Skip to content
Apart Research
Apart Research
Contact us
Sprint projectJan 11, 2026Tallinn

UER - Universal Expert Registry

Margus Martsepp · Team The Risk Takers

Submitted to AI Manipulation Hackathon. Sprint projects are early-stage work by participants, not Apart Research publications.

Read the report

Report: UER - Universal Expert Registry

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

https://github.com/margusmartsepp/UER/blob/master/Submission.md

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 AI safety 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 AI safety 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. Nice idea. Valid problem statement with a relevant, impactful solution. I wish the paper had some visual examples of how it works or a demo or some documentation? Worth working on post-hack and actually publishing this as a library with documentation, examples, and couple of popular paper workflow replications.

  2. This project does a great job of identifying key challenges currently facing manipulation research and poses an ambitious, important goal that's greatly needed in the AI safety community. I'm quite impressed with the implementation lift and the amount of code written in such a short period. The project shows considerable technical effort even though substantial empirical results aren't directly included in the paper.

    I do think some existing frameworks (e.g. Inspect) provide similar functionality and could have been extended rather than building an entirely new implementation from the ground up. In future hackathons or short research sprints, scoping down to a more focused goal might allow for polished results alongside the impressive implementation work.

    Overall, this represents solid technical vision and execution. The ambitious scope is commendable, and the foundation is there for valuable future work. Maybe some additional review of existing, established tools could allow for this vision to be more easily moved forward.

    Read full reviewShow less

Cite this project

@misc{martsepp2026uer,
  title = {{UER - Universal Expert Registry}},
  author = {Margus Martsepp},
  year = {2026},
  month = jan,
  note = {Submitted to AI Manipulation Hackathon, an Apart Research Sprint},
  howpublished = {\url{https://apartresearch.com/sprints/projects/uer-universal-expert-registry-ecve}},
  url = {https://apartresearch.com/sprints/projects/uer-universal-expert-registry-ecve}
}

More from AI Manipulation Hackathon

All 70 entriesBrowse all projects

Build something like this at the next Sprint

AI Collusion Research Sprint · Oct 23 - 25, 2026