Glossary
Vibe coding
Vibe coding is building software by describing what you want to an AI model and accepting the code it writes, without reviewing that code. Andrej Karpathy introduced the term, and the developer Simon Willison argues for a narrower meaning than the broad one now in use.
Updated October 17, 20263 cited facts, each traced to its source
Vibe coding is building software by describing what you want to an AI model, and accepting the code it writes. Andrej Karpathy introduced the term in a post on X, describing a new kind of coding where you "fully give in to the vibes, embrace exponentials, and forget that the code even exists" 1.
The original post was about speaking, not typing
Karpathy's post also described how he worked. He wrote that he talks to Cursor's Composer with SuperWhisper, so he barely touches the keyboard 2. The term was therefore tied to voice input from the start. The prompt is the work, and speaking is one way to deliver it.
Simon Willison's narrower definition
The developer Simon Willison wrote a long response to the term. He says that when he talks about vibe coding he means building software with an LLM without reviewing the code it writes, and that using LLMs for code responsibly is not vibe coding 3. His point is about review: AI-written code that a developer reads, tests and understands is a different practice from code that nobody checked.
The two meanings share a core: the person describes the goal in plain language and the AI writes the code. They differ on whether anyone reviews it. Other writers use the term more broadly, so check which meaning an author intends.
Why it matters for dictation and typing
Vibe coding puts the prompt at the center of the work, which is why it matters for voice input. You can describe a change out loud while you watch the app, then check the result. The guide to voice input for Claude Code, Cursor and AI coding tools covers how to speak into these tools, and speech to text for AI explains why spoken prompts can work well.
Vibe coding is not the same as voice coding. In voice coding you write and edit the code yourself, by speaking commands. In vibe coding the AI writes the code, and your voice is only one way to give it instructions. An AI dictation tool can clean up a spoken prompt before it is sent, but it does not decide whether the generated code is correct.
Related terms
- Voice coding: writing and editing code by voice, where the programmer stays in control of the code.
- AI dictation: speech to text with an AI rewrite step.
- Dictation: speaking words that software writes down.
Guides that cover it
Evidence
Every number on this page, with where it comes from. Open a fact to see the exact words in its source.
- 1.
- 2.
- 3.
Related terms
- Voice Typing in Google Docs, Word and Every Other AppThe topic this term belongs to
- Connected experiences (Microsoft 365)Connected experiences are Microsoft 365 features backed by cloud services, and Dictate is one of the experiences that analyze your content. You can turn them off in Manage Settings, but that setting also turns off other services.
- CursorlessCursorless is a spoken language for structural code editing that lets developers code by voice. Every command is an action performed on a target in the code, and it runs on Talon with a VS Code extension.
- Dictate (Microsoft 365)Dictate is the speech-to-text feature in Microsoft 365 apps such as Word, Outlook and PowerPoint. It needs a Microsoft 365 subscription, a microphone and a reliable internet connection.
- Dictation (ChromeOS)Dictation on ChromeOS is a built-in accessibility feature that types recognized speech into an editable field. You turn it on with Search + D or the microphone icon in the status tray.
- Site microphone permissionSite microphone permission is the browser's setting for each website that decides whether that site may use your microphone, usually chosen when the browser prompts you. It works alongside the operating system's own microphone setting, so both must allow the microphone before a site can listen.
- Talon VoiceTalon Voice, usually called Talon, is hands-free input software for writing, coding, browsing and gaming. It runs alongside a speech-recognition engine, and it is used for voice coding, often together with the Cursorless editing language.
- Text insertionText insertion is the step where dictation software places recognized words into the text field that has the cursor. It is done either by simulating keystrokes or by pasting the text from the clipboard.
- Transcribe (Microsoft 365)Transcribe is a Word for Microsoft 365 feature that turns an uploaded audio file into text in the Transcribe pane, rather than typing your speech into the document. Its monthly limits depend on your license.
- Voice codingVoice coding, also called programming by voice or coding by voice, is writing and editing source code by speaking instead of typing. It needs a speech-recognition engine and a separate platform that turns spoken words into code editing actions.
- Voice typing (Google Docs)Voice typing in Google Docs is a built-in speech-to-text tool that types as you speak. You start it from the Tools menu in a supported browser, and the browser controls the speech-to-text service.
- WaylandWayland is the display system that Linux desktops are moving to in place of the X Window System, called X11. Its compositor delivers input to each app, so a typing tool that worked on X11 may not type on a Wayland desktop.
- Web Speech APIThe Web Speech API is a set of browser interfaces that let a web page start speech recognition and receive the recognized words as text, through an object called SpeechRecognition. Where the recognition runs, on your device or on a server, depends on the browser.