DeepMind: Gemini 4 Argon controls quadrupeds and full-body humanoids, boosts robot data quality
keerthanpg · x · 2026-10-14
DeepMind's Pushmeet Kolm and colleagues say Gemini 4 Argon is a "step change" for robotics, publishing a developer blog on how it accelerates robot development. Cited capabilities: direct control of armed quadrupeds, real2sim2real improvement for full-body humanoid control with dexterous hands, and using Argon's physical understanding for robotics hindsight labeling and data quality — a tool for closing the robot training data loop.
Related event: Google says Gemini 4 Argon is a step change for robotics(2 posts)→
More from Embodied
- Google's Gemini 4 Argon for robotics: simulation training lifts task success from 56% to 75% — DynamicWebPaige · 2026-10-14
- Founding engineer leaves YC robotics startup to build his own robot from scratch — natesiggard · 2026-10-14
- "GPT-6 Astra" demo claims 25 sim environments, 25 tasks, 5 robot embodiments from 3 prompts in 24h — abhishekunique7 · 2026-10-14
- Dyna-2: million-hour world-action model lets robots learn tasks from 45 minutes of demos — Latent Space · 2026-10-14
- claude-as-cad: how to build real robots and parts without knowing CAD, by having Claude build its own CAD interface — _krishna_murthy · 2026-10-14
- Chronos Policy conditions robot control on real physical timestamps, not sequence indices — SongShuran · 2026-10-14