Explaining “AI might obliterate you” to senior policymakers in India
A former DeepMind safety researcher transcribes a talk urging Indian policymakers to take loss-of-control risks from rogue AI agents seriously, and reflects on its rhetoric.
Research
Focus All
Topic Compute & hardware + Agents
Source All
Date Any time
1 item
1 item
Ethical Hyper-Velocity (EHV): A Hardware-Rooted Zero-Trust Runtime Enforcement Architecture for Agentic AI Systems
Proposes a hardware-rooted runtime enforcement architecture for agentic AI combining constrained decoding, TEEs and policy sync, with bounded TLA+ checks showing no non-compliant actions in the modelled state space.