Jensen Huang's GTC Berlin finale: one-prompt Hermes Agent builds and trains a robot in simulation
NousResearch · x · 2026-10-22
Nous Research revealed that Jensen Huang closed GTC Berlin 2026 with a Hermes Agent demo: installing and customizing Hermes in one prompt, then using it on an RTX Spark to plan an obstacle course with Nemotron, have GPT-6 Astra build it via FreeCAD, Omniverse, Blender, Newton and Isaac Lab, and train thousands of simulated ducks until the validated policy ran on the real robot. Nous frames this as open source's practical power for chaining local and cloud models, devices and tools.
Related event: Jensen Huang Closes GTC Berlin with Hermes Agent Demo(2 posts)→
More from coding & agent
- Open-source huashu-motion turns Claude Code into a launch-film studio, 1.3k stars — AlchainHust · 2026-10-22
- Thinking Machines Ships StableReinforce, a Loss That Keeps Off-Policy RL From Collapsing — LiTianleli · 2026-10-22
- phoneuse launches MCP/API giving AI agents their own cloud Android and iPhone devices — Rasmic · 2026-10-22
- 15-person Keenable beats $350M-funded Exa atop Vals web search index at 49.1% — EXM7777 · 2026-10-22
- Rork's $1800/month Max tier offers 10,005 credits for tokenmaxxing Opus — rudrank · 2026-10-22
- AI Agents Spent $47.35 Overnight From a Single Prompt With No Numbers — aakashgupta · 2026-10-22