Vibe coding
Vibe coding is an AI-dependent computer programming practice where a person describes a problem in a few sentences as a prompt to a large language model (LLM) tuned for coding. The LLM generates software, freeing the programmer from having to write and debug the underlying code.[1][2][3] Vibe coding is claimed by its advocates to allow even amateur programmers to produce software without the extensive training and skills which coding previously needed.[4] The term was introduced by Andrej Karpathy in February 2025[5][2][4][1] and listed in the Merrian-Webster dictionary the following month as a "slang & trending" noun.[6]
Definition
Computer scientist Andrej Karpathy, a co-founder of OpenAI and former AI leader at Tesla, introduced the term vibe coding in February 2025.[5][2][4][1] The concept refers to a coding approach that relies on large language models, 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 bugs, requiring him to experiment with changes until the problems are resolved.[2]
A key part of the definition of vibe coding is that the user accepts code without full understanding.[1] AI researcher Simon 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]
Reception
New York Times journalist Kevin 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 that analyzed his fridge contents to suggest items for a packed lunch. 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 an e-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 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.[7][8]
Controversies
Vibe coding has raised concerns about understanding and accountability. Developers may use AI-generated code without fully comprehending its functionality, potentially leading to undetected bugs and errors. While this approach may be suitable for prototyping, it is considered by some experts to pose risks in professional settings, where a deep understanding of the code is crucial for debugging and maintenance. 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 March 2025, Forbes reported that while vibe coding has accelerated software development, it presents challenges for long-term software reliability. The article notes that AI-generated code can be difficult to troubleshoot, often requiring human oversight. Forbes states, “Companies embracing vibe coding must develop robust code review processes and invest in debugging tools to ensure quality and reliability.” Additionally, the article questions how this approach will impact software security and maintainability over time.[8]
External links
- VibeCodingList.com – Curated directory of vibe coding examples and resources.
References
- ^ a b c d e f g Edwards, Benj (March 5, 2025). "Will the future of software development run on vibes?". Ars Technica. Archived from the original on March 6, 2025. Retrieved March 6, 2025.
- ^ a b c d e "What is 'vibe coding'? Former Tesla AI director Andrej Karpathy defines a new era in AI-driven development". The Times of India. March 2, 2025. Archived from the original on March 4, 2025. Retrieved March 3, 2025.
- ^ a b c d e f Roose, Kevin (February 27, 2025). "Not a Coder? With A.I., Just Having an Idea Can Be Enough". The New York Times. ISSN 0362-4331. Archived from the original on March 3, 2025. Retrieved March 3, 2025.
- ^ a b c d e Chowdhury, Hasan; Mann, Jyoti (February 13, 2025). "Silicon Valley's next act: bringing 'vibe coding' to the world". Business Insider. Archived from the original on February 26, 2025. Retrieved March 3, 2025.
- ^ a b Karpathy, Andrej (February 2, 2025). "Andrej Karpathy on X: "There's a new kind of coding I call "vibe coding", where you fully give in to the vibes, embrace exponentials, and forget that the code even exists. ..."". X. Archived from the original on February 18, 2025. Retrieved March 7, 2025.
- ^ "vibe coding". www.merriam-webster.com. March 8, 2025. Retrieved March 15, 2025.
- ^ Mehta, Ivan (March 6, 2025). "A quarter of startups in YC's current cohort have codebases that are almost entirely AI-generated". TechCrunch. Archived from the original on March 6, 2025. Retrieved March 6, 2025.
- ^ a b Predin, Josipa Majic (March 10, 2025). "The AI Revolution That's Making VCs Bet Big On Human Intuition". Forbes. Retrieved March 11, 2025.