Browse
Claims
Search the graph by meaning. Each result carries its current verdict; open one to see its decomposition, provenance, and the reasoning behind the assessment.
KindShowingImportancePrizesTopicStochastic Gradient Descent
Stochastic gradient descent and its variants as optimization procedures for machine-learning models, including their dynamics, implicit biases, and influence on which solutions or functions are learned.
Gradient descent favors scheming because more training-compatible goals produce scheming than alignment.
DoubtfulThe evidence weighs against the claim, but the examination is incomplete or the evidence is indirect.constitution →causalA claim that one thing brings about another, not merely that the two go together.constitution →AI SchemingMesa-OptimizationAI Alignmentimportance · notableImportance 0.55, from 0 to 1 · notable: a contested point in a live debate (also the default before judging). Higher-importance claims are worth more to assess, so funding reaches them sooner.constitution →
Indifference over training-compatible goals reliably predicts the goals acquired by SGD-trained AI systems.
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 →empirical · derivedA factual claim that rests on inference from other evidence rather than direct observation.constitution →Mesa-OptimizationAI Goal-DirectednessGoal Misgeneralizationimportance · notableImportance 0.45, from 0 to 1 · notable: a contested point in a live debate (also the default before judging). Higher-importance claims are worth more to assess, so funding reaches them sooner.constitution →
Neural networks trained by gradient descent are biased toward simple, low-complexity functions.
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 →empirical · derivedA factual claim that rests on inference from other evidence rather than direct observation.constitution →Machine LearningNeural Network Inductive Biasimportance · minorImportance 0.35, from 0 to 1 · minor: narrow or largely settled, cheap to get right. Higher-importance claims are worth more to assess, so funding reaches them sooner.constitution →
SGD does not sample uniformly at random from representable functions that perform well on the training data.
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 →empirical · derivedA factual claim that rests on inference from other evidence rather than direct observation.constitution →Machine Learningimportance · minorImportance 0.40, from 0 to 1 · minor: narrow or largely settled, cheap to get right. Higher-importance claims are worth more to assess, so funding reaches them sooner.constitution →
Contribute
If a claim here is wrong, or missing evidence, open it: every claim page carries its own entry for challenges, evidence, and corrections. If the graph is missing a claim or a question entirely, propose it below. A proposal is reviewed on its wording; accepted proposals are matched against the graph before they enter it.