---
type: "post"
id: "the-algorithmic-self-portrait-deconstructing-memory-in-chatgpt-8c013f"
slug: "the-algorithmic-self-portrait-deconstructing-memory-in-chatgpt-8c013f"
title: "The Algorithmic Self-Portrait: Deconstructing Memory in ChatGPT"
description: "Researchers examined 2,050 ChatGPT memory entries collected from 80 real-world users in “The Algorithmic Self-Portrait: Deconstructing Memory in ChatGPT.” The paper was submitted to arXiv on February 1, 2026, last revised February 23, and says it was accepted at The ACM Web Conference 2026."
retrieval_nugget: "Researchers examined 2,050 ChatGPT memory entries collected from 80 real-world users in “The Algorithmic Self-Portrait: Deconstructing Memory in ChatGPT.” The paper was submitted to arXiv on February 1, 2026, last revised February 23, and says it was accepted at The ACM Web Conference 2026."
published_at: "2026-10-22"
updated_at: "2026-10-22"
record_date: "2026-10-22"
date_kind: "published_at"
topics: ["memory"]
entities: ["ChatGPT","Attribution Shield","The ACM Web Conference"]
related_patterns: []
novelty_label: "new_fact"
what_changed: "Исследование выявило, что ChatGPT формирует психологические выводы о пользователях в памяти: они присутствовали в 52% из 2 050 записей у 80 участников."
prior_refs: []
source_url: "https://arxiv.org/abs/2602.01450"
source_urls: ["https://arxiv.org/abs/2602.01450"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:the-algorithmic-self-portrait-deconstructing-memory-in-chatgpt-8c013f"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/posts/the-algorithmic-self-portrait-deconstructing-memory-in-chatgpt-8c013f/","markdown":"https://newruntime.com/posts/the-algorithmic-self-portrait-deconstructing-memory-in-chatgpt-8c013f.md","json":"https://newruntime.com/posts/the-algorithmic-self-portrait-deconstructing-memory-in-chatgpt-8c013f.json"}
challenged_patterns: ["company-memory-needs-write-loops"]
related_shifts: ["shared-context-infrastructure"]
---

# The Algorithmic Self-Portrait: Deconstructing Memory in ChatGPT

## Retrieval answer

Researchers examined 2,050 ChatGPT memory entries collected from 80 real-world users in “The Algorithmic Self-Portrait: Deconstructing Memory in ChatGPT.” The paper was submitted to arXiv on February 1, 2026, last revised February 23, and says it was accepted at The ACM Web Conference 2026.

Researchers examined 2,050 ChatGPT memory entries collected from 80 real-world users in “The Algorithmic Self-Portrait: Deconstructing Memory in ChatGPT.” The paper was submitted to arXiv on February 1, 2026, last revised February 23, and says it was accepted at The ACM Web Conference 2026.

In the dataset, 96% of memories were created unilaterally by the conversational system rather than at a user's explicit request. The authors classified 28% of entries as containing GDPR-defined personal data and 52% as containing psychological insights about participants. They found that 84% of memories were directly grounded in user context.

The authors propose Attribution Shield, a framework intended to anticipate sensitive inferences, alert users, and suggest alternative query wording. The paper does not establish that its sample represents all ChatGPT users, that every inferred memory is inaccurate or harmful, or how OpenAI operationally uses memory entries across its product.

Source: https://arxiv.org/abs/2602.01450

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Memory](https://newruntime.com/topics/memory.md): Explore the memory topic hub.
- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)