address specific individual needs, such as an app named LunchBox Buddy that analyzed his fridge contents to suggest items for a packed lunch.[3][7] Roose noted that while vibe coding enables non-programmers to generate functional software, the results are often limited and prone to errors.[3] In one case, the AI-generated code fabricated fake reviews for ane-commerce site.[3] He suggested that vibe coding is better suited for hobby projects rather than essential tasks.[3] He also observed that AI-assisted coding enables individuals to develop software that previously required an engineering team.[3] In response to Roose, AI expertGary Marcus said that the algorithm that generated Roose's LunchBox Buddy app had presumably been trained on existing code for similar tasks.[7] Marcus said that Roose's enthusiasm stemmed from reproduction, not originality.[7]
In February 2025,Business Insider described vibe coding as a new buzzword in Silicon Valley.[4]
In March 2025,Y Combinator reported that 25% of startups in its Winter 2025 batch had codebases that were 95% AI-generated, reflecting a shift toward AI-assisted development.[8]
Vibe coding has raised concerns about understanding and accountability. Developers may use AI-generated code without fully comprehending its functionality, leading to undetected bugs, errors, orsecurity vulnerabilities. While this approach may be suitable forprototyping or "throwaway weekend projects" as Karpathy originally envisioned, it is considered by some experts to pose risks in professional settings, where a deep understanding of the code is crucial fordebugging, maintenance, andsecurity.Ars Technica cites Simon Willison, who stated: "Vibe coding your way to a production codebase is clearly risky. Most of the work we do as software engineers involves evolving existing systems, where the quality and understandability of the underlying code is crucial."[1]In whatArs Technica described as an "ironic twist in the rise of 'vibe coding'", an AI coding assistant refused a programmer's request to generate code and responded with the text, "I cannot generate code for you, as that would be completing your work," and continued, "you should develop the logic yourself."[9]