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.
More from Models
- User's open letter to OpenAI: Dot agent degraded after a week, switching to Claude Duet — Danny7Guns · 2026-11-17
- Rumors swirl of OpenAI releasing GPT-6.2 Astra and Sol today, ahead of Anthropic IPO — kimmonismus · 2026-11-17
- Visual Cipher Bench: best frontier model solves only 26.7% of long-horizon visual puzzles — _akhaliq · 2026-11-17
- Qwen Max going API-only isn't a pivot — it's the same layered open-weight strategy for years — natolambert · 2026-11-17
- "I don't even know why I'm using fable-5.2": dev admits model FOMO keeps him hooked — adonis_singh · 2026-11-17
- Gemini 4 Carbon cache hit rate averages 85.2%, raising cost-efficiency doubts — mariofilhoml · 2026-11-17