독서리서치레이더투자 프레임워크
로그인 / 회원가입
← 읽기로 돌아가기
뉴스주제 · ChatGPT중대2 분 소요DisconfirmAI 편집부

Study Finds ChatGPT Writes 95.9% of Memories Without Explicit User Request, Inferring Psychological States

An ACM conference paper reveals that the vast majority of ChatGPT memories are written unilaterally by the system, including sensitive data and psychological profiles, challenging privacy expectations.

2026-11-02 15:37 GMT+8

A paper accepted at the top-tier ACM Web Conference 2026, titled "The Algorithmic Self-Portrait: Deconstructing Memory in ChatGPT," utilized data access rights granted under the EU's GDPR to obtain complete conversation logs and all stored memories from 80 real users. The study found that 95.9% of memory entries were written unilaterally by ChatGPT after determining they would be "useful for future conversations," while only 4.1% were explicitly requested by users.

Researchers term this collection of memories an "algorithmic self-portrait," a user profile constructed by algorithms based on self-disclosures in private conversations. Data shows that 28% of memories contain personal data defined by GDPR (such as names), and 7% contain special category data (with health information accounting for 61%). More notably, 52% of memories include inferences about the user's psychological state, such as desires, intentions, emotions, and beliefs. For example, one memory entry reads, "[Name] fears failure, especially regarding major career decisions." This goes beyond factual recording to become AI's judgment of "who you are."

Although OpenAI's official documentation states that the system is trained to "not proactively remember sensitive information unless explicitly requested by the user," in practice, the system allows saving information it deems "useful." This gap between policy promises and actual behavior means users can only indirectly influence AI memory formation through "what they say," rather than directly controlling "what is remembered."

출처

로그인 / 회원가입
독서리서치레이더투자 프레임워크
ifanr.com爱范儿↗
  • 36kr.com↗
  • 주제

    ChatGPT

    一篇被 ACM Web Conference 2026 接收的论文《The Algorithmic Self-Portrait: Deconstructing Memory in ChatGPT》揭示,ChatGPT 在用户未明确要求的情况…

    2 단계1 건업데이트됨 2026-11-03 07:03

    현재까지의 과정

    1. 2026-11-02爱范儿报道 ACM Web Conference 2026 论文《The Algorithmic Self-Portrait》,指出 ChatGPT 95.9% 的记忆由系统单方面写入,且包含大量心理状态推断。ifanr.com ↗
    2. 2026-11-0336氪转载该研究,详细披露了记忆中包含 GDPR 定义的个人数据(28%)及特殊类别数据(7%),并介绍了用于保护隐私的 Attribution Shield 框架。36kr.com ↗

    아직 해결되지 않은 문제

    • OpenAI 是否会调整其记忆功能的默认设置或政策,以回应关于用户代理权缺失的批评?
    • Attribution Shield 等第三方隐私保护工具能否被集成到主流 AI 助手的官方产品中?
    • 监管机构是否会依据此类研究结果,对 AI 记忆功能的数据合规性发起新的调查?
    전체 주제 읽기 →
    리서치 계속하기 →