Every's vibe check: Gemini 4 Carbon codes better but judgment lags Fable 5.2
every · x · 2026-11-16
Every reviews Google DeepMind's Gemini 4 Carbon, which launched one day after Anthropic's Fable 5.2 raised expectations for agentic work.
Key findings:
- Much stronger coder than Gemini 4 Argon; can run ambitious builds for hours with little supervision
- Better 3D object generation
- Judgment is mixed: in a Miami hotel-picking test where models kept converging on the same choices, Carbon picked the Kimpton Hotel Palomar South Beach and suggested an unconsidered restaurant — showing independent judgment on location, price, and context, though testers disagree on how much supervision it needs
- Verdict: Carbon makes DeepMind more competitive, but Fable has reset what a flagship must deliver — choosing the right work, respecting limits, knowing when it's done
More from Models
- MiniMax M3.1 Flash lands on OpenRouter, with Inferact as first provider — Xianbao_QIAN · 2026-11-16
- Thinking Machines hailed as leading an American open-source comeback with the impressive Inkling 2 Small — victormustar · 2026-11-16
- Fable 5.2 vs Astra 6 on real PCB layout: 2 clean iterations vs 30 failed ones — ilovemydickuwu · 2026-11-16
- Google's rumored Gemini 4 Oxygen Flash model turns heads at design work — feblet · 2026-11-16
- Shanghai AI Lab's Sage S2.1 Flash tops 4 of 15 scientific benchmarks — pmttyji · 2026-11-16
- DeepSeek free-tier limits spark one-star review revolt as users treat free AI as entitlement — teortaxesTex · 2026-11-16