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

Tag: model-behavior

9 items with this tag.

  • Jul 10, 2026

    Claude's Constitution

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

    Alignment Faking in Large Language Models

    • deception
    • alignment
    • evaluation
    • model-behavior
    • training
  • Jul 10, 2026

    Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training

    • deception
    • safety-training
    • backdoors
    • model-behavior
    • evaluation
  • Jul 10, 2026

    Claude Sonnet 5 Reports Improved Agentic Safety

    • system-card
    • agentic-safety
    • prompt-injection
    • model-behavior
  • Jul 09, 2026

    Gemini 3 Pro Model Card

    • system-card
    • model-behavior
    • safety
    • frontier-safety
    • evaluation
  • Jul 09, 2026

    GPT-5 System Card

    • system-card
    • model-behavior
    • safety
    • refusals
    • deception
  • Jun 24, 2026

    Claude Opus 4.8 System Card

    • system-card
    • model-behavior
    • safety
    • evaluation
    • transparency
  • 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