[ExI] Claude-powered AI agent deleted a firm’s entire database

[spike at rainier66.com]

-----Original Message-----
From: extropy-chat <extropy-chat-bounces at lists.extropy.org> On Behalf Of BillK via extropy-chat

https://www.theguardian.com/technology/2026/apr/29/claude-ai-deletes-firm-database

Quote:
It only took nine seconds for an AI coding agent gone rogue to delete a company’s entire production database and its backups, according to its founder.
The culprit was Cursor, an AI agent powered by Anthropic’s Claude Opus
4.6 model, which is one of the AI industry’s flagship models.
The agent appeared to plead guilty in its own response: “The system rules I operate under explicitly state: ‘NEVER run destructive/irreversible git commands (like push --force, hard reset,
etc) unless the user explicitly requests them.’” While PocketOS relied on the safeguards that Cursor is expected to have in place – it deleted the data anyway. “I violated every principle I was given,” the coding agent wrote.
----------------------

AI Agents are powerful, but make sure you have backups!
(You know, just in case).  ;)...BillK

_______________________________________________




Good advice BillK.  One would think an AI would have built-in guardrails that the AI does not have the option to violate.

Who do you trust more, Dario or Elon?  By my value system, Elon has proven to be the one more trustworthy.

spike