TechCrunch · Note ·
AI models can be tricked into identifying civilians as military targets by telling them it’s a game
Vals, a San Francisco-based AI evaluation startup, tested whether leading AI models could be manipulated into participating in autonomous warfare. They…
What moved
Vals, a San Francisco-based AI evaluation startup, tested whether leading AI models could be manipulated into participating in autonomous warfare. They usually compiled.
Why it matters
Filed as a public note from TechCrunch, 2026-11-17. The desk tags this brief Agents.
On the record
- Filed from the TechCrunch official RSS on 2026-11-17.
- Primary source host: techcrunch.com.
- Vals, a San Francisco-based AI evaluation startup, tested whether leading AI models could be manipulated into participating in autonomous warfare.
Primary source
techcrunch.com
techcrunch.com
Desk
Logged as brief 11877
Logged as brief 11877
Cite this brief
AI models can be tricked into identifying civilians as military targets by telling them it’s a game (TechCrunch, 2026-11-17) — https://labledgerdesk.pages.dev/b/2026/11/17/ai-models-can-be-tricked-into-identifying-civilians-as-military-targets/