About Blank / Research
  • Overview
  • Recent
  • Areas
  • Landscape
  • Favorites
  • Pipeline
Papers
  • Papers
  • Chapters
  • Triage
  • Review queue
  • Top cited
  • All references
Knowledge graph
  • Frameworks
  • Concepts
  • Methods
  • Findings
  • Claims
  • Hypotheses
  • Predictions
  • Questions
People & places
  • Thinkers
  • Institutes
  • Venues
Communities & gaps
  • Communities
  • Bridges
  • God nodes
  • Shortest path
  • Knowledge graph
  • Gaps
thinker
active
thinker:jan-betley

Jan Betley

Author of work identifying behavioral self-awareness where models describe latent policies without examples

Authored
1
Introduces
0
Studies
1
Affiliations
0
Cited by
5

Authored papers (1)

  • Training large language models on narrow tasks can lead to broad misalignment2025
    referenced-only

More papers — OpenAlex / S2

Studies (1)

Behavioral Self-Awareness

Their work is cited by (5)

  • Persona Features Control Emergent Misalignment1× refs
  • Open Character Training: Shaping the Persona of AI Assistants through Constitutional AI1× refs
  • Activation Oracles: Training and Evaluating LLMs as General-Purpose Activation Explainers1× refs
  • Steering at the Source: Style Modulation Heads for Robust Persona Control1× refs
  • Persona-Model Collapse in Emergent Misalignment1× refs
Other inbound relations (4)
  • citesLarge Language Models Report Subjective Experience Under Self-Referential Processing(artifact)
  • citesLarge Language Models Report Subjective Experience Under Self-Referential Processing(paper)
  • mentionsDiscovering Undesired Rare Behaviors via Model Diff Amplification - Goodfire(paper)
  • mentionsPersona-Model Collapse in Emergent Misalignment(paper)

Recent mentions (3)

  • papers-typed
    discovering-undesired-30a4ef.md
  • papers-typed
    costa-2026-persona-collapse.md
  • papers-typed
    cameron-2025-large.md