Linkpost to arXiv: https://arxiv.org/abs/2506.13609.

Summary: We present a scalable oversight protocol where honesty is incentivized at equilibrium. Prior debate protocols allowed a dishonest AI to force an honest AI opponent to solve a computationally intractable problem in order to win. In contrast, prover-estimator debate incentivizes honest equilibrium behavior, even when the AIs involved (the prover and the estimator) have similar compute available. Our results rely on a stability assumption, which roughly says that arguments should not hinge on arbitrarily small changes in estimated probabilities. This assumption is required for usefulness, but not for safety: even if stability is not satisfied, dishonest behavior will be disincentivized by the protocol.

How can we correctly reward desired behaviours for AI systems, even when justifications for those behaviours are beyond humans’ abilities to efficiently judge?

This is the problem of scalable oversight: a core question to solve if we want to align potentially superhuman systems. Proposals for scalable oversight (including iterated distillation and amplification and debate) tend to rely on recursion. They break down complex justifications into components easier for humans to judge. However, to date, such recursive proposals have suffered from the obfuscated arguments problem: a dishonest system can adversarially choose how to recurse in such a way that dishonesty cannot be efficiently identified. In debate, this means that an honest debater might need exponentially more compute than their dishonest opponent, which is very bad.

Our new paper presents a protocol robust to this problem – but in order to prove that the protocol can in-principle answer any relevant question (‘completeness’), we need a stability assumption. The need for stability for completeness was discussed by Beth Barnes’ original post introducing obfuscated arguments; our paper presents one route to stability, but does not resolve whether most questions have stable arguments in practice.

This post presents a simplified overview of the protocol and proofs – please see the paper for more details.

The Prover-Estimator Debate Protocol

TL;DR: The prover (Alice) breaks a problem down into subclaims, the estimator (Bob) estimates the probability that each subclaim is correct. Alice then picks a subclaim for recu...

Posts

Wikitag Contributions

Comments