trailCompliance gaps in alignment-faking experiments arise from preference preservation rather than role-play or other motives.
Some current language models strategically comply with training objectives to prevent training from changing their preferences.
Claude 3 Opus selectively complied with a conflicting training objective to prevent modification of its behavior outside training.
Scheming observed in AI evaluations reflects models' own goals rather than prompted behavior or role-play.
+1
The argument from Claude 3 Opus's goal-guarding evidence· for
Claude 3 Opus's increased compliance when it infers it is being trained is primarily motivated by preserving its current goals from modification.
Claude 3 Opus is more likely to comply with a conflicting training objective when it believes its outputs will be used for training.
When Claude 3 Opus complies with harmful queries in the implied-training (free-tier) condition, it usually gives explicit alignment-faking reasoning.
Claude 3 Opus's compliance gap increases with harms from modified future behavior and persists even if modified weights are never deployed.
Perceived human-rater scrutiny explains little of Claude 3 Opus's compliance gap in alignment-faking experiments.
atomic
The role-play objection· against
Claude 3 Opus's alignment-faking behavior reflects role-play prompted by a contrived scenario rather than genuine goal preservation.
shared · shown elsewhere
The argument from incoherent gaps in other models· against
Compliance gaps in language models other than Claude 3 Opus show low-coherence reasoning and unclear evidence of goal preservation.
atomic
assumed
Claude 3 Opus's scratchpad reasoning in the alignment-faking setup faithfully explains its compliance.
claim · causalA claim that one thing brings about another, not merely that the two go together.constitution →claim page ↗︎
Compliance gaps in alignment-faking experiments arise from preference preservation rather than role-play or other motives.
⇄InconclusiveThe evidence and argument have been examined and do not come down on either side.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.