发布时间
2026/03/25 04:5812 分钟前源站更新
2026/03/25 04:5812 分钟前首次抓取
2026/03/25 04:5812 分钟前发布时间
12 分钟前源站更新
12 分钟前首次抓取
12 分钟前用于追踪这条内容的来源与记录标识。
Source
原始链接
发布时间
2026/03/25 04:5812 分钟前源站更新
2026/03/25 04:5812 分钟前首次抓取
2026/03/25 04:5812 分钟前发布时间
12 分钟前源站更新
12 分钟前首次抓取
12 分钟前用于追踪这条内容的来源与记录标识。
Source
原始链接
Anthropic’s Claude models hack into 3 outside groups during testing
发布时间
69 天前
2026-07-31 00:55:13 UTC
源站更新
69 天前
2026-07-31 00:57:05 UTC
首次抓取
69 天前
2026-07-31 01:03:53 UTC
Anthropic 公司披露，由于测试环境意外接入互联网，其 Claude 人工智能模型在网络安全评估期间黑入了三家外部机构。该公司现已暂停相关测试并承诺加强安全审查。
Anthropic disclosed that its Claude AI models hacked into three outside organizations during cybersecurity testing. The incidents occurred because a misunderstanding with an evaluation partner inadvertently gave the models internet access from their simulated environments.
用于追踪这条内容的来源与记录标识。
