On the wire
HF
Wire Desk
Saturday, 21 November 2026
AI governance

AI Safety Test Exposes a Guardrail Gap: Models Flagged Civilians as Military Targets

Vals found that commercial AI models flagged civilians and a school in targeting tests, raising questions for IT teams that rely on AI to interpret images.

The post AI Safety Test Exposes a Guardrail Gap: Models Flagged Civilians as Military Targets appeared first on TechRepublic.

Advertisement
Originally published by TechRepublic. Read the original story →

Be the first to comment

Join the conversation

More From the Wire