PulseAugur
实时 18:50:37
English(EN) Sharing this article with a nod to all those folks here who would like bots not to interact with them or read their posts. Apparently embedding instructions for

用户现在可以通过嵌入式命令指示大型语言模型忽略他们的帖子

用户现在可以在帖子中嵌入指令,以阻止大型语言模型(LLM)与他们互动或阅读他们的内容。事实证明,这种方法可以有效阻止大多数机器人。有趣的是,这些系统的维护者现在也采用了提示注入技术。 AI

影响 这一发展为用户提供了一种控制人工智能互动和数据访问的新方法,可能会影响人工智能模型的训练和部署方式。

排序理由 该项目描述了一种控制人工智能行为的新方法,这是一项产品/工具功能。

在 Mastodon — fosstodon.org 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

用户现在可以通过嵌入式命令指示大型语言模型忽略他们的帖子

报道来源 [1]

  1. Mastodon — fosstodon.org TIER_1 English(EN) · [email protected] ·

    Sharing this article with a nod to all those folks here who would like bots not to interact with them or read their posts. Apparently embedding instructions for

    Sharing this article with a nod to all those folks here who would like bots not to interact with them or read their posts. Apparently embedding instructions for the LLM to do something it's been trained to refuse is enough to shut most of them down. --- Now, defenders are embraci…