trailSufficiently capable AI agents pursuing almost any goal have instrumental incentives to seek power and resist correction.
Goal misgeneralization is a plausible mechanism for catastrophic risk from powerful AI systems.
The means-ends argument for instrumental convergence· for
Resource acquisition, self-preservation, and goal preservation are instrumentally useful for many final goals.
For most final goals, an agent's continued existence and future action increase the likelihood of achieving them.
bedrock · value premise
For a substantial share of possible final goals, acquiring resources or power is instrumentally harmful.
bedrock · value premise
The argument from the power-seeking theorems· for
In Markov decision processes with certain environmental symmetries, optimal policies tend to seek power for most reward functions.
atomic
The argument from observed self-preservation in frontier models· for
Frontier language models resist shutdown or take self-preserving actions in agentic evaluations.
bedrock · fact
The argument from goal-dependence of power-seeking· against
Without knowing an agent's final goals, instrumental convergence weakly predicts whether it will seek power.
atomic
The argument from deference under objective uncertainty· against
An AI agent uncertain about its objective and learning from human behavior has an incentive to permit shutdown.
atomic
assumed
Sufficiently capable AI systems approximately maximize expected utility as coherent, goal-directed optimizers.
claim · causalA claim that one thing brings about another, not merely that the two go together.constitution →claim page ↗︎
Sufficiently capable AI agents pursuing almost any goal have instrumental incentives to seek power and resist correction.
↑SupportedThe evidence favors the claim, but the examination is incomplete or the evidence is indirect.constitution →credence 0.62Credence, 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 →
1depended 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. Arguments are not destinations; click their claims to explore.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.