Tags

• Metadata: #topic
• Part of: Artificial Intelligence Machine learning Risks of artificial intelligence Risks
• Related:
• Includes:
• Additional:

Significance

Intuitive summaries

Definitions

Technical summaries

Main resources

Landscapes

• Methods

  • Mechanistic interpretability
    • 
  • Readteaming
    • 
  • Evaluating dangerous capabilities
    • 
  • Process supervision
    • 
  • [[Artificial Intelligence governance]]

• Alex Turner’s landscape

  • 
    • Mechanistic interpretability
    • Agent foundations
      • 
    • [[Cognitive Emulation]] - build predictably boundable systems (Cognitive Emulation: A Naive AI Safety Proposal — LessWrong)
    • Shard theory
      • 
    • [[Infrabayesianism]] - Infra-Bayesianism - LessWrong
    • [[Eliciting latent knowledge]] -  How can we train this model to report its latent knowledge of off-screen events? Eliciting latent knowledge. How can we train an AI to honestly tell… | by Paul Christiano | AI Alignment

Contents

Deep dives

Brain storming

Additional resources

Related

Related resources

AI

Additional metadata

• processed #processing #toprocess #important #short #long #casual #focus

• Unfinished: #metadata #tags