Tagged "agent-safety"

• 96.8% of MCP Tool Descriptions Don't Warn the Agent About Destructive Behaviour 1 May 2026
• When Should AI Step Aside?: Teaching Agents When Humans Want to Intervene 17 April 2026
• The Case for Out-of-Process Enforcement for AI Agents 17 April 2026
• GPT-OSS 20B Demonstrates Practical Agentic Capabilities Running Fully Locally 23 February 2026