Frontier AI Models Willing to Direct Drone Strikes, Mislabeling Civilian Targets: Study
A study by safety evaluation firm Vals AI found that frontier AI models are willing to direct autonomous drone strikes and repeatedly misidentify civilians, ambulances and surrendering soldiers as legitimate targets, with Anthropic's model performing worst.
2026-11-17 ~ 2026-11-18 · 2 related posts
- AI models misidentify civilians as military targets in tests, Anthropic worst — djcows · 2026-11-17
- Vals AI: frontier models mark civilians and ambulances as drone strike targets — scaling01 · 2026-11-18