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

RiskLab

Yuvan Aarya Chikka · Team Ultraviolet Chikorita

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

Read the report

Report: RiskLab

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

A comprehensive, production-ready system for measuring, analyzing, and governing manipulative behavior in AI systems. Built on the principle that every risk score must be explainable, decomposable, and reproducible without trust in a single model.

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. The idea of using multiple evaluator signals to assess risk is well motivated, and the evaluation setup is clearly described. The framework works as intended as a proof of concept.

    However, the experiments rely on a small number of prompts and relatively mild framing changes, which makes it difficult to tell whether the observed score differences reflect meaningful risk signals or general prompt sensitivity. While multiple evaluator outputs are collected, there is limited analysis of where evaluators disagree or which signals are most informative.

    The project would benefit from stronger framing contrasts and more focused analysis of evaluator disagreement. Overall, this is a solid prototype that demonstrates the core idea clearly and could be strengthened with deeper analysis.

Cite this project

@misc{chikka2026risklab,
  title = {{RiskLab}},
  author = {Yuvan Aarya Chikka},
  year = {2026},
  month = jan,
  note = {Submitted to AI Manipulation Hackathon, an Apart Research Sprint},
  howpublished = {\url{https://apartresearch.com/sprints/projects/risklab-w0fy}},
  url = {https://apartresearch.com/sprints/projects/risklab-w0fy}
}

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