The Behavioral Layer
BriefingsMapAboutRSS
the open note's neighborhood · Full map ↗

Tag: alignment

8 items with this tag.

  • Jul 10, 2026

    Claude's Constitution

    • behavioral-contracts
    • model-behavior
    • alignment
    • specification
    • transparency
  • Jul 10, 2026

    Petri

    • alignment
    • auditing
    • agent-safety
    • evaluation
    • open-source
  • Jul 10, 2026

    Claude Sonnet 5 System Card

    • system-card
    • agentic-safety
    • prompt-injection
    • over-refusal
    • alignment
  • Jul 10, 2026

    Alignment Faking in Large Language Models

    • deception
    • alignment
    • evaluation
    • model-behavior
    • training
  • Jun 24, 2026

    Sparrow

    • rules
    • behavioral-contracts
    • dialogue
    • alignment
    • behavior
  • Jun 24, 2026

    InstructGPT

    • rlhf
    • instruction-following
    • alignment
    • training
    • behavior
  • Jun 24, 2026

    OpenAI Model Spec

    • behavioral-contracts
    • model-behavior
    • governance
    • alignment
    • specification
  • Jun 24, 2026

    Constitutional AI

    • behavioral-contracts
    • alignment
    • model-behavior
    • governance
    • training

The Behavioral Layer · How this site is made · RSS

© 2026 Joel Goldfoot