doubly-efficient

Tag

Cards List
#doubly-efficient

How to Avoid Debate: Scalable AI Safety via Doubly-Efficient Interactive Proofs

arXiv cs.AI · 2026-07-07 Cached

This paper proposes single-prover interactive proofs for AI safety verification, avoiding the need for debate between two competing models, and extends the approach to oracle-aided computations.

0 favorites 0 likes
← Back to home

Submit Feedback