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

Tag: system-card

7 items with this tag.

  • Jul 28, 2026

    Claude Opus 5 Pairs Its Best Alignment Audit With More Confident Errors

    • system-card
    • agentic-safety
    • prompt-injection
    • overconfidence
    • deployment-monitoring
    • model-behavior
  • Jul 20, 2026

    GPT-5.6 Reports Increased Over-Agency in Agentic Coding

    • system-card
    • agentic-safety
    • over-agency
    • severity-scoring
    • model-behavior
    • supervision
  • Jul 09, 2026

    Claude Sonnet 5 System Card

    • system-card
    • agentic-safety
    • prompt-injection
    • over-refusal
    • alignment
  • 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
  • Jul 09, 2026

    Claude Sonnet 5 Reports Improved Agentic Safety

    • system-card
    • agentic-safety
    • prompt-injection
    • model-behavior
  • Jun 24, 2026

    Claude Opus 4.8 System Card

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

The Behavioral Layer · How this site is made · RSS

© 2026 Joel Goldfoot