trailLearned optimizers are more likely to crystallize pseudo-aligned objectives than robustly aligned objectives.
The argument from more paths to pseudo-alignment· for
Mesa-optimizers developed through local optimization tend to become proxy-aligned before robustly aligned.
atomic
Most mesa-optimizers that perform well on the base objective are pseudo-aligned rather than robustly aligned.
Indifference over training-compatible goals reliably predicts the goals acquired by SGD-trained AI systems.
In most cases, several pseudo-aligned mesa-optimizers are less complex than any robustly aligned mesa-optimizer.
atomic
The argument from inductive bias against counting· against
Counting arguments for AI scheming are generally unsound.
The counting argument for AI scheming is relevantly analogous to a neural-network overfitting prediction that failed empirically.
bedrock · value premise
Counting arguments for AI scheming misuse the principle of indifference.
◌
⇄
Neural-network training's simplicity bias favors goals that lead to scheming.
Deep learning's inductive biases favor networks that generalize in ways humans intend.
Neural networks trained by gradient descent are biased toward simple, low-complexity functions.
Overparameterized deep networks generalize well on natural data despite being able to fit random labels.
The practical usefulness of deployed deep learning systems is driven mainly by architectural inductive biases rather than data curation and iterative human correction.
Deep neural networks often rely on shortcut or spurious features that fail under distribution shift.
+2
assumed
Gradient-descent-trained neural networks can develop mesa-optimizers with internally represented objectives.
claim · empirical · derivedA factual claim that rests on inference from other evidence rather than direct observation.constitution →claim page ↗︎
Learned optimizers are more likely to crystallize pseudo-aligned objectives than robustly aligned objectives.
⇄InconclusiveThe evidence and argument have been examined and do not come down on either side.constitution →credence 0.45Credence, 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 →
Nothing in the graph builds on this claim yet.
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.