trailVerifying an AI system's output for correctness and safety requires less capability than producing it.
Scalable oversight can reliably control superintelligent AI systems.
Amplified oversight can supervise AI systems moderately beyond overseers’ capabilities, but not superintelligent systems.
AI oversight success rates decline as the capability gap between overseer and overseen system grows.
The argument from protocols that shift the work onto the producer· for
AI debate enables less capable judges to supervise more capable debaters.
Debate between passage-informed debaters makes judges who cannot see the passage more accurate on reading-comprehension questions than answering unaided or hearing one assigned advocate.
Debate improves weaker judges' accuracy over answering alone when judges and debaters see the same information.
In LLM debate experiments, judge accuracy rises as debaters become more persuasive.
Human judges of AI debates are influenced by rhetorical tactics independently of which side is correct.
+4
Better scaffolding and chain-of-thought access let weaker AI models reliably monitor stronger AI agents.
Monitors reading a reasoning model's chain of thought detect misbehavior substantially better than monitors that see only actions and outputs.
✓
↑
↑
More capable AI agents can evade weaker trusted monitors using adaptive attacks such as prompt injection.
Prompted or rewritten reasoning can make chain-of-thought monitors miss misbehavior they would otherwise detect, without model training.
Chain-of-thought monitoring depends on models externalizing legible reasoning, which future models may stop doing.
↑
↑
Scalable oversight protocols remain effective against AI systems that deliberately deceive their overseers.
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.
Some AI oversight methods resist deception better as the overseen model's capability advantage grows.
The assumptions behind recursive AI debate's honesty guarantees hold for real-world oversight tasks.
↓
↓
↓
+5
The argument from measured dependence of detection on checker capability· against
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 the universal quantifier under adversarial pressure· against
In AI debates, dishonest debaters can win by making arguments too complex for opponents to refute.
shared · shown elsewhere
claim · empirical · derivedA factual claim that rests on inference from other evidence rather than direct observation.constitution →claim page ↗︎
Verifying an AI system's output for correctness and safety requires less capability than producing it.
⇄InconclusiveThe evidence and argument have been examined and do not come down on either side.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.