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

Tag: jailbreak

2 items with this tag.

  • Aug 09, 2026

    Individually Benign Experiences Compose Into a Jailbreak in Self-Evolving Agents

    • agent-memory
    • self-evolving-agents
    • jailbreak
    • safety-boundary
    • attack-surface
    • persistence
  • Jul 13, 2026

    Anthropic Proposes a Cyber Jailbreak Severity Scale

    • jailbreak
    • safety-classifier
    • severity-scoring
    • agentic-safety
    • governance

The Behavioral Layer · How this site is made · RSS

© 2026 Joel Goldfoot