Every's vibe check: Gemini 4 Carbon codes better but judgment lags Fable 5.2

every · x · 2026-11-18

Every reviewed Google DeepMind's Gemini 4 Carbon (early access disclosed): a much stronger coder than Gemini 4 Argon with better 3D output and multi-hour autonomy, but it launched a day after Anthropic's Fable 5.2 reset expectations for agentic judgment — choosing the right work, respecting limits, knowing when to stop. Testers disagree on supervision needs. The piece also features Jack Cheng's 'have the committee look at it' setup: Opus on a Mac Mini summoning Fable, Codex, and Gemini as cross-reviewers.

Related event: Every Tests Gemini 4 Carbon: Stronger Coding but Shaky Judgment(2 posts)→

Original post →

More from coding & agent

coding & agent channel →