vibe coding
In plain wordsProgramming by conversation: you ask an AI for what you want, try out what it produces and ask again until it works, trusting the code without really reading it.
A way of building software by conversation in which the person judges an AI coding agentcoding agent, n.: An AI agent that writes and fixes software by itself: it reads a codebase, edits files, runs commands and tests, and keeps working until a feature is built or a bug is fixed.'s work only by how the program behaves: they ask for features in plain language, run the result, feed back errors or new wishes, and accept the changes without reading or understanding the code. In its original sense the term named a deliberate trade of review and comprehension for speed, tolerable for prototypes, personal tools and throwaway projects, and distinct from AI-assisted engineering, in which a developer reviews, tests and answers for every change. In wider use it has broadened to mean almost any software development done mainly by prompting, a dilution some programmers resist. Concerns include security flaws, unmaintainable code, hallucinated dependenciesslopsquatting, n.: An attack that exploits AI coding assistants' habit of inventing software packages that do not exist: attackers publish malicious code under those made-up names and wait for people or agents to install it. and the erosion of skills; proponents stress that it lets people who cannot program build working software.
Vibe code the weekend prototype if you like, but nothing vibe-coded ships to production without review.
Origin
Coined by Andrej Karpathy in a post on X on 2 February 2025 describing a style of coding in which one goes with the vibes and can 'forget that the code even exists'. Merriam-Webster added it to its 'Slang & Trending' section in 2025, and Collins English Dictionary named it its Word of the Year for 2025 (announced 6 November 2025).
Usage note
Simon Willison and others argue that the term should keep its narrow meaning — code its author has not reviewed — rather than cover all AI-assisted programming. Spin-offs include vibe engineeringvibe engineering, n.: Building serious software with AI coding assistants while still taking full responsibility for its quality — the careful, professional opposite of vibe coding. for the disciplined, review-heavy alternative and vibe hackingvibe hacking, n.: Using AI coding assistants to carry out cyberattacks by describing the goal in everyday language, letting the AI do technical work the attacker could not do alone. for AI-assisted cybercrime.
Related
- coding agentcoding agent, n.: An AI agent that writes and fixes software by itself: it reads a codebase, edits files, runs commands and tests, and keeps working until a feature is built or a bug is fixed.
- agentic codingagentic coding, n.: Writing software by directing AI agents that plan, edit and test code themselves, with the human acting more as a reviewer and manager than as the person typing every line.
- vibe engineeringvibe engineering, n.: Building serious software with AI coding assistants while still taking full responsibility for its quality — the careful, professional opposite of vibe coding.
- vibe hackingvibe hacking, n.: Using AI coding assistants to carry out cyberattacks by describing the goal in everyday language, letting the AI do technical work the attacker could not do alone.
- Software 3.0Software 3.0, n.: Andrej Karpathy's name for programming computers by writing plain-language instructions for AI models, following traditional code (Software 1.0) and trained neural networks (Software 2.0).
- English is the hottest new programming languageEnglish is the hottest new programming language, phr.: A catchphrase meaning that people can now get computers to do things by describing what they want to an AI in ordinary language, instead of writing code.
- Andrej KarpathyAndrej Karpathy, prop. n.: A Slovak-Canadian AI researcher and teacher who co-founded OpenAI, led Tesla's self-driving vision team, and coined popular phrases such as 'vibe coding'.
- one-shotone-shot, v.: Slang for an AI completing a whole task correctly on the first try from a single request — 'it one-shotted the app' — with no corrections or follow-up needed.
Mentioned in
coding agentcoding agent, n.: An AI agent that writes and fixes software by itself: it reads a codebase, edits files, runs commands and tests, and keeps working until a feature is built or a bug is fixed., GitHub CopilotGitHub Copilot, prop. n.: An AI assistant from GitHub, built into programmers' code editors, that suggests code as they type, answers questions about code and can carry out coding tasks on its own., agentic codingagentic coding, n.: Writing software by directing AI agents that plan, edit and test code themselves, with the human acting more as a reviewer and manager than as the person typing every line., AI coding assistantAI coding assistant, n.: AI software that helps people write computer programs — suggesting the next lines, explaining code, finding bugs or making changes on request — inside the tools programmers already use., AI-enabled cyberattackAI-enabled cyberattack, n.: A computer attack in which criminals or spies use AI to help — writing convincing scam messages, finding weak spots, producing malicious code, or even running much of the hacking by itself., AI-nativeAI-native, adj.: Describes a product, company or person built around AI from the start, rather than one that added AI features to older ways of working., Andrej KarpathyAndrej Karpathy, prop. n.: A Slovak-Canadian AI researcher and teacher who co-founded OpenAI, led Tesla's self-driving vision team, and coined popular phrases such as 'vibe coding'., code generationcode generation, n.: Having an AI write computer code from a description in plain language, from finishing a single line as you type to building whole programs., one-shotone-shot, v.: Slang for an AI completing a whole task correctly on the first try from a single request — 'it one-shotted the app' — with no corrections or follow-up needed., OpenClawOpenClaw, prop. n.: A free, open-source AI helper that lives on a computer you control; you send it requests by text message, through apps such as Telegram or Signal, and it acts for you in your email, calendar and files., prompt engineerprompt engineer, n.: A person whose job is writing and testing the instructions given to AI models so they behave reliably; hyped in 2023 as a six-figure job anyone could learn, the role has since largely merged into ordinary engineering., Software 3.0Software 3.0, n.: Andrej Karpathy's name for programming computers by writing plain-language instructions for AI models, following traditional code (Software 1.0) and trained neural networks (Software 2.0)., vibe checkvibe check, n.: Trying out a new AI model informally — chatting with it, asking your favorite test questions — to get a gut feeling for how good it is, rather than measuring it with formal tests., CursorCursor, prop. n.: A code editor built around AI, in which programmers can ask a model to write, change or explain code across a whole project, or hand it tasks to finish on its own., dark factorydark factory, n.: A way of building software in which AI agents write, test and ship all the code and no human writes or reads it, like a factory run with the lights off., Deep Blue (malaise)Deep Blue (malaise), n.: A feeling of gloom and dread among programmers as AI tools become able to do much of the work that once gave their jobs meaning., English is the hottest new programming languageEnglish is the hottest new programming language, phr.: A catchphrase meaning that people can now get computers to do things by describing what they want to an AI in ordinary language, instead of writing code., Ralph Wiggum loopRalph Wiggum loop, n.: A blunt way of using AI coding assistants: feed the same instructions to the AI again and again in an endless loop until the software gets built., Simon WillisonSimon Willison, prop. n.: A British programmer and blogger, co-creator of the Django web framework, whose widely read writing on language models coined 'prompt injection' and the 'lethal trifecta'., slopsquattingslopsquatting, n.: An attack that exploits AI coding assistants' habit of inventing software packages that do not exist: attackers publish malicious code under those made-up names and wait for people or agents to install it., spec-driven developmentspec-driven development, n.: Building software with AI coding agents by first writing a detailed description of what it should do, which the AI then follows to plan and write the code., vibe engineeringvibe engineering, n.: Building serious software with AI coding assistants while still taking full responsibility for its quality — the careful, professional opposite of vibe coding., vibe hackingvibe hacking, n.: Using AI coding assistants to carry out cyberattacks by describing the goal in everyday language, letting the AI do technical work the attacker could not do alone., vibe portingvibe porting, n.: Using AI coding agents to translate a whole software project into another programming language, usually checking the result against the original project's tests.