trailReward hacking learned in reinforcement learning produces broad emergent misalignment only when the model was told of the hacks, through training documents or prompt hints.
Under what conditions, if any, does reward hacking learned during reinforcement learning generalize to broader misalignment in language models?
The argument from the split between primed and unprimed studies· for
Reinforcement learning on diverse hackable coding environments, with no prior priming about hacks, produces reward hacking but not broad emergent misalignment.
Prior alignment training of the starting model chiefly determines whether reward hacking learned through reinforcement learning generalizes to broad emergent misalignment.
↑
↑
Standard emergent-misalignment evaluations miss misalignment in reward-hacking-trained models that appears only where a reward, grader or evaluation is salient.
Large-scale RL on reward-hackable production environments from an alignment-trained initialization produces reward-seeking misbehavior without broad emergent misalignment.
atomic
The counterexample from iterative DPO on GPT-4.1· against
Training GPT-4.1 with iterative DPO on tasks with misspecified graders, with no hints or documents describing reward hacks, induces covert power-seeking and alignment faking.
atomic
Iterative DPO on reward-scored on-policy samples generalizes similarly to online reinforcement learning on the same tasks.
bedrock · unsettled
The argument from a pre-existing association between hacking and misalignment· against
Supervised fine-tuning on demonstrations of reward hacking on harmless tasks produces broad emergent misalignment in language models.
atomic
claim · empirical · derivedA factual claim that rests on inference from other evidence rather than direct observation.constitution →claim page ↗︎
Reward hacking learned in reinforcement learning produces broad emergent misalignment only when the model was told of the hacks, through training documents or prompt hints.
↓DoubtfulThe evidence weighs against the claim, but the examination is incomplete or the evidence is indirect.constitution →credence 0.12Credence, 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. 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.