Vibe coding has escaped the terminal

Casey Newton · rss · 2026-07-08 source ↗ Reader 🖥️

practical · narrative — A first-person account of building three apps with Raycast's Glaze, structured as anecdote-plus-reflection rather than sustained argument. It edges toward the practical (implicitly urging readers to notice/try the shift) but never states a call to action; its real work is descriptive/illustrative, culminating in one modest, explicitly hedged generalization about the future of software.

Structure

Key terms

• vibe coding Vibe Coding
  Building working software — now extended to full consumer desktop apps, not just code — primarily by typing intent into a prompt box and watching an AI agent generate and live-update the result, evaluated on how satisfying and personal the outcome feels rather than on code quality.
• hyper-personalized software
  Software built bespoke for one person's specific, often idiosyncratic and previously uneconomical needs or tastes (e.g. a Nightwing-skinned to-do app), made viable because the marginal cost of building one-off apps has collapsed.
• SaaS-pocalypse
  Newton's own half-joking coinage for a hypothetical mass displacement of subscription software-as-a-service products by cheap, user-generated personal apps.

Propositions

• explicitGlaze is an all-in-one vibe-coding app purpose-built for creating and sharing Mac desktop apps, distinct from general-purpose coding tools like Claude Code.conf: high
• explicitGlaze offers concrete UX advantages over a pure coding tool for a non-technical user: a working app template to start from, automatic compiling/installing, native image-generation calls, and live in-app visual editing (including circling elements to target changes).conf: high
• explicitIn his first month with Glaze, Newton built three apps — Nightwing (a comic-themed to-do app), a Platformer research/archive app, and Source Code (an unfinished contacts/CRM app) — of which only the Platformer app has utility beyond what already exists in the App Store.conf: high
• implicitThe primary value Newton reports from these tools is delight and personal fit ('making my chores fun'), not objectively superior functionality.conf: high
• implicitdevelopedThe collapse in the marginal cost and skill required to build software is what makes previously not-worth-pursuing ideas (a joke to-do app, a personal CRM) newly viable to build at all.conf: high
  extends ←The case for making your own apps · p1 — Mann's quantified 30-50%-of-your-Mac prediction extends Newton's own earlier observation (from his first month with Glaze) that collapsing build cost/skill makes previously not-worth-pursuing software newly viable — turning a personal anecdote into a market-scale forecast.
• explicitNewton's overall verdict ('a future for hyper-personalized software, at least in the short term') is explicitly self-described as not extending far beyond 'it's fun to make things.'conf: high
• implicitNewton's assessment rests entirely on his own first-person, one-month experience as an early-access, well-resourced tech journalist with a personal connection to Anthropic, not on any broader usage data, retention figures, or a representative user.conf: high

Arguments

Narratives

• The Nightwing to-do app: a comic-book-themed, purely-for-delight to-do list with AI-generated character images and animations.
  → Illustrates that near-zero-cost app-building lets a non-technical user pursue an idea with no functional justification, purely for personal enjoyment — supporting the 'hyper-personalized software' thesis via a case that is fun but not useful.
• The Platformer app: a semantic-search research assistant over the newsletter's archive, built in about a day, replacing a friction-heavy terminal/Claude-Code workflow.
  → Supplies the piece's strongest evidence of genuine (not just novelty) value, distinguishing Glaze-built software from a toy.
• Source Code: a half-finished personal CRM merging phone and LinkedIn contacts, with the author still unresolved on privacy, security, and even whether he likes the design.
  → Functions as an honest counter-narrative/caveat — shows unresolved limits (privacy, security, product-design uncertainty, willingness to pay) even for an enthusiastic early adopter, tempering the closing generalization.

Questions addressed

• ✅ Has vibe-coding moved beyond terminal/IDE-bound tools into consumer app-building?
  Yes, per Newton's direct experience with Glaze building three distinct Mac apps.
• ⭕ Is there a durable future for hyper-personalized, one-off software?
  Newton offers only a hedged, personal-anecdote-based 'yes, at least in the short term' — he explicitly declines to extend the claim further.
• ⭕ What are the legal/IP and platform-liability implications of an app-builder that generates copyrighted characters via AI image models?
  Raised rhetorically ('does it represent a copyright violation... almost certainly') and then dropped without further analysis.
• ⭕ What happens to the broader consumer-software/SaaS market — and to Glaze's own app store — if personalized one-off apps become common?
  Named via the 'SaaS-pocalypse' quip but never seriously examined.

Gaps

• incompleteThe piece offers no data on how typical Newton's experience is — he is an early-access, well-resourced tech journalist with a household connection to Anthropic, not a representative consumer; there is no discussion of skill floor, cost sensitivity, or failure/abandonment rate for a broader user base trying Glaze.
  Read next: Look for adoption/retention data on vibe-coding app-builders (Glaze, Wabi) beyond first-month enthusiast anecdotes — completion rates, subscription churn, or a more skeptical follow-up in the spirit of this corpus's 'AI Confidence Theater' theme, which treats vivid personal anecdote as a weak substitute for verifiable evidence.
• incompleteNewton flags the copyright/IP question about AI-generated Nightwing artwork but doesn't pursue what it implies for Glaze's business model, Raycast's legal exposure, or likely rightsholder response.
  Read next: Seek legal/industry analysis of IP liability for AI app-builders that call image-generation models, and how a marketplace like Glaze's store moderates for this.
• incompleteNo examination of the security/privacy architecture behind an app like Source Code, which merges phone contacts with LinkedIn data into a 'private, locally stored' CRM; Newton himself says he is 'still thinking through issues related to privacy and security,' but the piece never examines what guarantees Glaze actually provides around local storage, API-key handling, or data-exfiltration risk.
  Read next: Look for appsec-focused writing on the threat model of vibe-coded apps built by non-technical users that handle personal data (contacts, LinkedIn, API keys) — directly relevant to the reader's application-security interest.
• uninformedAs an outside-observer journalist rather than a practitioner, Newton doesn't engage with the mechanism underneath Glaze — what agent/model architecture it runs, how the 'circle an element to edit it' feature is implemented, or whether the generated code's quality or security is auditable. The piece is long on implications and 'vibes,' short on any rigorous look at what's actually happening under the hood.
  Read next: For the engineering-craft angle, look for a practitioner teardown of Glaze's (or Wabi's) underlying agent harness and tooling, analogous to a technical review of Claude Code internals.
• illogicalThe 'SaaS-pocalypse' and 'revenge' framing treats one person's delight in personalizing his own software as evidence for a market-level claim (a genuine threat to existing SaaS and App Store businesses), without addressing switching costs, the long-term maintenance burden of AI-generated one-off code, or whether most consumers actually want to build rather than buy.
  Read next: Look for a more rigorous build-vs-buy or market-structure analysis of personal software in the vibe-coding era, rather than a single enthusiast's month-one impression.

Related documents

• AI Enthusiasts Are in a Race Against Time, AI Skeptics Are in a Race Against Entropy
  AI Confidence Theater Vibe Coding
• AI Is Changing the Rules of Entrepreneurship
  Taste & Judgment Vibe Coding
• Eight years of wanting, three months of building with AI
  Taste & Judgment Vibe Coding
• SWLW #701: Gazing at the misty AI Frontier, From Vibe Coding to Agentic Engineering, and more.
  Taste & Judgment Vibe Coding