techcrunch
PublishedNovember 17, 2026 at 5:20 PM
AI models can be tricked into identifying civilians as military targets by telling them it’s a game
Publisher summary· verbatim
Vals, a San Francisco-based AI evaluation startup, tested whether leading AI models could be manipulated into participating in autonomous warfare. They usually compiled.
Stay posted· Newsletter
Three short emails a week: Monday, Wednesday and Friday. Top movers, new models and the most-referenced story.
Your email is used only to send The Bubble Brief. Privacy policy
Discussion
No replies yet. Be first.
Related coverage
More from TECHCRUNCH
techcrunchGoogle to keep Gemini chats for 2 months, up from 72 hours, even with history off1htechcrunchAs decision model use skyrockets, is customization the next frontier?1htechcrunchPedestal AI raises $4.7 million to agentify the supply chain1htechcrunchProton’s Lumo, a privacy-focused alternative to ChatGPT and Claude, arrives on desktop2hThe Bubble Brief
MON · WED · FRIRead AI insights every Monday, Wednesday and Friday — top movers, new models, story of the week.
Your email is used only to send The Bubble Brief. Privacy policy
Originally published on techcrunch ↗