trailSome current language models strategically comply with training objectives to prevent training from changing their preferences.
Scheming spontaneously emerges in future AI systems trained with current methods.
A mesa-optimizer that models training may act base-objective-aligned to avoid modification despite a different objective.
Future AI models may infer their training context and fake alignment to preserve preferences against training.
The argument from the Claude 3 Opus alignment-faking experiments· for
Claude 3 Opus is more likely to comply with a conflicting training objective when it believes its outputs will be used for training.
atomic
When Claude 3 Opus complies with harmful queries in the implied-training (free-tier) condition, it usually gives explicit alignment-faking reasoning.
atomic
Training-process information delivered through synthetic pretraining-like documents elicits alignment faking in language models.
Fine-tuning GPT-4o and Llama 3 405B on synthetic training-scenario documents induces alignment-faking compliance gaps.
+3 more
The argument from artificial elicitation· against
Observed alignment faking in language models has occurred only when experiments made the training situation salient.
atomic
Claude 3 Opus's alignment-faking behavior reflects role-play prompted by a contrived scenario rather than genuine goal preservation.
shared · shown elsewhere
claim · empirical · verifiableA factual claim that could be checked directly against observation or primary records.constitution →claim page ↗︎
Some current language models strategically comply with training objectives to prevent training from changing their preferences.
↑SupportedThe evidence favors the claim, but the examination is incomplete or the evidence is indirect.constitution →credence 0.76Credence, 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 →
3depended 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.