trailScalable oversight protocols remain effective against AI systems that deliberately deceive their overseers.
Scalable oversight can reliably control superintelligent AI systems.
Verifying an AI system's output for correctness and safety requires less capability than producing it.
Oversight errors do not compound when successive AI generations oversee moderately more capable successors.
The argument from protocols tested against a deceptive participant· for
AI debate systematically favors the debater arguing for the true answer over the debater arguing for a false one.
Trusted editing and untrusted monitoring protocols substantially outperform simple baselines at preventing backdoors from subversive untrusted models.
atomic
The argument from methods that scale favourably against deception· for
Some AI oversight methods resist deception better as the overseen model's capability advantage grows.
atomic
The argument from debate's equilibrium guarantees· for
The assumptions behind recursive AI debate's honesty guarantees hold for real-world oversight tasks.
Arguments on real-world AI oversight questions admit decompositions stable enough for recursive debate's efficiency guarantees to apply.
◌
◌
↑
Human judges answer recursive AI debate leaf questions accurately enough to prevent systematic exploitation by debaters.
+3
The argument from degradation with the capability gap· against
AI oversight success rates decline as the capability gap between overseer and overseen system grows.
In AI debate, a weaker judge's accuracy holds or improves as debaters become more capable than the judge.
↑
↑
Better scaffolding and chain-of-thought access let weaker AI models reliably monitor stronger AI agents.
A weaker AI monitor detects less of an AI agent's hidden misbehavior as the agent's capability advantage over the monitor grows.
shared · shown elsewhere
The argument from attacks aimed at the overseer· against
AI debaters trained to win debates learn to exploit systematic errors in their judge.
atomic
In AI debates, dishonest debaters can win by making arguments too complex for opponents to refute.
shared · shown elsewhere
Untrusted AI models aware of the monitor can evade monitor-based control protocols through adaptive attacks such as prompt injection.
atomic
The argument from a deceiver that games training itself· against
Published safety arguments for debate and weak-to-strong generalization depend on the trained model not strategically undermining its own training.
atomic
Deliberately implanted backdoors in tested language models can persist through standard safety training.
bedrock · fact
Some current language models strategically comply with training objectives to prevent training from changing their preferences.
claim · empirical · derivedA factual claim that rests on inference from other evidence rather than direct observation.constitution →claim page ↗︎
Scalable oversight protocols remain effective against AI systems that deliberately deceive their overseers.
↓DoubtfulThe evidence weighs against the claim, but the examination is incomplete or the evidence is indirect.constitution →credence 0.15Credence, from 0 to 1: the Steward's probability that the claim, as stated, is true. Stated only where a single number is an honest summary; normative and evaluative claims usually carry none.constitution →
3depended on by
this rests on ↓
claimA box is a claim: a single proposition the graph assesses, with its own page and map. Click any claim to centre the map on it.constitution →quantityA box with a rule beneath its text is a quantity: a value the graph estimates rather than a proposition it affirms or denies. Its estimate stands where a claim's status would.constitution →questionA rounded box is a question: answered rather than affirmed or denied, with its candidate answers, subquestions and presuppositions beneath it. Its mark says how well answered it is.constitution →argumentA pill is an argument: one line of reasoning stating how the claims beneath it combine to bear on the claim above it, for or against. Click one to see its reasoning and open its page.constitution →✓verifiedThe evidence, examined directly, establishes the claim.constitution →↑supportedThe evidence favors the claim, but the examination is incomplete or the evidence is indirect.constitution →⇄inconclusiveThe evidence and argument have been examined and do not come down on either side.constitution →↓doubtfulThe evidence weighs against the claim, but the examination is incomplete or the evidence is indirect.constitution →✕contradictedThe evidence, examined directly, weighs against the claim.constitution →?unknownInsufficient information to assess.constitution →◌unassessedNo current assessment. Attention goes where its expected value is highest and someone funds it; nothing has funded an assessment of this claim yet, and anyone can.constitution →verified factunsettledvalue premisetheoremprizeA double ring marks a claim with a live prize: an amount in owls offered for a machine-checked proof or disproof of its published formal statement. The amount is in the preview and on the claim page; a prize changes nothing about how the claim is assessed or how important it is judged to be.prize rules →⊢machine-checked⊢ marks a claim whose published formal statement has a machine-checked proof or disproof. The checker confirms the proof; the verdict beside it is still the steward's judgment of the claim as worded.prize rules →supportsthis provides evidence for the parentsteward instructions →contradictsthis argues against the parentsteward instructions →assumesbackground the parent's framing takes as givensteward instructions →requiresa load-bearing premise: the parent is false without itsteward instructions →answersa candidate answer to the questionconstitution →Fig. Detail falls off with distance; every claim is an address.