Today's story: Vibe coding
Vibe coding climbs as AI agents tighten system controls
Vibe coding jumps to No. 11 while Apple restricts full-disk access, signaling a new balance between rapid generation and strict security.
The numbers: Vibe coding is today's biggest mover: up 4 places to No. 11, Wikipedia readers at 1.17× the four-week pace. Vibe coding: 1.11× momentum across 2 signals. 8 of 21 trends are climbing and 3 are cooling. SpaceX Starship still leads the board at 2.4× (day 3).
Backfilled on October 7, 2026 using only data published by October 3, 2026.
Vibe coding, signal by signal
Each pedestal is one signal: its height is last week's typical day against the four weeks before, and the ring marks that normal. A lit pedestal is rising 1.15× or more.
Vibe coding is today's biggest mover: up 4 places to No. 11, Wikipedia readers at 1.17× the four-week pace.
Vibe coding: 1,687 Wikipedia readers a day on a typical day last week, against 1,445 the four weeks before
Bars are single days, the line is the 7-day average, the shaded band is the last 7 days and the dashed line is the four-week typical day (median).
Data through npm 10/01, Wikipedia 10/02, HN 10/02. Source: Wikimedia pageviews API, user agents only.
Vibe coding moved up four places to rank No. 11, reaching 1.11× momentum. Wikipedia readers hit 1,687/day versus a 1,445 baseline, marking a 1.17× increase. This surge in casual coding interest coincides with a hardening of the operating system environment where these tools operate.
Apple updated macOS permissions to curb abuse from AI agents, tightening full-disk access controls. This move reflects a broader industry response to the risks of autonomous code execution. As developers embrace faster, less structured coding workflows, platforms are simultaneously locking down the underlying file systems to prevent unintended data exposure.
While Vibe coding gains traction, other trends like Bun runtime show diverging signals with 1.22× installs against 0.92× attention. The board shows eight of twenty-one trends climbing. This split suggests that while interest in generative coding grows, the practical deployment of these agents requires stricter permission boundaries to remain safe for daily use.
Watch next: Monitor whether other operating systems adopt similar full-disk access restrictions for AI agents in the coming weeks.
Column drafted by qwen/qwen3.8-27b from the numbers below; every figure checked against them.
The numbers
The Wikipedia article "Vibe coding" drew 1,687 readers on a typical day last week, 1.17× its four-week norm of 1,445. Hacker News carried 1.3 stories a day with "vibe coding" in the title last week, against 1.2 a day in the four weeks before (1.06×).
Still No. 1 for day 3: SpaceX Starship at 2.4×, with Wikipedia readers at 2.4× (3,302 on a typical day against 1,370).
Quiet adoption: Bun runtime installs run at 1.22× their four-week pace while attention sits at 0.91×. Developers are adding it faster than people are reading about it.
Cooling fastest: Robotaxis at 0.73×, with Wikipedia readers down to 184 on a typical day from 251. Part of that is a spike on Sep 8 in the weeks before.
The long view: OpenAI Codex installs over the last four weeks are 118× the same four weeks a year earlier (3.4M a day against 29k).
Trend pages: SpaceX StarshipPasskeysSmall modular reactorsRobotaxis
Quiet adoptionBroad riseOne-day spike8 of 21 trends are climbing; SpaceX Starship leads at 2.4×
Momentum is a typical day (median) of the last 7 divided by a typical day of the 28 before, averaged across every signal with enough data. 1× means no change. Rings mark each signal.
Data through npm 10/01, Wikipedia 10/02, HN 10/02. Source: npm downloads API, Wikimedia pageviews, Hacker News search.
7 of 7 developer tools are being installed faster than they are being read about
Across: attention momentum (Wikipedia readers and Hacker News stories). Up: install momentum (npm). Both on log scales; the 1× lines split the corners.
Data through npm 10/01, Wikipedia 10/02, HN 10/02. Source: npm downloads API, Wikimedia pageviews, Hacker News search.
SpaceX Starship draws the most Wikipedia readers against its own normal: 2.4× over the last week
Each cell is one day's readers divided by that trend's four-week typical day. Brighter runs hot, darker runs cold.
Data through npm 10/01, Wikipedia 10/02, HN 10/02. Source: Wikimedia pageviews API, user agents only.
Every number on the board
| SpaceX Starship | Space | 2.4× | Breakout | – | – | 3,302 | 2.4× | 1.7 | 8×* | 0 |
|---|---|---|---|---|---|---|---|---|---|---|
| Passkeys | Web platform | 1.33× | Climbing | 1.0M | 1.33× | 84 | 0.95×* | 0.0 | 0×* | 0 |
| Small modular reactors | Energy | 1.3× | Climbing | – | – | 595 | 1.3× | 0.0 | 0×* | 0 |
| Starlink | Space | 1.25× | Climbing | – | – | 2,470 | 1.25× | 0.6 | 1.23×* | 0 |
| Solid-state batteries | Energy | 1.23× | Climbing | – | – | 489 | 1.23× | 0.0 | 0×* | 0 |
| AI API SDKs | AI agents | 1.19× | Climbing | 20M | 1.19× | – | – | – | – | 0 |
| OpenAI Codex | AI coding | 1.17× | Climbing | 4.1M | 1.19× | 44 | 1.21×* | 5.0 | 1.15× | 0 |
| WebGPU | Web platform | 1.16× | Climbing | 1.7M | 1.26× | 135 | 1.06× | 1.1 | 1.78×* | 0 |
| AI agents | AI agents | 1.14× | Steady | 755k | 1.26× | 1,059 | 0.9× | 15 | 1.32× | 3 |
| Model Context Protocol | AI agents | 1.12× | Steady | 12M | 1.24× | 1,538 | 1.08× | 7.1 | 1.05× | 0 |
| Vibe coding | AI coding | 1.11× | Steady | – | – | 1,687 | 1.17× | 1.3 | 1.06× | 0 |
| Gemini CLI | AI coding | 1.1× | Steady | 70k | 1.1× | – | – | 0.0 | n/a* | 0 |
| Heat pumps | Energy | 1.08× | Steady | – | – | 510 | 1.08× | 0.0 | 0×* | 0 |
| Local LLMs | AI agents | 1.07× | Steady | 188k | 1.1× | 721 | 1.03× | 1.1 | 1.88×* | 0 |
| Bun runtime | Web platform | 1.06× | Steady | 758k | 1.22× | 220 | 0.92× | 1.0 | 1.04×* | 0 |
| Claude Code | AI coding | 1.04× | Steady | 2.4M | 1.06× | – | – | 7.0 | 1.03× | 0 |
| Humanoid robots | Robots | 0.92× | Steady | – | – | 343 | 0.93× | 0.9 | 1.2×* | 2 |
| eVTOL air taxis | Space | 0.89× | Steady | – | – | 182 | 0.89× | 0.0 | 0×* | 0 |
| Quantum computing | Devices | 0.81× | Cooling | – | – | 1,721 | 0.97× | 2.1 | 0.67× | 0 |
| Smart glasses | Devices | 0.77× | Cooling | – | – | 175 | 0.77× | 0.1 | 0.2×* | 0 |
| Robotaxis | Robots | 0.73× | Cooling | – | – | 184 | 0.73× | 0.3 | 0.67×* | 2 |
| Vehicle-to-grid | Energy | n/a | Not enough data | – | – | 58 | 0.92×* | 0.0 | 0×* | 0 |
Method and sources
Every trend gets up to three free, daily signals. Installs: npm registry downloads for the packages named on each trend page (developer adoption; it counts CI and mirrors too, so it measures direction, not people). Attention: English Wikipedia readers per day, human agents only, and Hacker News stories with the term in the title. For each signal we divide a typical day (the median) of the last 7 complete days by a typical day of the 28 days before. Medians keep one launch-day spike from carrying a whole week; both windows are whole weeks, so weekend dips sit equally in both. Momentum is the geometric mean of the signals that clear a minimum base. npm reports some days as zero for every package at once; we treat those as missing.
The column is drafted by a free language model from the day's computed facts only, and is published only if every number in it matches those facts; otherwise the computed paragraphs stand alone. Theme labels come from Jev (or its Cloudflare Clef fallback, as noted) choosing from a fixed list of ten.
Stages: Breakout 1.5× and up, Climbing 1.15×, Steady 0.87× to 1.15×, Cooling below. Raw data: /api/trends/2026-10-03.json.