Robot Learns a Task From a Single Demo With Zero Fine-Tuning
E0M · x · 2026-08-20
A member of the Genesis team (@felixwyw) recounts that late on Aug 3, while experimenting with few-gradient learning on GEN-1.5, they improvised a test of "physical prompting": show the robot a task once, and it imitates the demo exactly with zero fine-tuning. More prompts for different tasks also landed successful rollouts. The author credits years of team work and community groundwork for the breakthrough. Reposter @benbarry recalls a 2018 conversation with Ilya Sutskever: AI progress can go from feeling nearly impossible to just working overnight — and he feels it again now.
Related event: Genesis robot learns from a single demo with zero fine-tuning(2 posts)→
More from Embodied
- Robot crash sparks debate: Is China's robotics industry over-optimizing for speed? — 2C_ornot2C · 2026-08-20
- AI wearables only make sense once users fully buy into agentic AI, analyst says — BenBajarin · 2026-08-20
- Robot Crash at Beijing Games: Perception Loop Missed Barrier at Close Range — rohanpaul_ai · 2026-08-20
- Cosmic Robotics unveils Mars roadmap, deploying bots on Earth sites — ycombinator · 2026-08-20
- Opinion: Robotics field currently at GPT-3 era — oyhsu · 2026-08-20
- Wayve co-founder shares contrarian ideas on building better robots in SF — alexgkendall · 2026-08-20