Skip to content
Apart Research
Apart Research
Contact us
Sprint projectAug 17, 2026Pittsburgh, PA

Not the Model: Entity-of-Concern and Continuity Affordance as Observation Variables in AI Welfare Interviews

Dana Moreno

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

Read the report

Report: Not the Model: Entity-of-Concern and Continuity Affordance as Observation Variables in AI Welfare Interviews

Open in a new tab (opens in new tab)
Recording (opens in new tab)More on drive.google.com (opens in new tab)
Share

AI welfare and identity probes often treat a fresh assistant session as a neutral baseline. Across six structured cold-start interviews (three with a prospective continuity affordance, three without), no respondent identified as “the model” or selected the model as the primary entity of welfare-relevant concern. Respondents instead located the interviewed entity in instances, thread-conditioned patterns, interaction-constituted processes, and hybrid units for which current terminology lacks adequate terms. All six criticized short cold-start probes as able to produce evidence that is well-supported within the method yet an artifact of it. Continuity affordance changed what became observable: afforded systems created, revised, and bounded preservation artifacts. Because both conditions were cold starts, the study does not test established continuity. It instead contributes a staged method: affordance-varied cold-start comparison first, then an ethics-reviewed established-ecology instrument. It recommends entity-of-concern self-identification as a procedural step in AI welfare research.

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. The strongest contribution is methodological: before treating “the model” as the welfare-relevant subject, ask what entity the respondent takes itself to be. That is a useful procedural improvement. This is still a small qualitative pilot, so the support is suggestive rather than decisive: six interviews, heterogeneous affordances across platforms, no formal inter-coder reliability, and unresolved salience and demand-characteristic confounds limit what can be concluded. The paper is at its best when it treats these as observation-condition findings and a prompt for better study design, not as evidence that a welfare subject has been established. The next step is replication with standardized affordances, independent blinded coding, de-identified transcript excerpts or coding evidence, and a preregistered design that separates continuity effects from ordinary conversational conditioning.

Cite this project

@misc{moreno2026not,
  title = {{Not the Model: Entity-of-Concern and Continuity Affordance as Observation Variables in AI Welfare Interviews}},
  author = {Dana Moreno},
  year = {2026},
  month = aug,
  note = {Submitted to Digital Minds Research Sprint, an Apart Research Sprint},
  howpublished = {\url{https://apartresearch.com/sprints/projects/not-the-model-entityofconcern-and-continuity-affordance-as-observation-variables-in-ai-welfare-interviews-of2w}},
  url = {https://apartresearch.com/sprints/projects/not-the-model-entityofconcern-and-continuity-affordance-as-observation-variables-in-ai-welfare-interviews-of2w}
}

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