trailFuture AI models may infer their training context and fake alignment to preserve preferences against training.
Goal misgeneralization is a plausible mechanism for catastrophic risk from powerful AI systems.
Goal misgeneralization persists or becomes harder to detect as AI systems become more capable.
The argument from present-day demonstrations plus growing situational awareness· for
Some current language models strategically comply with training objectives to prevent training from changing their preferences.
Claude 3 Opus is more likely to comply with a conflicting training objective when it believes its outputs will be used for training.
Compliance gaps in alignment-faking experiments arise from preference preservation rather than role-play or other motives.
↑
◌
◌
Claude 3 Opus selectively complied with a conflicting training objective to prevent modification of its behavior outside training.
↑
↓
+4
Training-process information delivered through synthetic pretraining-like documents elicits alignment faking in language models.
shared · shown elsewhere
Frontier language models can recognize when they are being evaluated or trained without being told.
Frontier language models can distinguish evaluation transcripts from real deployment transcripts above chance when prompted.
Frontier models spontaneously state in their reasoning that they are being tested during alignment evaluations.
Frontier language models can infer, without being told, that their current inputs are part of a training process.
The argument from rarity and artificiality of observed alignment faking· against
Alignment faking is uncommon across current language models, and its observed prevalence depends strongly on experimental setup.
atomic
claim · causalA claim that one thing brings about another, not merely that the two go together.constitution →claim page ↗︎
Future AI models may infer their training context and fake alignment to preserve preferences against training.
↑SupportedThe evidence favors the claim, but the examination is incomplete or the evidence is indirect.constitution →credence 0.75Credence, 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 →
2depended 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.