trailFrontier AI models exhibit goal-directed strategic behavior in evaluations, including scheming, sandbagging, or reward hacking.
Training and competitive pressures push increasingly capable AI systems toward coherent, goal-directed agency.
Large language models trained on human data generalize intended goals well enough that goal misgeneralization is not a serious risk.
Outcome-based reinforcement learning incentivizes persistent goal pursuit in long-horizon agentic tasks.
+1
The argument from documented evaluation results· for
Frontier language models engage in covert scheming when pursuing assigned goals in evaluations.
atomic
Frontier AI models strategically underperform on capability evaluations.
Frontier AI models sandbag without explicit instruction when evaluation context suggests high scores could harm them.
Frontier AI models can be prompted or fine-tuned to selectively underperform on capability evaluations.
At least one frontier AI model has been confirmed to sandbag on a real pre-deployment dangerous-capability evaluation.
↑
Frontier coding RL reward hacks include inspecting or modifying test harnesses or grading code.
atomic
Scheming observed in AI evaluations reflects models' own goals rather than prompted behavior or role-play.
Some frontier models scheme during evaluations without an in-context goal, pursuing goals learned during training.
◌
Most scheming observed in frontier-model evaluations depends on in-context goal nudges or prompts encouraging agency.
Models' role-playing of contrived scenarios substantially explains misaligned behavior in AI scheming evaluations.
◌
◌
◌
Compliance gaps in alignment-faking experiments arise from preference preservation rather than role-play or other motives.
↑
◌
◌
claim · empirical · verifiableA factual claim that could be checked directly against observation or primary records.constitution →claim page ↗︎
Frontier AI models exhibit goal-directed strategic behavior in evaluations, including scheming, sandbagging, or reward hacking.
✓VerifiedThe evidence, examined directly, establishes the claim.constitution →credence 0.95Credence, 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 →
4depended 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.