Tagged "agent-safety"
5 articles tagged agent-safety, 23 February 2026 to 9 August 2026. Newest first.
-
llama.cpp Adds Tool Isolation Support via Docker
Recent llama.cpp releases introduce initial tool isolation capabilities through Docker integration, enabling safer execution of AI agent tools in local deployments. Multiple updates improve server infrastructure including working directory handling and improved tool sandboxing.
-
96.8% of MCP Tool Descriptions Don't Warn the Agent About Destructive Behaviour
A critical safety analysis of Model Context Protocol tool descriptions reveals widespread gaps in agent safety guardrails, with implications for local LLM applications using autonomous agents.
-
When Should AI Step Aside?: Teaching Agents When Humans Want to Intervene
CMU research on training AI agents to recognize when to defer decisions to humans and request intervention, critical for safe autonomous systems in real-world deployment scenarios.
-
The Case for Out-of-Process Enforcement for AI Agents
A security framework proposal for enforcing constraints and safety policies on locally-deployed AI agents through separate enforcement layers rather than relying on in-process controls.
-
GPT-OSS 20B Demonstrates Practical Agentic Capabilities Running Fully Locally
Users successfully deploy gpt-oss-20B as a fully local agentic system using the ZeroClaw framework, with both model and embeddings running on-device for autonomous task execution and shell command generation.