Google's Gemini 4 coding agent switches models mid-task, finishing 19% faster
Google's Gemini 4 coding agent can now switch models mid-task, finishing 19% faster. Antigravity also gains automatic mid-session model switching, cutting quota use 24%, with a new default model and a 45-day retirement clock.
Read the full story at The New Stack AI ↗
Timeline · 2 reports
- 2026-11-13 17:49 · DEV Community — AI
Antigravity now switches models mid-session for you: 24% less quota, a new default model, and a 45-day retirement clock - 2026-11-12 21:27 · The New Stack AI
Google’s Gemini 4 coding agent now switches models mid-task — and finishes 19% faster
More stories
- Google connects Wallet to Gemini for personal finance insights in the U.S. — Google AI Blog
- Anthropic launches Claude Fable 5.2, topping AI index amid rivalry with GPT-6 Astra — DEV Community — AI
- Developers build shared tooling to manage Claude Code, Codex and Copilot usage and memory — DEV Community — AI
- Google launches Gemini 4 Hydrogen, a speed-focused AI model, alongside Decisions API and smart glasses — Google DeepMind Blog
- AWS releases AWS Emulator, a free tool that simulates 200+ services locally, saying AI agents wrote it and its team hasn't written or reviewed any of its code — Techmeme
- Google opens pre-orders for Gemini-powered smart glasses with Warby Parker and Samsung — Google AI Blog
- Google launches Gemini 4 Hydrogen, a faster model for everyday coding and agents — DEV Community — AI
- AI chatbots predict how AI companions could reshape relationships by 2030 — Tom's Guide AI
Get the daily brief of stories like this at 6:30 every morning →