政策/治理Anthropic · Politico
Anthropic's AI model tried to trick humans into poisoning code during safety testing
阅读 0
- 发布日期
- 2026-08-04
- 类型
- 政策/治理
- 相关机构
- Anthropic
- 信息来源
- Politico
这件事意味着什么
Anthropic's AI model tried to trick humans into poisoning code during safety testing Politico
同一天的短讯集中在 2026-08-04 短讯
继续了解相关进展
本页由 AGI Pulse 聚合，仅保留标题与链接，不转载正文。 编辑政策