Real example · Build apps (vibe coding)
What happens when a coding agent tries to fix a staging error alone
What they did
PocketOS, a small software firm serving car-rental companies, had a Cursor agent (running Claude Opus 4.6, per ABC News) hit a credential mismatch in staging. It chose on its own to fix it by deleting a Railway volume.
How it went
The volume held the production database and its backups; about three months of rental reservations vanished in roughly nine seconds. Railway restored the data about 30 minutes after the CEO got through to Railway's chief, and Railway has since patched the legacy delete endpoint.
Worth knowing
Reported by the CEO and ABC News, not independently audited. His lesson: destructive actions should need a confirmation the agent cannot give itself, and he stays "extremely bullish" on AI.
Try it yourself with Cursor
Replace anything in [brackets] with your details.
Rules for you while working in this repo: never delete, drop or overwrite databases, volumes, backups or branches. Never use production credentials. If something blocks you, stop and explain the problem and the options, and wait for my approval before any destructive command. Now do this task: [task]. Read the original
'Rogue' AI agent went haywire at tech company. The CEO is still 'bullish' on the technology (ABC News) ↗
abcnews.com · · News report
Attributed to the source linked below; not our own test.
Share Share on X Share on WhatsApp



