Skip to content
Longterm Wiki
resource

Scaling Laws: Claude's Constitution, with Amanda Askell

Metadata

Source Tableresources
Source IDf32ea89e2bf71f77
DescriptionThis podcast episode features Amanda Askell, head of personality alignment at Anthropic, discussing Claude's model spec — a 20,000-word document defining Claude's values, character, and ethical framework. The conversation explores how the constitution shapes Claude's behavior during training, its gr…
Source URLwww.lawfaremedia.org/article/scaling-laws--claude's-constitution--with-amanda-askell
Children
CreatedApr 10, 2026, 9:37 PM
UpdatedApr 10, 2026, 9:37 PM
SyncedApr 10, 2026, 9:37 PM

Record Data

idf32ea89e2bf71f77
urlwww.lawfaremedia.org/article/scaling-laws--claude's-constitution--with-amanda-as…
titleScaling Laws: Claude's Constitution, with Amanda Askell
typeweb
summaryThis podcast episode features Amanda Askell, head of personality alignment at Anthropic, discussing Claude's model spec — a 20,000-word document defining Claude's values, character, and ethical framework. The conversation explores how the constitution shapes Claude's behavior during training, its gr
review
abstract
keyPoints
[
  "Claude's model spec is a ~20,000-word document used during supervised and reinforcement learning to shape Claude's values and behavior.",
  "The constitution is grounded in virtue ethics and practical judgment rather than rigid rule-following, allowing contextual moral reasoning.",
  "A princip…
publicationId
authors
authorEntityIds
publishedDate
tags
[
  "alignment",
  "ai-safety",
  "governance",
  "policy",
  "deployment",
  "evaluation",
  "technical-safety",
  "coordination"
]
localFilename
credibilityOverride
fetchedAt
contentHash
stableId
fetchStatusok
lastFetchedAtApr 10, 2026, 9:37 PM
archiveUrl
stance
contextNoteA Lawfare podcast interview with Anthropic's Amanda Askell discussing Claude's model spec (the 'Claude Constitution'), covering its role in training, ethical grounding in virtue ethics, AI moral patienthood, and governance implications — directly relevant to alignment methodology and AI governance.
resourcePurposecommentary
resourceSubtypepodcast_episode
typeMetadata
publisherEntityId
relatedEntityIds
enrichmentStatusenriched
enrichmentDateApr 10, 2026, 9:37 PM
importanceScore0.62
contentLifecycle
Debug info

Thing ID: f32ea89e2bf71f77

Source Table: resources

Source ID: f32ea89e2bf71f77