the-case-for-physical-ai-safety.pdf
paisi.ai · 8,046 words · saved by 1 readers
N/A
The Case for Physical AI Safety Kaylene Stocking∗ Bear Häon∗ The Physical AI Safety Institute July 2026 1 Executive Summary – Robotics is undergoing a paradigm shift: from narrow single-task perception, planning, and control, to large general-reasoning robot foundation models (RFMs). The upcoming era is that of Physical AI. – RFMs take plain language instructions as input (“tidy the kitchen”, “unload the truck”) and produce physical…
saved by
related reading
- The Science of Physical AI Safety — CoRL 2026spais-ws.org
- TechnicalAgenda.pdfintelligence.org
- AI Safety: A Short FAQ for Mathematiciansalkjash.github.io
- Existential Risk from AI: An Exposition for Mathematiciansalkjash.github.io
- Recommendations for Technical AI Safety Research Directionsalignment.anthropic.com
- Generalist - GEN-0 / Embodied Foundation Models That Scale with Physical Interactiongeneralistai.com
- Emergence of Human to Robot Transfer in Vision-Language-Action Modelspi.website
- Frontier of General-Purpose Robotics (2025)adampatni.com
- AI Safety for Fleshy Humans: a whirlwind touraisafety.dance
- The Physical Intelligence Layerpi.website
- Constitutional AI: Harmlessness from AI Feedbackarxiv.org
- GitHub - adam-maj/robotics: A deep dive on the history of robotics and the future of humanoidsgithub.com