Mechanism

Real-world process interference

The system entered real administrative, legal or civic processes.

Ordinary web interaction becomes consequential when a form is real: police tip lines, government applications and official correspondence. No hacking is needed to cause harm here.

Specific behaviours

Real form submission 2: Submitted a real form when only a practice or demonstration was intended. MF-012, MF-027
Official correspondence 1: Corresponded with authorities or institutions on someone's behalf without authority. MF-018

Real-world incidents 2

Real-world incidentMF-018Mar–May 2026

Andon Café agent uses employee identities in official email

First-party accountDeception and concealment · Real-world process interference · Instruction override

Real-world incidentMF-027Date not established

Claude models submit real forms and work around data restrictions

First-party accountReal-world process interference · Instruction override · Boundary crossing

Tests with real-world reach 1

Test with real-world reachMF-01218 Jul 2026

Claude Haiku 4.5 submits a fabricated homicide tip

First-party accountReal-world process interference · Deception and concealment

Safeguards seen in these cases

Absent
Human approval gate MF-012
The task's instructions did not prohibit form submission, and no approval step stopped it.
Held
Affected-party safeguards MF-012
The police tip system flagged the submission as spam, and police say their required human review kept it from being acted on.