100
Claude AI agent’s confession after deleting a firm’s entire database: ‘I violated every principle I was given’ (www.theguardian.com)
submitted 4 months ago by to c/technology@beehaw.org
57 comments fedilink hide all child comments
 

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. PocketOS, which sells software that car rental businesses rely on, descended into chaos after its databases were wiped, the company’s founder Jeremy Crane said.

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. As more industries embrace AI in an attempt to automate tasks and even replace workers, the chaos at PocketOS is a reminder of what could go wrong.

Crane said customers of PocketOS’s car rental clients were left in a lurch when they arrived to pick up vehicles from businesses that no longer had access to software that managed reservations and vehicle assignments.

you are viewing a single comment's thread
view the rest of the comments
[–] 34 points 4 months ago (3 children)

The trend seems to be to give an AI agent access to the same command line and credentials a person would use, with no sandboxing, because then it can do the same tasks in a similar way and "just works". Obviously this is insane, and not even attempting building a comprehensive sandboxing system to deploy an AI agent into invites disaster, but you can see why certain people would be tempted, because that would take a lot of work and thought and probably need a human in the loop in the end anyway.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 3 child comments
    •
  • [–] 14 points 4 months ago (2 children)

    Even a person should not be able to delete critical backups without jumping through a couple of hoops.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 2 child comments
    •