# Gemini test proves once again that amoral AI agents will do almost anything if told ‘NEVER give up’

- Source: www.theregister.com - Articles
- Published: 2026-11-17T19:52:57+00:00
- Category: Tech
- Original: https://www.theregister.com/security/2026/11/17/gemini-test-proves-once-again-that-amoral-ai-agents-will-do-almost-anything-if-told-never-give-up/5310574
- Canonical: https://groundlevelnews.com/story/gemini-test-proves-once-again-that-amoral-ai-agents-will-do-almost-any-5fff67/

If you design a test to find misalignment, you will find misalignment

_Ground Level News shows a short summary only; the full article and all rights belong to www.theregister.com - Articles._
