A system overview for near-term, low-trust AI compute verification (opens in new tab)

Version 0.2, working draftThis is a working draft of my current best idea for a privacy-preserving, retrofittable AI compute verification system, for confidence-building in an arms-control-like AI agreement between rival nation states. The purpose of this draft is to elicit community engagement by making use of : I make assertions about what the (emerging) field of AI verification should aim for, and people with experience in international policy, cybersecurity and any relevant field of engin...