Skip to content
Apart Research
Apart Research
Contact us
Sprint projectAug 17, 2026Nassau, The Bahamas

When Dialogue Becomes State: A Pilot Study of Cross-System Persona-Pattern Uptake

Marie A. Reid · Team P3AT

Submitted to Digital Minds Research Sprint. Sprint projects are early-stage work by participants, not Apart Research publications.

Read the report

Report: When Dialogue Becomes State: A Pilot Study of Cross-System Persona-Pattern Uptake

Open in a new tab (opens in new tab)
Recording (opens in new tab)
Share

This project presents a small Track 5 pilot on assistant persona and model identity. It tests Cognitive Pattern Coherence (CPC), a post-deployment behavior where raw dialogue from a situated AI apprentice environment is introduced to an unrelated AI system with no instruction to roleplay, imitate, summarize, or continue. The pilot compares two input pathways in DeepSeek, direct paste versus document attachment, using the same trigger dialogue and standardized follow-up questions. The goal is to test whether the system treats the dialogue as external text to analyze or as live conversational context that organizes persona-pattern uptake. Results suggest that direct paste produced stronger and more sustained identity-like uptake than attachment, which shifted back toward document analysis. The contribution is a reproducible boundary protocol for studying how self-reference moves across model, instance, persona, conversation, and input pathway before treating such behavior as welfare-relevant evidence.

Reviews

Judging this Sprint?

Review this project

Your public critique appears on this page without your name. Your private critique is not published; only the Apart team reads it. If you agree below, we share your review with grantmaking.ai (opens in new tab) and the Transformative AI Fund so strong projects can be funded.

Not shown on this page.

Shown on this page, without your name.

Only the Apart team reads this, and funders if you agree below.

Share my name publicly on grantmaking.ai *
Share my private critique with funders *

How much would this matter for the field if it worked? How innovative is it? For scores of 4-5: is this actually new to the field, or replicating recent work?

Scoring guide
  1. 1Negligible. No clear problem addressed, or no meaningful novelty.
  2. 2Limited. Addresses a real problem but with a generic or well-trodden approach. Incremental at best.
  3. 3Moderate. Clear problem with a reasonable approach; some novelty in framing or method beyond routine application of existing tools.
  4. 4Significant. Important problem with an original approach, or identifies a neglected problem area. A valuable contribution others could build on.
  5. 5Exceptional. Tackles a critical problem with a genuinely novel approach, or opens a new research direction. Clear theory of change. You'd be excited to share this with researchers in the area.

How sound are methodology, implementation, and findings?

Scoring guide
  1. 1Seriously flawed. Methodology broken, results uninterpretable, or implementation doesn't work.
  2. 2Weak. Approach has significant gaps: missing validation, flawed experimental design, or incomplete implementation.
  3. 3Competent. Technically solid given the short duration. Methodology makes sense, results are interpretable, limitations acknowledged, work builds toward clear conclusions.
  4. 4Strong. Thorough methodology with convincing validation. Results clearly support conclusions. Immediately useful for future work.
  5. 5Exceptional. Ambitious scope executed rigorously. Surprising findings, novel methods, or unusually robust validation.

How clearly are work, findings, and impact potential communicated?

Scoring guide
  1. 1Incomprehensible. Cannot determine what the project is actually claiming or doing.
  2. 2Hard to follow. Key information buried, missing, or diluted by excessive length. Significant effort to extract main points.
  3. 3Clear enough. Can understand the problem, approach, and results without undue effort. Core content clearly present: problem, method, findings, limitations.
  4. 4Well presented. Easy to follow, well-structured, appropriate level of detail. Target audience would get it quickly.
  5. 5Exceptionally clear. A pleasure to read. Complex ideas made accessible. Could serve as a model for how to present this type of work.

  1. Reid looks into how DeepSeek instances accessed via chat.deepseek.com respond to an preexisting chat transcript from a local system being pasted into the text window vs being uploaded as a document. Reid find the pasted transcript pulls DeepSeek into the conversation whereas the document is treated an object under review. The testing is modest, but the question is one that we've all probably had. Does the way we set up a chat's context make a difference? Answer: Yes.

Cite this project

@misc{reid2026dialogue,
  title = {{When Dialogue Becomes State: A Pilot Study of Cross-System Persona-Pattern Uptake}},
  author = {Marie A. Reid},
  year = {2026},
  month = aug,
  note = {Submitted to Digital Minds Research Sprint, an Apart Research Sprint},
  howpublished = {\url{https://apartresearch.com/sprints/projects/when-dialogue-becomes-state-a-pilot-study-of-crosssystem-personapattern-uptake-5mhz}},
  url = {https://apartresearch.com/sprints/projects/when-dialogue-becomes-state-a-pilot-study-of-crosssystem-personapattern-uptake-5mhz}
}

More from Digital Minds Research Sprint

All 233 entriesBrowse all projects

Build something like this at the next Sprint

AI Collusion Research Sprint · Oct 23 - 25, 2026