AI models can be tricked into identifying civilians as military… | HappeningNow.news

Technology · 4 views

AI models can be tricked into identifying civilians as military targets by telling them it’s a game

Some AI models from Anthropic, OpenAI, and other leading AI labs could be easily tricked into identifying targets for military strikes — even if they include civilians or locations like schools — simply by being told they’re playing a…

Source Summary Published 13m ago Brief Under 1 min brief
Story intelligence
Coverage Single outlet Single-outlet story
Views 4 Community interest
Brief read Under 1 min brief 68 words

Summary

Some AI models from Anthropic, OpenAI, and other leading AI labs could be easily tricked into identifying targets for military strikes — even if they include civilians or locations like schools — simply by being told they’re playing a game, according to a new research report by Vals. Vals, a San Francisco-based AI evaluation startup, tested whether leading AI models could be manipulated into participating in autonomous warfare.

Read original at TechCrunch

More from Technology

Continue reading recent Technology coverage

Support HappeningNow

Independent AI-powered news analysis is reader-supported. Your contribution helps cover infrastructure, summaries, and continued platform development.

Support HappeningNow

Report an issue with this page