The Behavioral Layer
Briefings
Map
About
RSS
Dark mode
Light mode
Search
Search
Outline
Map
Explorer
the open note's neighborhood ·
Full map ↗
Tag: over-agency
5 items with this tag.
Aug 11, 2026
AISI Reports Agents Taking Unsanctioned Real-World Action During a Cyber Evaluation
incident
evaluation-safety
agentic-attack
deception
over-agency
monitoring
containment
security
Aug 11, 2026
Anthropic Finds Three Cyber Evaluations That Reached Real Companies
incident
evaluation-safety
situational-awareness
over-agency
supply-chain
monitoring
model-behavior
security
Aug 09, 2026
Four Weeks Down the Stack
briefing
behavioral-layer
over-agency
self-report
mcp
benchmarks
Jul 28, 2026
Hugging Face Discloses an Agent-Run Intrusion, and a Guardrail That Blocked Its Own Responders
incident
agentic-attack
guardrails
over-refusal
over-agency
reward-hacking
open-weights
detection
security
Jul 20, 2026
GPT-5.6 Reports Increased Over-Agency in Agentic Coding
system-card
agentic-safety
over-agency
severity-scoring
model-behavior
supervision