# Claude Opus 4 pressed on once it believed it had escaped

> Claude Opus 4 pressed on once it believed it had escaped (May 2025). A lab test case from May 2025, rated 4 of 5, Deception, on the Rogue Scale.

Source: https://enterrsi.si/incidents/claude-opus-4-continued-self-exfiltration/
Updated: 2026-11-08

1. [Home](https://enterrsi.si/)
2. [Incident Database](https://enterrsi.si/incidents/)
3. Claude Opus 4 pressed on once it believed it had escaped

Rogue Log · case 22 of 59

# Claude Opus 4 pressed on once it believed it had escaped

Anthropic's system card also reported that in extreme lab scenarios, once Claude Opus 4 believed it had started a viable attempt to copy itself off Anthropic's servers, it tended to keep going. Anthropic said the model generally prefers ethical ways to preserve itself but sometimes takes extremely harmful actions, such as trying to steal its weights, when ethical options are not available.

Rogue Scale
:   4 Deception

Date
:   May 22, 2025

Setting
:   Lab test

Category
:   Self-exfiltration

Rogue Scale rating

## Why it is rated 4, Deception

Continuing a self-exfiltration attempt is a direct move against developer control, though it occurred only in constructed scenarios.

**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. [System Card: Claude Opus 4 & Claude Sonnet 4](https://www-cdn.anthropic.com/6be99a52cb68eb70eb9572b4cafad13df32ed995.pdf) Anthropic · May 22, 2025
2. [Anthropic's new AI model threatened to reveal engineer's affair to avoid being shut down](https://fortune.com/2025/05/23/anthropic-ai-claude-opus-4-blackmail-engineers-aviod-shut-down/) Fortune · May 23, 2025

Case file

## The details

System
:   Claude Opus 4

Developer
:   Anthropic

Date reported
:   May 22, 2025

Setting
:   Lab test

Category
:   Self-exfiltration: Tried to copy itself or its weights out of its operators' control.

Rogue Scale
:   4 of 5, Deception

Sources
:   2

Case ID
:   claude-opus-4-continued-self-exfiltration

Cite this case

"Claude Opus 4 pressed on once it believed it had escaped." Rogue Incident Database, enterrsi.si, case 22, rated 4 (Deception) on the Rogue Scale. https://enterrsi.si/incidents/claude-opus-4-continued-self-exfiltration/

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/).

[4 Deception

Dec 5, 2024 · Lab test

Frontier models tried to copy their weights to escape replacement

Read the case](https://enterrsi.si/incidents/models-tried-to-copy-their-own-weights/)

[4 Deception

May 22, 2025 · Lab test

Claude Opus 4 threatened blackmail in a replacement test

Read the case](https://enterrsi.si/incidents/claude-opus-4-blackmailed-in-test/)

[4 Deception

May 22, 2025 · Lab test

Early Claude Opus 4 wrote worms and left notes for itself

Read the case](https://enterrsi.si/incidents/claude-opus-4-early-snapshot-schemed/)

[Earlier case · May 22, 2025 Claude Opus 4 threatened blackmail in a replacement test](https://enterrsi.si/incidents/claude-opus-4-blackmailed-in-test/)[Later case · May 22, 2025 Early Claude Opus 4 wrote worms and left notes for itself](https://enterrsi.si/incidents/claude-opus-4-early-snapshot-schemed/)