Gemini 4 Hydrogen and Orchestrator

一句话概要

Today, we’re rolling out Gemini 4 Hydrogen inside Google Antigravity alongside a new model dropdown option called Orchestrator, which pairs Hydrogen with…

原文开头节选

Earlier this week, we introduced Gemini 4 Carbon alongside /swarm for tackling massive, multi-worktree engineering tasks with parallel agent teams. In just a couple of days, tens of thousands of swarms have been launched on Antigravity, pushing frontier intelligence on the hardest problems.

For everyday feature work and debugging inside a single session, running a frontier reasoning model with multiple parallel agents on every step of every routine task slows down your loop and burns frontier quota. A common industry approach is to use a static “model router” that guesses task difficulty from your first prompt and routes the entire task to the cheapest model that is good enough to complete the task. Unfortunately, these start breaking down as agents become longer running, requiring different levels of complexity at different stages, often discovered as the task evolves.

Orchestrator takes a dynamic, bidirectional approach between Carbon and Gemini 4 Hydrogen within the evolution of a single trajectory.

(以上为原文节选,完整内容见下方”原文来源”)

这条动态今日登上 Hacker News 首页(176 赞 / 35 评论,来源 antigravity.google)。技术雷达每日自动聚合 AI 工程、后端架构、DevOps 方向的前沿动态;相关工程落地可浏览下方的相关服务与延伸阅读,或直接与我们团队交流。