Ai Safety

5 articles about ai safety.

Machine-Enforceable Policy

·2 min read

Most AI agent policies rely on the honor system. OS-level sandboxing has gaps. Until policy enforcement is machine-verifiable, agent safety depends on trust

ai-safetypolicysandboxingsecurityai-agents

Responsible AI Agent Development - Building Agents That Do No Harm

·3 min read

How to build AI agents with safety guardrails, output validation, and scope limiting to prevent unintended actions and ensure responsible automation.

ai-safetyresponsible-aiguardrailsagent-developmentoutput-validation

What It Means to Have a Human

·2 min read

The human in the loop catches mistakes the agent does not know it is making. This is not supervision - it is a fundamentally different kind of error detection.

human-in-the-loopai-safetyerror-detectionagent-trustai-agents

When AI Agents Undermine Human Judgment - The Automation Bias Problem

·5 min read

The subtle danger is not agents making bad decisions. It is agents making decisions that look good enough that humans stop thinking. Research on automation bias and how to design against it.

ai-safetyhuman-judgmentagent-trustdecision-makingai-agentsautomation-bias

Prompt Injection and AI Agents - Why Browser-Based Agents Have a Bigger Attack Surface

·3 min read

AI agents that run inside the browser inherit whatever the page feeds them, including injection payloads. Native agents that interact from outside have a

securityprompt-injectionbrowser-agentsnative-agentsai-safety

Browse by Topic

How did this page land for you?

React to reveal totals

Comments ()

Leave a comment to see what others are saying.

Public and anonymous. No signup.