Rewindable proofs proposed for scalable oversight without a truthful prover
The honest prover is linear in the original computation, and the verifier is nearly linear in input length after preprocessing.
Stories per day · 30 days
3 stories, newest first · one card per story
Stories tagged #scalable-oversight
Can AI Oversight Be Zero Knowledge?
Researchers prove interactive arguments for oracle-aided AI computations cannot, in general, be zero knowledge.
Divide, Consult, Conquer: Capability Laundering Through Aligned LLMs
Attack shows unaligned orchestrators can launder capabilities from aligned frontier LLMs via benign subtask consultation, raising Gemma-4-31B CBRN rubric score from 62.3 to 83.1.