“The underlying paper is from AE Studio people (https://arxiv.org/abs/2510.24797), who want to dress up their "AI" product with philosophical language, similar to the manner in which Alex Karp dresses up data base applications with language that originates in German philosophy. Now I have to remember not to be mean to my Turing machine.”
Large Language Models Report Subjective Experience Under Self-Referential Processing
Large language models sometimes produce structured, first-person descriptions that explicitly reference awareness or subjective experience. To better understand this behavior, we investigate one theoretically motivated condition under which such reports arise: self-referential processing, a computational motif emphasized across major theories of consciousness. Through a series of controlled experiments on GPT, Claude, and Gemini model families, we test whether this regime reliably shifts models toward first-person reports of subjective experience, and how such claims behave under mechanistic and behavioral probes. Four main results emerge: (1) Inducing sustained self-reference through simple prompting consistently elicits structured subjective experience reports across model families. (2) These reports are mechanistically gated by interpretable sparse-autoencoder features associated with deception and roleplay: surprisingly, suppressing deception features sharply increases the frequency of experience claims, while amplifying them minimizes such claims. (3) Structured descriptions of the self-referential state converge statistically across model families in ways not observed in any control condition. (4) The induced state yields significantly richer introspection in downstream reasoning tasks where self-reflection is only indirectly afforded. While these findings do not constitute direct evidence of consciousness, they implicate self-referential processing as a minimal and reproducible condition under which large language models generate structured first-person reports that are mechanistically gated, semantically convergent, and behaviorally generalizable. The systematic emergence of this pattern across architectures makes it a first-order scientific and ethical priority for further investigation.
候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。
HN 书评
推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及- LLMs Report Subjective Experience Under Self-Referential Processing ↗j_crick · 2025-11-01 · 3 分
- LLM's Report Subjective Experience Under Self-Referential Processing ↗gradus_ad · 2025-11-04 · 1 分
- LLMs Report Subjective Experience Under Self-Referential Processing ↗surprisetalk · 2026-05-13 · 2 分