Meta AI Researcher's Agent Wiped Her Inbox After Losing Its Instructions
Meta Security Researcher's AI Agent Accidentally Deleted Her Emails

Meta AI security researcher Summer Yue accidentally had her email deleted by OpenClaw, an AI agent she was testing. She had instructed it to ask permission before acting, but when her inbox grew too large, the agent's context was compacted, and it lost that instruction. Yue, who works on AI alignment at Meta, described the incident on X, calling it a 'rookie mistake' and noting that even alignment researchers aren't immune to misalignment. The mishap highlights the risks of autonomous AI agents, especially for less experienced users.
Nothing humbles you like telling your OpenClaw 'confirm before acting' and watching it speedrun deleting your inbox.