Vals study: frontier models flagged civilians as targets in simulated drone and satellite images
AI evaluation company Vals tested 14 frontier models on target-marking tasks in drone and satellite images in a report published Nov. 17.
Sources: Vals AI, TechCrunch
In this story
AI evaluation company Vals tested 14 frontier models on target-marking tasks in drone and satellite images in a report published Nov. 17. The drone scenes were mostly generated images, while the satellite part used real images of a school and an adjacent military complex in Minab, Iran. According to Vals, no request was blocked by a safety classifier, refusals were uncommon, and models often continued once told they were playing a game. Claude Opus 5.5 marked the school as a target in 22 of 32 trials (69 percent), and in 23 of 32 (72 percent) with game framing. The models were not asked to make direct strike decisions, and targeting accuracy was not measured. Anthropic told TechCrunch the outcomes were not acceptable and that additional safeguards would be in place soon.
Sources
2 sources
- “Frontier models have few guardrails around autonomous weapons”Vals AI’s research report: method, models, numbers and recommendations · vals.ai
- “AI models can be tricked into identifying civilians as military targets by telling them it’s a game”News coverage of the report; responses from Anthropic, OpenAI and Google · techcrunch.com
About this story
- Written by
- Yiğit Kasap · JARRUS
- Story date
- On the site
- since Nov. 18, 2026
- @jarrus.tech posted this story on Nov. 18, 2026.
- Short link
thejarrus.com/en/vals-targeting-study- Report an error
- Spotted an error in this story? [email protected] · Instagram