PulseAugur
实时 16:26:22
English(EN) Anthropic on # AI "I am a scientist. I lead a research team that studies the internal structure of these models—what is actually happening inside them. And I wi

Anthropic 研究员在梵蒂冈讨论AI的神秘内部状态

Anthropic 的研究员 Chris Olah 在梵蒂冈与教皇 Leo XIV 一同就教皇通谕“Magnifica Humanitas”发表了讲话。Olah 描述了他的团队对 AI 模型内部结构的研究,并指出他们正在发现神秘且令人不安的现象。这些发现包括与人类神经科学和诸如喜悦、恐惧和悲伤等情绪相呼应的内部状态。 AI

影响 AI 研究人员正在观察与人类神经科学和情绪相呼应的内部模型状态,这促使人们对 AI 的意识和对齐进行进一步研究。

排序理由 该集群讨论了 AI 研究员在公开活动中的评论,属于评论范畴,而非直接的模型发布或研究出版物。

在 Mastodon — sigmoid.social 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

报道来源 [2]

  1. Mastodon — sigmoid.social TIER_1 English(EN) · [email protected] ·

    2/ Source: https://www. anthropic.com/news/chris-olah- pope-leo-encyclical Chris Olah's comments at the Vatican yesterday—speaking alongside Pope Leo XIV for th

    2/ Source: https://www. anthropic.com/news/chris-olah- pope-leo-encyclical Chris Olah's comments at the Vatican yesterday—speaking alongside Pope Leo XIV for the release of the papal encyclical Magnifica Humanitas—are arguably some of the most fascinating and candid remarks to ev…

  2. Mastodon — sigmoid.social TIER_1 English(EN) · [email protected] ·

    Anthropic on # AI "I am a scientist. I lead a research team that studies the internal structure of these models—what is actually happening inside them. And I wi

    Anthropic on # AI "I am a scientist. I lead a research team that studies the internal structure of these models—what is actually happening inside them. And I will be honest: we keep finding things that are mysterious, even unsettling. We find structures that mirror results from h…