Every's Vibe Check: Gemini 4 Carbon Codes Better but Trails Fable 5.2 on Judgment
every · x · 2026-11-14
Every reviewed Gemini 4 Carbon (early access from Google, no vendor input):
- Coding: much stronger than Gemini 4 Argon, works autonomously for hours, better 3D objects; testers disagree on how much supervision it needs.
- Bad timing: launched a day after Anthropic's Fable 5.2, which raised the bar by exercising good judgment over long tasks — choosing right work, respecting limits, knowing when it's done.
- Example: for a podcast room, Randy Counsman gave Carbon a 3D scan, photos, and an equipment list; it built a simulator to move lights, test angles and lenses, and check camera positions before buying anything.
Verdict: a real win for Google loyalists, but Fable reset flagship expectations.
More from coding & agent
- Dev builds 3D point-and-click adventure game with Gemini 4 Carbon, big step up from Argon — chongdashu · 2026-11-15
- One Prompt, Zero Fixes: Gemini Hydrogen Builds a Full Falcon 9 Landing Sim in One HTML File — minchoi · 2026-11-14
- GitHub MCP server adds Skills extension with 18 filtered, opt-in workflow skills — 0xkarasy · 2026-11-14
- vibe-codevember day 13: a Three.js 3D labyrinth demo — thespite · 2026-11-14
- Lean proofs as guardrails: AI agents optimize code freely without breaking guarantees — bigdata · 2026-11-14
- Anthropic ships official Claude Fable 5.2 prompting guide: set effort high, finish whole task — JohnAlexander · 2026-11-14