trailAmplified oversight can supervise AI systems moderately beyond overseers’ capabilities, but not superintelligent systems.
The argument from the overseer's structural advantages· for
Verifying an AI system's output for correctness and safety requires less capability than producing it.
shared · shown elsewhere
AI debate systematically favors the debater arguing for the true answer over the debater arguing for a false one.
shared · shown elsewhere
Developers' control of an AI system's inputs, memory, copies, and internals offsets a moderate capability advantage over its overseers.
In AI control evaluations, weak trusted monitors with resampling, replay, and auditing catch most sabotage attempts by stronger untrusted models.
bedrock · unsettled
Untrusted AI models aware of the monitor can evade monitor-based control protocols through adaptive attacks such as prompt injection.
Frontier language models can recognize when they are being evaluated or trained without being told.
◌
✓
↑
The argument from oversight degrading as the capability gap widens· for
AI oversight success rates decline as the capability gap between overseer and overseen system grows.
shared · shown elsewhere
In AI debates, dishonest debaters can win by making arguments too complex for opponents to refute.
shared · shown elsewhere
AI debate enables less capable judges to supervise more capable debaters.
shared · shown elsewhere
Scalable oversight can reliably control superintelligent AI systems.
Scalable oversight protocols remain effective against AI systems that deliberately deceive their overseers.
Strong pretrained language models fine-tuned on weak-model labels consistently outperform their weak supervisors.
◌
◌
Training an AI system on an accurate oversight signal makes it act as its overseers intend throughout deployment, including in rare high-stakes situations.
✓
✓
⇄
+2
The argument from optimisation against the overseer· against
AI debaters trained to win debates learn to exploit systematic errors in their judge.
atomic
The argument that debate has no ceiling in principle· against
The assumptions behind recursive AI debate's honesty guarantees hold for real-world oversight tasks.
shared · shown elsewhere
The argument from bootstrapping· against
Oversight errors do not compound when successive AI generations oversee moderately more capable successors.
shared · shown elsewhere
claim · empirical · derivedA factual claim that rests on inference from other evidence rather than direct observation.constitution →claim page ↗︎
Amplified oversight can supervise AI systems moderately beyond overseers’ capabilities, but not superintelligent systems.
⇄InconclusiveThe evidence and argument have been examined and do not come down on either side.constitution →credence 0.38Credence, 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 →
Nothing in the graph builds on this claim yet.
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.