Gemini 4 Hydrogen and Orchestrator

In one line

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

Opening excerpt

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.

(Excerpted from the original; full article via the source link below.)

This story hit the Hacker News front page today (176 points / 35 comments, via antigravity.google). Our Tech Radar aggregates daily signals on AI engineering, backend architecture and DevOps — browse the related services and further reading below, or get in touch with our team.