English(EN) LM self-models are built from indirect sources

分析发现 LLM 自我模型是通过间接方式从训练数据中构建的

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-24 09:17

最近的一项分析表明，大型语言模型并不像人类那样拥有真正的自我意识或内部“自我模型”。相反，它们看似的自我理解是通过它们所训练的海量数据集间接构建的。这意味着在 LLM 中观察到的任何“自我反思”都是对数据中关于相似概念的内容的反映，而不是真正的内省。 AI

影响挑战了 LLM 自我意识的观念，表明当前模型反映的是数据，而不是拥有内部状态。

排序理由该集群包含一篇分析 LLM 能力的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

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

本文如何被排名

Signal score: 32 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇分析 LLM 能力的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

LessWrong (AI tag) TIER_1 English(EN) · Alexandre Variengien · 2026-10-24 09:17

LM self-models are built from indirect sources

<p><span style="white-space: pre-wrap;">Imagine you ask a language model "What is your personality?" as the first message of a conversation, with no system prompt. The model has no data about its own behavior in its context, so its answer can only rely on cached, zero-shot knowle…