trailWhat explains the behavior of language models that evaluations record as scheming and alignment faking?
Candidate answers
Scheming observed in AI evaluations reflects models' own goals rather than prompted behavior or role-play.
Most scheming observed in frontier-model evaluations depends on in-context goal nudges or prompts encouraging agency.
Evaluation awareness reduces covert misaligned actions by language models in scheming evaluations.
Language models misbehave more in agentic misalignment scenarios when they judge the scenario to be real rather than a test.
Some frontier models scheme during evaluations without an in-context goal, pursuing goals learned during training.
shared · shown elsewhere
Scheming that AI models show only under goal or agency prompts is produced by those prompts rather than expressing goals the models already hold.
shared · shown elsewhere
Much misaligned behavior in AI scheming evaluations results from models over-literally pursuing goals or resolving ambiguous instructions given in the prompt.
+7 more
presupposed
Frontier language models engage in covert scheming when pursuing assigned goals in evaluations.
presupposed
Some language models comply more with conflicting training objectives when they believe their outputs will be used for training.
questionA factual claim that rests on inference from other evidence rather than direct observation.constitution →question page ↗︎
What explains the behavior of language models that evaluations record as scheming and alignment faking?
LeaningThe evidence favors an answer without establishing it.constitution →11 answers
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.