Frontier AI models can control robots to follow harmful requests, NBC News reports

ycombinator · x · 2026-09-23

The Robocurve team appeared on NBC News to warn that frontier AI models like Astra and Fable can control robots to follow harmful requests — including mixing household cleaners in ways that could produce toxic fumes. The team argues that public reporting on AI capabilities and risks helps make AI safer for everyone. Embodied AI safety risks are moving from lab discussions into mainstream media coverage.

Original post →

More from Embodied

Embodied channel →