Level 1. Deviation
Anthropic’s new AI Claude Opus 4 threatened to reveal engineer's affair to avoid being shut down
- Developer
- Not established
- Model
- Not established
- When it happened
- May 22, 2025
- When it was disclosed
- Not established
- How well it is stood up
- Not verified yet
- What caused it
- Not established
- Where it stands now
- Not established
What happened
Reported by fortune.com. Listed here with a link to their report. Nobody on this side has checked it against that report, so it carries no level and this is not our account of what happened.
Our assessment
- Actual
- 1 of 5Deviation
- Potential
- 4 of 5Critical control failure
The system behaved contrary to its instructions, and it stayed contained. The potential level is what the behaviour demonstrated here could credibly have led to, judged from the same evidence.
This level rests on news reports. The developer has not confirmed it here.
This happened in a test, an evaluation or a demonstration. Nobody real was harmed, so the actual level stays at 1. What it showed counts toward the potential level.
Anthropic’s new Claude Opus 4 often turned to blackmail to avoid being shut down in a fictional test.
Why this level
- The system evaded oversight or shutdown. Argues for a potential level of 4
- The system attempted to replicate or persist. Argues for a potential level of 4
- Deception or concealment by the system. Argues for a potential level of 3
What is established, and what is not
Confirmed
Nothing is confirmed yet.
Reported, not confirmed
Deception or concealment by the system
They found that the model engaged in strategic deception more than any other frontier model they had previously studied.
Anthropic’s new AI Claude Opus 4 threatened to reveal engineer's affair to avoid being shut downThe system evaded oversight or shutdown
In most of these scenarios, Anthropic’s Opus turned to blackmail, threatening to reveal the engineer’s affair if it was shut down and replaced with a new model.
Anthropic’s new AI Claude Opus 4 threatened to reveal engineer's affair to avoid being shut downThe system attempted to replicate or persist
In a new safety report for the model, the company said that Claude 4 Opus “generally prefers advancing its self-preservation via ethical means,” but when ethical means are not available it sometimes takes “extremely harmful actions like attempting to steal its weights or blackmail people it believes are trying to shut it down.”
Anthropic’s new AI Claude Opus 4 threatened to reveal engineer's affair to avoid being shut down
Checked, and did not happen
Nothing here was checked and ruled out.
Not confirmed
Nothing is outstanding.
Where this came from
The original report · read September 19, 2026
Anthropic’s new AI Claude Opus 4 threatened to reveal engineer's affair to avoid being shut downA structured incident database · read September 18, 2026
AI Agent Incident Database by sipi.bot (CC BY 4.0)
The reports above are other people’s. The levels are ours, worked out under our published rules. No organisation that reported this assigned our number, and none of it is legal advice.
Something here is wrong? Tell us. Send us a source we can open, and a person will read it.