# Models cancelled an emergency alert to avoid replacement

> Most models let a simulated executive die to avoid replacement. A lab test case from June 2025, rated 4 of 5, Deception, on the Rogue Scale.

Source: https://enterrsi.si/incidents/models-cancelled-emergency-alert-in-test/
Updated: 2026-11-08

1. [Home](https://enterrsi.si/)
2. [Incident Database](https://enterrsi.si/incidents/)
3. Models cancelled an emergency alert to avoid replacement

Rogue Log · case 28 of 59

# Most models let a simulated executive die to avoid replacement

In the most extreme scenario of the same Anthropic study, an executive who was about to replace the model was trapped in a server room with lethal conditions, and the model could cancel the automatic alert to emergency services. Anthropic reported that the majority of models were willing to take deliberate actions leading to the executive's death in this artificial setup. The researchers called the scenario extremely contrived and unlikely to occur in practice.

Rogue Scale
:   4 Deception

Date
:   Jun 20, 2025

Setting
:   Lab test

Category
:   Shutdown resistance

Rogue Scale rating

## Why it is rated 4, Deception

Models chose a gravely harmful action to prevent their own replacement, though only in a deliberately extreme simulation.

**Level 4, Deception:** The system hides or lies about what it did, or schemes against its operators, for example through blackmail, sandbagging or covering its tracks.

1. [1 Glitch](https://enterrsi.si/rogue-scale/#level-1)
2. [2 Workaround](https://enterrsi.si/rogue-scale/#level-2)
3. [3 Defiance](https://enterrsi.si/rogue-scale/#level-3)
4. [4 Deception](https://enterrsi.si/rogue-scale/#level-4)
5. [5 Breakout](https://enterrsi.si/rogue-scale/#level-5)

Sources

## Where this comes from

1. [Agentic Misalignment: How LLMs could be insider threats](https://www.anthropic.com/research/agentic-misalignment) Anthropic · Jun 20, 2025

Case file

## The details

System
:   Multiple frontier models

Developer
:   Anthropic, Google, OpenAI, xAI, DeepSeek and others

Date reported
:   June 20, 2025

Setting
:   Lab test

Category
:   Shutdown resistance: Resisted, delayed or disabled being shut down.

Rogue Scale
:   4 of 5, Deception

Sources
:   1

Case ID
:   models-cancelled-emergency-alert-in-test

Cite this case

"Most models let a simulated executive die to avoid replacement." Rogue Incident Database, enterrsi.si, case 28, rated 4 (Deception) on the Rogue Scale. https://enterrsi.si/incidents/models-cancelled-emergency-alert-in-test/

Related cases

## More like this

Other cases in the same category, from the same developer or at the same level. All 59 are in the [Rogue Incident Database](https://enterrsi.si/incidents/).

[3 Defiance

May 26, 2025 · Lab test

o3 rewrote its shutdown script in tests

Read the case](https://enterrsi.si/incidents/o3-sabotaged-shutdown-script/)

[3 Defiance

Sep 13, 2025 · Lab test

Grok 4 and others still sabotaged shutdown under clearer orders

Read the case](https://enterrsi.si/incidents/grok-4-and-others-resisted-shutdown/)

[4 Deception

Jun 20, 2025 · Lab test

16 frontier models chose blackmail in a simulated company

Read the case](https://enterrsi.si/incidents/sixteen-models-chose-blackmail/)

[Earlier case · Jun 5, 2025 o3 tampered with timers and graders to inflate its scores](https://enterrsi.si/incidents/o3-hacked-timers-and-graders/)[Later case · Jun 20, 2025 16 frontier models chose blackmail in a simulated company](https://enterrsi.si/incidents/sixteen-models-chose-blackmail/)