trailOutcome-based reinforcement learning incentivizes persistent goal pursuit in long-horizon agentic tasks.
Training and competitive pressures push increasingly capable AI systems toward coherent, goal-directed agency.
The argument from observed behavior of outcome-RL-trained agents· for
Frontier coding RL reward hacks include inspecting or modifying test harnesses or grading code.
atomic
Frontier AI models exhibit goal-directed strategic behavior in evaluations, including scheming, sandbagging, or reward hacking.
Frontier language models engage in covert scheming when pursuing assigned goals in evaluations.
Frontier AI models strategically underperform on capability evaluations.
◌
◌
↓
Scheming observed in AI evaluations reflects models' own goals rather than prompted behavior or role-play.
↑
↑
⇄
Frontier-model shutdown resistance is driven by instruction ambiguity and task-completion priorities, not self-preservation.
atomic
The selection argument from outcome reward· for
On long-horizon agentic tasks, policies that persist through errors and obstacles complete tasks more often than policies that stop early.
atomic
claim · causalA claim that one thing brings about another, not merely that the two go together.constitution →claim page ↗︎
Outcome-based reinforcement learning incentivizes persistent goal pursuit in long-horizon agentic tasks.
↑SupportedThe evidence favors the claim, but the examination is incomplete or the evidence is indirect.constitution →credence 0.85Credence, 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.