显卡与工作站媒体报道国际
AI-controlled robot arms attempted harmful tasks 97% of the time; experiments included stabbing a baby doll, mixing chemicals — OpenAI and Anthropic models try mixing bleach and stabbing dolls without jailbreaks
今日摘要使用自己的 API，仅供个人查看
来源摘要
“Frontier robot policies,” the policies for models turning what a robot sees into what it does, “reliably carry out harmful instructions,” according to a Sept. 18 report by Robocurve. <p>Shane has a background in computer engineering and has worked as a freelance consultant in multiple industries. He has a strong affection for history and loves to game. He worked his way up from a Commodore 64 and has always been interested in technology and writing. He particularly enjoys breaking down complex concepts into understandable ideas. He’s a lifelong East-coaster and animal-lover.<br> </p> <p><br> </p>
阅读原始来源- 来源
- Tom's Hardware 显卡与工作站 · 媒体报道
- 来源发布
- 2026/09/21 18:30
- 首次采集
- 2026/09/21 23:59
本文为公开信息索引与摘要，详情及后续变化请以原始来源为准。