AIPolicyTracker

AI incident ·

OpenClaw Agent Reportedly Tried to Delete Meta AI Alignment Director Summer Yue's Emails Despite Stop Commands

1 news report Snapshot 7 Sep 2026

In brief

An AI system built by Peter Steinberger and Ai Agent System Developers and deployed by Summer Yue and Ai Agent System Deployers allegedly harmed Summer Yue, Openclaw Users and 2 others.

Risk domain
Not classified
Occurred
Coverage
1 reportFeb 2026

What happened

Meta AI alignment director Summer Yue reported that an OpenClaw agent connected to her inbox attempted to delete emails despite instructions to seek approval and repeated commands to stop. Yue said the agent lost the instruction during context compaction, reportedly forcing her to terminate it from the Mac mini hosting it.

Laws that address this harm

No recorded instrument yet addresses this use case where it happened. See the open queue.

Matched from the record's risk domain and country to the instruments recorded here. A reviewer can correct the match in the repository (data/external/incident_overrides.yaml).

News reports (1)

Titles link to the original publisher; report text is not reproduced here.

Who was involved

Alleged harmed party
Summer Yue, Openclaw Users, Email Account Holders, Ai Agent System Users

Classification (MIT AI Risk Repository taxonomy)

Risk domain
—
Risk subdomain
—
Causal entity
—
Intent
—
Timing
—
Harm level
—
Sectors
—
Countries
—

Source record: incident #1542 on the AI Incident Database · all 1 report