# Silicon Valhalla

- **Event:** [Google Gemini Hackathon](https://cerebralvalley.ai/e/2025-ted-ai-hackathon)
- **When:** Oct 18 at 9:00 AM – Oct 19 at 5:00 PM (PDT)
- **Where:** Shack15, San Francisco, CA
- **Team:** [Adi Singh](https://cerebralvalley.ai/u/teamadi), [Oliver Sch](https://cerebralvalley.ai/u/oliver), [Lars Talian Stangebye-Hansen](https://cerebralvalley.ai/u/larstalian)
- **GitHub:** https://github.com/larstalian/hardcoding-agent
- **Demo video:** https://www.youtube.com/watch?v=qyu74jpZocI
- **Gallery:** https://cerebralvalley.ai/e/2025-ted-ai-hackathon/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/2025-ted-ai-hackathon/hackathon/gallery/40

Silicon Valhalla - Fast-Track Unpredicted Robot Control with Gemini (Gemini Robotics 1.5)

This project accelerates robot programming by fusing simulation, vision, and language reasoning into one system. Using Gemini 2.5 Flash, a multimodal model that interprets both images and text, robots in simulation can be guided through natural-language commands instead of code or retraining. Each iteration processes the robot’s camera view, reasons about the scene, and outputs refined motion commands: forming a trial-and-feedback loop that builds precise hardcoded trajectories without datasets or model training. By leveraging Isaac Sim or PyBullet, Gemini’s reasoning bridges perception and control, enabling fast, zero-training robotic demos and radically shortening development cycles.

---

Markdown version of https://cerebralvalley.ai/e/2025-ted-ai-hackathon/hackathon/gallery/40. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt