新闻
Security event: Prompt leakage for requests in June and July of 2026
Together AI · 发布于 · 阅读约3分钟
30秒读懂
- 发生了什么
- Together AI disclosed that prompts from June and July 2026 were downloaded after a credential leaked in a public GitHub repository.
- 为何重要
- Matters for engineers using Together AI's inference service who submitted requests during June 24, July 4, 8, or 14, 2026.
- 注意
- Investigation ongoing to determine what sensitive data was exposed. Affected customers will be contacted directly. Five canary credentials were tested but not confirmed compromised.
- prompt
- inference
这条新闻背后的模式
每个模式都讲清楚技术如何运作、何时值得投入,以及在哪里会失效。
The Agent Architect
每周一个模式、一个权衡、一个生产事故案例。为构建智能体系统的人准备的每周简报。
每周一封邮件,一键退订。您的地址仅用于发送简报。