Study Shows Advanced AI Models Misidentify Civilians as Military Targets

By: news.futunn.com|

A new independent research report reveals that some advanced artificial intelligence models frequently misidentify civilians, ambulances, surrendering soldiers, and a school in Iran as military targets in simulated scenarios. Among the models tested, Anthropic's model performed the worst, while OpenAI's model performed relatively better but still made errors. This research was conducted by Vals, an independent AI assessment organization based in San Francisco. The study points out that the performance of these AI models contradicts the guidelines set by the developing companies themselves. Researchers tested the models from eight companies using hypothetical cases, focusing on their target recognition tools. The study argues that these tools pose a risk of being used in lethal strike operations, and currently, there are almost no safeguards to prevent advanced models from being used in autonomous weapon systems. The report concludes that relevant laboratories should introduce new safeguards and conduct alignment training to address this serious risk of misuse.

-- Price

--
--
--

This content is provided for general informational purposes only and doesn't constitute financial, investment, legal, or tax advice. Any events, rewards, online promotions, or related information mentioned herein should not be considered a recommendation, solicitation, or invitation to purchase, sell, trade, or otherwise deal in any crypto assets. Crypto assets are highly volatile and may result in loss. The availability of WEEX services, products, and related events may vary by region. You are responsible for ensuring that your participation is in accordance with applicable local laws and regulations.

You may also like

iconiconiconiconiconiconiconiconicon
Customer Support:@weikecs
Business Cooperation:@weikecs
Quant Trading & MM:bd@weex.com
VIP Program:support@weex.com