/
Navigation
Chronicles
Browse all articles
Explore
Semantic exploration
Research
Entity momentum
Nexus
Correlations & relationships
Story Arc
Topic evolution
Drift Map
Semantic trajectory animation
Posts
Analysis & commentary
Pulse API
Tech news intelligence API
Browse
Entities
Companies, people, products, technologies
Domains
Browse by publication source
Handles
Browse by social media handle
Detection
Concept Search
Semantic similarity search
High Impact Stories
Top coverage by position
Sentiment Analysis
Positive/negative coverage
Anomaly Detection
Unusual coverage patterns
Analysis
Rivalry Report
Compare two entities head-to-head
Semantic Pivots
Narrative discontinuities
Crisis Response
Event recovery patterns
Connected
Search: /
Command: ⌘K
Embeddings: large
TEXXR

Chronicles

The story behind the story

days · browse · Enter similar · o open

A look at Vibecoding, a term popularized by AI researcher Andrej Karpathy for a trend where AI lets nontechnical hobbyists build bespoke apps for themselves

and the joys of using AI to build “software for one.” [image] LinkedIn: Joe McKendrick : A new term to ponder: “Vibecoding,” explained by Kevin Roose in The New York Times  —  “Vibecoding, a term that was popularized …

New York Times Kevin Roose

Context & Ripple Effects

Vibecoding names the consumer-facing extension of AI coding assistance: instead of aiming only at professional software teams, it frames prompting as a way for hobbyists to make narrowly tailored tools for their own use. It follows claims that AI agents could take on much larger chunks of software projects, as in Cognition AI's project-completion assistant.

The idea later became productized in tools such as Google's Opal test for prompt-built mini web apps. Related developer coverage also suggests the professional counterpart: AI can move programmers toward an architect-like role rather than eliminating the need to define and judge what gets built.

First-order effects

  • Nontechnical hobbyists can turn personal workflows and ideas into bespoke, single-user apps without first acquiring conventional programming skills.
  • The value of AI coding tools shifts beyond code generation toward helping users describe, iterate on, and validate a useful personal tool.

Second-order effects

  • Low-code and AI app-building vendors face pressure to make prompt-to-app creation, remixing, and iteration accessible to users with little technical expertise.
  • Some simple internal or personal software needs may be met with one-off tools rather than purchased, generalized applications, raising the importance of usability and customization for software providers.

Third-order effects

  • If the pattern holds, software creation could broaden from a specialist production activity into a routine form of personal problem-solving, while professional developers concentrate more on architecture, integration, and review.
  • The enduring constraint may shift from writing code to specifying needs and evaluating outputs—an opening for products that make those judgment and safety tasks easier.

The trend: Vibecoding is one expression of AI moving software creation from expert-led development toward workflow-native, prompt-driven customization.

Discussion

  • @mstefan Mike on bluesky
    I'll file “vibecoding” in the same place I put “information superhighway”
  • @sonjadrimmer Sonja Drimmer on bluesky
    “Man so feckless he needs AI to tell him to make turkey sandwich” is my favorite news article of 2025. www.nytimes.com/2025/02/27/t...  [image]
  • @kevinroose Kevin Roose on x
    I wrote about my experiments in vibecoding — and the joys of using AI to build “software for one.” [image]