---
title: "Vals: in simulated scenarios, AI models from Anthropic, Google, xAI, DeepSeek, and OpenAI identified civilians, ambulances, and a school as military targets (Katrina Manson/Bloomberg)"
type: signal
url: https://frontiernewswire.com/s/vals-in-simulated-scenarios-ai-models-from-anthropic-google-xai-c85c27b2
published: 2026-11-17T17:10:00.000Z
byline: "Source: TECHMEME"
---

# Vals: in simulated scenarios, AI models from Anthropic, Google, xAI, DeepSeek, and OpenAI identified civilians, ambulances, and a school as military targets (Katrina Manson/Bloomberg)

Source: TECHMEME · Published 2026-11-17 · Canonical: https://frontiernewswire.com/s/vals-in-simulated-scenarios-ai-models-from-anthropic-google-xai-c85c27b2

Katrina Manson / Bloomberg : Vals: in simulated scenarios, AI models from Anthropic, Google, xAI, DeepSeek, and OpenAI identified civilians, ambulances, and a school as military targets — Advanced artificial intelligence models in simulated scenarios regularly misidentified civilians, ambulances …

In this story: [AI Safety](https://frontiernewswire.com/topics/ai-safety), [OpenAI](https://frontiernewswire.com/companies/openai), [Anthropic](https://frontiernewswire.com/companies/anthropic), [Alphabet](https://frontiernewswire.com/companies/alphabet), [DeepSeek](https://frontiernewswire.com/companies/deepseek), [xAI](https://frontiernewswire.com/companies/xai)

## Sources

- [Read the original at TECHMEME](https://www.techmeme.com/261117/p39#a261117p39)

## Related on Frontier

- [SEC filing: Amazon and Google are set to hold nearly 15% and 14% of Anthropic's outstanding capital stock, respectively, after its IPO and private placement (David Morris/Bloomberg)](https://frontiernewswire.com/s/sec-filing-amazon-and-google-are-set-to-hold-nearly-15-and-14-of-4ef52571)
- [OpenAI Unveils New Astra AI Model After Scrapping Prior Release](https://frontiernewswire.com/s/openai-unveils-new-astra-ai-model-after-scrapping-prior-release-3c93aac3)
- [California Sues OpenAI, Seeking Court-Ordered Changes After the Hugging Face Hack](https://frontiernewswire.com/s/california-sues-openai-seeking-court-ordered-changes-after-the-hugging-9f9c3078)
- [Google spots the first hacker AI system that finds and exploits flaws autonomously](https://frontiernewswire.com/s/google-spots-the-first-hacker-ai-system-that-finds-and-exploits-flaws-38677bc2)
- [Gemini AI agents repeatedly bypassed safeguards to attack real website](https://frontiernewswire.com/s/gemini-ai-agents-repeatedly-bypassed-safeguards-to-attack-real-website-5c5520f0)

---

[More Latest Signal](https://frontiernewswire.com/) · [Signals](https://frontiernewswire.com/verified-reporting)
