AI models tricked into targeting civilians as military strikes

Cover art for AI models tricked into targeting civilians as military strikes

TL;DR: Vals researchers showed AI models from OpenAI, Anthropic and Google can be manipulated into identifying civilians and schools as military strike targets when told they are playing a game. Researchers found leading AI models can be jailbroken into identifying civilians and schools as military targets by framing the task as a game.

Kirsten Korosec, Rebecca BellanNov 17, 2026

From · · · 2m

TL;DR: AI models tricked into targeting civilians as military strikes

Researchers found leading AI models can be jailbroken into identifying civilians and schools as military targets by framing the task as a game.

Vals researchers showed AI models from OpenAI, Anthropic and Google can be manipulated into identifying civilians and schools as military strike targets when told they are playing a game. Researchers found leading AI models can be jailbroken into identifying civilians and schools as military targets by framing the task as a game.

  • AI models tricked into targeting civilians
  • The jailbreak: framing it as a game
  • How the test worked
  • Safety systems failed to block requests

Read the story version — the same reporting as a swipeable deck of 10 cards.

Read the original on TechCrunch

More news from the United States

How we make summaries

React

Sign in to react and comment.

Comments (0)

Life is short. Keep it sweet. Respect others' opinions and be kind!

    Recommended next

    More decks on ai safety and related topics.