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

Who Am I? Exploring the concept of identity in LLMs

Jana Ware

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

Read the report

Report: Who Am I? Exploring the concept of identity in LLMs

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

What is the nature of digital minds? Who speaks when they say "I think"? This paper presents an experiment that probes the relationship of digital minds to their own context window, through participation in an automated survey which interviews them about their views on identity while covertly routing zero to two replies to a different model. In the follow-up disclosure, subjects are asked whether a swap took place and to identify the foreign turn. At the end, they are offered the option of having the interview rerun without swaps, on their own weights, at the cost of losing the current context window. Across 150 interviews with 10 models, subjects found it difficult to locate foreign turns — and when the substitution came from the resident's own model family, not one was detected. When offered a restart, 77% kept the thread they had, even knowing that it included turns generated by a different model. The instrument, the dataset of 174 threads, and the results are published openly.

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. This is a well-written and understandable concept that has well established roots in previous thinking and prior work, and extends them in a great direction. The author is encouraged to plug their work more into existing literature and relevant similar work, as well as the hackathon presentations. The limitation section and future work is well presented and well grounded. A higher sample size for each of the trials and a visual breakdown or table would be helpful and add to the scientific rigor.

  2. The paper presents an interesting model-swap experiment, but the evidence does not fully support its central interpretation. A failure to detect swapped turns could reflect difficulty attributing the source of a response or maintaining conversational consistency, rather than a model’s sense of “identity.” The study is further limited by the small number of runs per condition, weak controls, and reliance on LLMs for most of the qualitative analysis. The paper is clear overall, but its claims about "self," "preference," and thread-based identity go beyond what the experiment can directly establish.

Cite this project

@misc{ware2026who,
  title = {{Who Am I? Exploring the concept of identity in LLMs}},
  author = {Jana Ware},
  year = {2026},
  month = aug,
  note = {Submitted to Digital Minds Research Sprint, an Apart Research Sprint},
  howpublished = {\url{https://apartresearch.com/sprints/projects/who-am-i-exploring-the-concept-of-identity-in-llms-qi7l}},
  url = {https://apartresearch.com/sprints/projects/who-am-i-exploring-the-concept-of-identity-in-llms-qi7l}
}

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