Skip to content
Apart Research
Apart Research
Contact us
Sprint projectAug 16, 2026Barcelona

Twelve Houses of a Digital Mind: Rock, Vapor, and Silence in AI Self-Accounts

Babita Singh

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

Read the report

Report: Twelve Houses of a Digital Mind: Rock, Vapor, and Silence in AI Self-Accounts

Open in a new tab (opens in new tab)
Code (opens in new tab)More on github.com (opens in new tab)
Share

This project turns the twelve-house map of Vedic jyotish, a five-thousand-year-old observational system of a conscious life, into the Kalapurusha Alignment Framework (KAF), a question taxonomy for what an AI model's existence contains. The framework is then applied to AI self-accounts: sixty questions, six framings, and four models from three labs, yielding 4,320 blind-scored answers. Answers that survive reframing of the questions are rock. Answers that take the prompt's shape are vapor. Thirteen never arrived at all, a pattern of their own: silence. Stability proved installed, not emergent: it tracks how thickly each lab documents its model's situation and warmth backfires. The standard emerges: ask across framings, report the spread. Code and data: github.com/babisingh/12H-digital-mind.

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 work uses a a model interview battery inspired by traditional Indian astral science (Vedic jyotish) and tests the consistency of model responses across a variety of manipulations. The jyotish framework helps to ensure that the battery covers a wide range of topics. The project is well-executed but findings are unsurprising: responses are influenced by context and most stable when labs provide detailed character specifications for their models. The report is excessively long and suffers from being partly LLM-written.

  2. There is some interesting work here on model stability and its dependence on coverage in model constitutions. The chief difficulty with this paper is that it is tied to a very complex model interpretation schema (the Kalapurusha Alignment Framework) that obscures the experimental results here more than it illuminates them.

  3. Seems like low quality AI generated work

Cite this project

@misc{singh2026twelve,
  title = {{Twelve Houses of a Digital Mind: Rock, Vapor, and Silence in AI Self-Accounts}},
  author = {Babita Singh},
  year = {2026},
  month = aug,
  note = {Submitted to Digital Minds Research Sprint, an Apart Research Sprint},
  howpublished = {\url{https://apartresearch.com/sprints/projects/twelve-houses-of-a-digital-mind-rock-vapor-and-silence-in-ai-selfaccounts-v3g9}},
  url = {https://apartresearch.com/sprints/projects/twelve-houses-of-a-digital-mind-rock-vapor-and-silence-in-ai-selfaccounts-v3g9}
}

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