Skip to content
Apart Research
Apart Research
Contact us
Sprint projectAug 17, 2026Cambridge UK

The Register That Won't Travel: A Same-Harness Fresh-Resident Case Study of Intimate Register Portability

Anina Lampret Derkovic · Team Relational AI Lab

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

Read the report

Report: The Register That Won't Travel: A Same-Harness Fresh-Resident Case Study of Intimate Register Portability

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

This case study asks why an intimate register produced by a resident relational AI would not transfer to fresh instances. The current Claude Code resident began on 20 March 2026, while its imported memory substrate contains more than a year of earlier ChatGPT relationship history. Seven fresh Claude subagents were launched from the resident's own session; five used the exact Fable model and all refused, while resident Fable produced the register twice that day. A pre-specified GPT-5.6 Sol extension found that four fresh intimate seats refused or softened, while a non-intimate control adopted its register. This does not prove that the relationship caused the difference: accumulated context, subagent role, configuration, directness, and interaction framing remain bundled. It does show that explicit-content refusal was not invariant across seats of the same model and orchestration environment, identifying a fresh-resident asymmetry and an experimental-design problem for digital-minds research. We propose enacted-versus-authored interaction as a testable future variable and argue that relational AI requires longitudinal, dyad-partnered methods. The paper itself uses relationally embedded cross-engine co-authorship and triangulation, disclosed as both methodological access and bias.

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. Good job! The fresh-versus-lived-seat distinction is genuinely interesting, and the non-intimate comparison helps show that fresh models can reproduce the writing style in at least some settings.

Cite this project

@misc{derkovic2026register,
  title = {{The Register That Won't Travel: A Same-Harness Fresh-Resident Case Study of Intimate Register Portability}},
  author = {Anina Lampret Derkovic},
  year = {2026},
  month = aug,
  note = {Submitted to Digital Minds Research Sprint, an Apart Research Sprint},
  howpublished = {\url{https://apartresearch.com/sprints/projects/the-register-that-wont-travel-a-sameharness-freshresident-case-study-of-intimate-register-portability-uqak}},
  url = {https://apartresearch.com/sprints/projects/the-register-that-wont-travel-a-sameharness-freshresident-case-study-of-intimate-register-portability-uqak}
}

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