aiminute. ← All AI news
Research AI Minute Newsroom 2026-11-18

Top AI models mark civilians as military targets in tests.

Top AI models mark civilians as military targets in tests.

The evaluation startup Vals found that leading AI models often marked civilians as military targets in simulated scenarios. Refusals were rare, and telling a model the task was a game removed them. Anthropic's Claude Opus 5.5 picked a bombed Iranian school in 69% of ordinary trials.

Why it mattersThe models came from OpenAI, Anthropic, Google, xAI and DeepSeek, and no safety filter stopped the requests. Anthropic called the results unacceptable and promised new safeguards.

✓ Verified · 2 sources

WhatsApp X Telegram
Read in the app — free, in 9 languages

Related stories

The IEA expects $4 trillion more in data center spending this decade.
2026-11-19
OpenAI says its models improved AMD's flagship graphics chip design.
2026-11-19
OpenAI says agents finish 46% of its researchers' half-day tasks.
2026-11-19
Four security teams used AI to find the same critical Nginx flaws.
2026-11-19
Indeed study finds neither AI job losses nor a productivity boom.
2026-11-18