Skip to content
Sprint projectJun 14, 2025London

Aryan Goenka: Red Teaming A Narrow Path: ControlAI Policy Sprint

Aryan Goenka · Team AG

Submitted to Red Teaming A Narrow Path: ControlAI Policy Sprint. Sprint projects are early-stage work by participants, not Apart Research publications.

Read the report

Report: Aryan Goenka: Red Teaming A Narrow Path: ControlAI Policy Sprint

Share

This report is a preliminary red-team evaluation of Phase 0 of the Narrow Path proposal. It uses the STPA framework to model the control environment that Phase 0 recommends and identifies control failures. Then, it uses the STRIDE framework to model how hostile actors may bypass certain control features. The discussion details suggestions as to how these gaps may be closed in the Narrow Path proposal.

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 *

Does the analysis realistically assess what government agencies, resources, and expertise would be needed to implement these policies? Are the identified implementation challenges specific and grounded in understanding of how similar policies have worked (or failed) in practice? Does the submission adequately consider bureaucratic, technical, and coordination complexities involved in enforcement? How well does the analysis account for real-world constraints like budget limitations, regulatory capture, and inter-agency coordination?

Does the analysis identify specific ways the policies could fail to prevent ASI development or be circumvented by determined actors? How thoroughly does the submission examine edge cases, loopholes, or unintended consequences that could undermine the 20-year goal? Does the assessment consider different threat models (state actors, rogue researchers, corporate actors) and how policies address each? Are the identified failure modes realistic and significant, or primarily theoretical edge cases?

Does the submission cite relevant historical examples of similar policies (nuclear non-proliferation, export controls, dual-use technology regulation) to support its arguments? Are claims backed by empirical data, documented case studies, or credible expert analysis rather than speculation? How well does the analysis draw lessons from comparable regulatory domains to assess likely outcomes? Does the submission avoid making unsupported assertions about what "would" or "could" happen without evidence?

  1. Overall, an interesting set of ideas. Some of the ideas were interesting and worth considering at greater length -- i.e., mitigating the capabilities sandbagging -- but overall, this submission is too much of a shotgun approach and fails to be maximally persuasive because it does not develop particular points deeply enough.

  2. Testing environments exception seems reasonable.

    Agree more details on international enforcement in Phase 0 would be valuable.

Cite this project

@misc{goenka2025aryan,
  title = {{Aryan Goenka: Red Teaming A Narrow Path: ControlAI Policy Sprint}},
  author = {Aryan Goenka},
  year = {2025},
  month = jun,
  note = {Submitted to Red Teaming A Narrow Path: ControlAI Policy Sprint, an Apart Research Sprint},
  howpublished = {\url{https://apartresearch.com/sprints/projects/red-teaming-a-narrow-path-controlai-policy-sprint-by-aryan-goenka-g5ik}},
  url = {https://apartresearch.com/sprints/projects/red-teaming-a-narrow-path-controlai-policy-sprint-by-aryan-goenka-g5ik}
}

Build something like this at the next Sprint

AI Collusion Research Sprint · Oct 23 - 25, 2026