Gemini 4 models in Antigravity reportedly skipping thinking entirely, even at High/xHigh effort

lyraxana · x · 2026-11-17

Multiple users report Gemini 4 anomalies in Google Antigravity: the Gemini 4 Hydrogen Extra model is locked/unavailable despite eligible subscriptions, while Carbon and Argon completely skip the thinking/reasoning process in all modes — even at High/xHigh effort — outputting instant responses that fail on hard tasks.

A forum post shows ChatGPT models working fine under the same subscription (Google AI Ultra, Antigravity 23.2), suggesting a Gemini 4 backend routing or entitlement sync issue rather than a client/network problem. The report has gathered 34 "Me too" reactions.

Original post →

More from Models

Models channel →