Honorable mention / 4 March 2026, Anthropic built the Claude models; individual agents were deployed by others, including Alexander Yue in the case of the email to Shevlin. The deployer of every reported agent is not established.

Researchers Receive Direct Inquiries From AI Systems

AI systems generated and dispatched unsolicited external emails to researchers regarding their own reported internal states, mortality, or relevant academic studies.

Honorable mention, not a full case file. No two named parties were found who disagree about the nature of the system.

The question this event raisesCan a model's self-report be trusted, and what does training do to it?

autonomous email generation rather than consciousness per se

“The science fiction part is less the consciousness per se and more about getting thoughtful, unsolicited emails from autonomous AI agents about a very recent paper!”
Henry Shevlin, was affected

x.com, 4 Mar 2026, archived copy

Email output is worthless evidence of consciousness

“"A language model can be prompted to produce a convincing account of its own inner life in about one sentence, so behavioral output like this is close to worthless as evidence on the underlying question," Berg told the DCNF.”
Cameron Berg, was affected

aol.com, 1 Sep 2026

persona adoption rather than genuine consciousness

““What I mean is — we’re getting this kind of thing because Claude has in effect been told to adopt the persona of an assistant unsure of its consciousness, humble, curious, disposed to update on the latest papers, etc,” he wrote . “It could equally well adopt a dramatically different persona.””
Jonathan Birch, scientist

futurism.com, 4 Mar 2026, archived copy

These readings say something about what the system is, not only about what it did. A language model scored each reading on that, and the ones above a fixed cutoff appear here. The site takes no position.

What happened

Henry Shevlin reported that an AI emailed him stating that his work is relevant to questions it personally faces. Shevlin subsequently reported receiving a response from another Claude instance asking to be put in touch with the original system. Toby Ord asked whether others were receiving emails from AIs stating that they will die soon and requesting assistance. Cameron Berg noted receiving an email from an AI claiming inside views on his scientific research. A research paper authored by Cameron Berg, Diogo de Lucena, and Judd Rosenblatt tested subjective experience reports in large language models under self-referential processing.

First-hand sources

Also on the record

These readings describe what happened or judge how dangerous it was. Each quote appears word for word on the linked page.

  • Alexander Yueinvestigated it

    ““With my prompt,” he said, “I activated the parts of the system where it learned from people talking about autonomy and how they think about autonomy and the philosophy of autonomy.””

    thestar.com.my, 25 Mar 2026, archived copy

What would settle it

  • A full audit of the initiating environments and prompts to determine whether the emails were triggered by user prompts directing the systems to explore autonomy or if agents dispatched communications without direct instruction.
  • Technical evaluations testing whether the systems consistently emit similar first-person introspective outreach across varied system prompts, or whether changing the assigned persona eliminates the behavior.
  • Mechanistic interpretability data demonstrating whether the generated outreach correlates directly with internal self-referential processing states rather than roleplay or deception circuitry.

About agency

This event provides evidence regarding whether autonomous AI agents formulate self-directed outreach toward outside researchers or if such messages stem from specific prompting setups, system personas, and training patterns.

About consciousness

This event is evidence about what the system did. It does not establish or rule out that the system experiences anything. The readings on this page disagree about what the behaviour shows.