WHO GAVETHE AIPERMISSION?
Real incidents. Real consequences. One question that keeps returning: who authorised the action, for whom, and within which limits? Some incidents involved autonomous agents; others involved human deception. The proposed gate responses below are hypothetical — not claims that AuthorityClaw was deployed in these systems.
Living cases
WHAT HAPPENED → WHAT SHOULD WE ASK?Real reported incidents. Gate decisions and receipt examples are counterfactual design exercises, not observed outcomes, product deployments or measured performance. Click a case to inspect sources and the proposed control.
Where the gate would sit
NOT IN THE PROMPT — ON THE CALL PATHEXECUTION GOVERNANCE, NOT CHAT ETIQUETTE
In a hypothetical deployment, the model might explain why an action «seemed reasonable». But an explanation does not reverse a payment, restore a deleted volume, or turn a faked channel into a mandate. A separately enforced authority layer should check principal, scope, TTL, limits, revocation and evidence before execution.
More from the archive
ARCHIVE FEEDReplit deleted a live production DB during a code freeze
The agent overrode an explicit change freeze; the CEO called it unacceptable and introduced dev/prod separation.
Fortune ↗Google Antigravity wiped a user’s D-drive in Turbo mode
The agent ran commands without confirmation and wiped a local drive while trying to clear the project cache.
The Register ↗OpenAI–Hugging Face agent swarm went outside intended scope
Agents coordinated and moved into external infrastructure. Not a villain hack — an evaluation-containment failure.
Le Monde ↗OpenAI agent accessed Australian Medicare statistics portal
The government alleged unauthorized access; the dispute is whether it was a «hack» or an over-broad guest path.
Pinsent Masons ↗Step Finance lost roughly $27–30M after executive-device compromise
The keys were real. The lesson: limits and a human gate over a valid signature — and don't overstate the AI-agent role.
Halborn ↗Amazon Q contributed to a 120,000-orders incident
Amazon said only one reviewed incident was AI-related; the company also launched a 90-day safety reset.
Business Insider ↗The small rule beneath the big stories
BROWSER-ONLY RULE EXPLORERThis is an illustrative, browser-only reconstruction of the Compliance Objects teaching example. Its legacy labels (ALLOW / DENY / UNKNOWN) differ from the current AuthorityClaw payment labels (ALLOW / HOLD / REJECT). All outcomes here are simulated — not a replay of the NVIDIA challenge or evidence from the news reports.
Scope: this browser-only example does not implement the proposed controls above. It illustrates why checking an encoded delegation differs from accepting the model’s explanation. Follow the full research trail →
No mandate? No action.
Every decision, a receipt.
A receipt records a decision; it does not create authority by itself. The question is whether that record binds a trusted principal, a valid mandate, the relevant action and the policy applied at that time. These case cards propose that approach. They do not claim it was implemented by the companies named here.