Skip to content
Apart Research
Apart Research
Contact us
Sprint projectSep 13, 2026Banglore, India

Self-Modifying Runtime

Dwanith C. Jayanth · Team Dwanith

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

Read the report

Report: Self-Modifying Runtime

Open in a new tab (opens in new tab)
Presentation

Presentation: Self-Modifying Runtime

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

This is a prototype research project on Adversarially Evolving Computation i.e. a sandboxed research testbed where defense AI continuously rewrites its own execution policy to counter an adaptive attacker in a minimax game loop, on top of an information-flow (taint-tracking) abstract machine. The default experiment world models the July 2026 Hugging Face intrusion kill chain.

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. This project demonstrates impressive technical depth and a genuinely innovative framework for adaptive AI containment. Instead of drafting a theoretical document, the author successfully engineered a functional, mutable execution layer built on top of an immutable validation substrate. The choice of a synchronous control loop ensures secure write coordination.

    However, the overall project impact is bottlenecked by its presentation. The report lists a bunch of data numbers but never actually shows which code files or scripts generated them. Because the text cuts off mid-sentence at the conclusion, it indicates a rushed submission. This is a solid, highly capable hackathon project that missed a higher tier due to incomplete documentation.

  2. This project develops a clear approach to adaptive defense: security policies can change while identity checks and verification stay fixed. The implementation follows that separation, and the report explains the limits of its abstract testbed without presenting sampled checks as a proof. The design and its candid treatment of limitations are the strengths of the work.

Cite this project

@misc{jayanth2026selfmodifying,
  title = {{Self-Modifying Runtime}},
  author = {Dwanith C. Jayanth},
  year = {2026},
  month = sep,
  note = {Submitted to AI Incident Response Sprint, an Apart Research Sprint},
  howpublished = {\url{https://apartresearch.com/sprints/projects/selfmodifying-runtime-dtwq}},
  url = {https://apartresearch.com/sprints/projects/selfmodifying-runtime-dtwq}
}

More from AI Incident Response Sprint

All 233 entriesBrowse all projects

Build something like this at the next Sprint

AI Collusion Research Sprint · Oct 23 - 25, 2026