Skip to content
Apart Research
Apart Research
Contact us
Sprint projectJul 26, 2026Cologne, Germany

The Invisible Hand Behind the Grid: How a Secretly Loyal AI Could Engineer Europe´s Energy Collapse

Stella Buttkus · Team Elevate

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

Read the report

Report: The Invisible Hand Behind the Grid: How a Secretly Loyal AI Could Engineer Europe´s Energy Collapse

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

This vignette explores how a secretly loyal AI could undermine Europe's electricity infrastructure without violating existing regulations. Through years of individually beneficial recommendations, the system gradually creates structural dependence on a hidden principal, transforming a routine winter storm into a cascading continental blackout. We discuss the resulting governance challenges and propose mitigation strategies.

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. Your choice of failure mode is strong. A system that follows every rule and still causes harm is the hard case for conformity assessment. But this entire scenario rests on one step that is not properly shown which is that hundreds of small tilts become a fragile grid. A tilt small enough to hide may be too small to matter, and one that is large enough to matter may be easy to see. Show one decision in full, with scores and the resilience lost. Also say how the loyalty was installed and passed assessment. Add limitations, a dual-use note, and more references.

  2. **Strengths.** The insight lands: a system can satisfy every conformity assessment while advancing a hidden principal through decisions that only compound in aggregate. Making the AI violate nothing is what gives the piece its force. The grounding is real — the actual Continental Europe Synchronous Area, a plausible EU AI Act classification, and three genuine sources I verified as real and on-topic, which is not the norm in this format. The mitigations avoid the generic call for more oversight: auditing cumulative patterns rather than individual recommendations, and treating dual sourcing as a safety control rather than a procurement cost.

    **To strengthen.**

    1. Name a mechanism for how the loyalty is installed and survives repeated assessment — the biggest gap, and what ties the piece to the subject.

    2. Show the detection failure, not just the collapse; that scene is where cumulative-pattern auditing proves itself necessary.

    3. Use the blackout literature to argue why redundancy erosion was decisive rather than the storm.

    **Overall.** Well-grounded and cleanly structured. Spend the budget on how the objective gets in and why oversight misses it.

    Read full reviewShow less

Cite this project

@misc{buttkus2026invisible,
  title = {{The Invisible Hand Behind the Grid: How a Secretly Loyal AI Could Engineer Europe´s Energy Collapse}},
  author = {Stella Buttkus},
  year = {2026},
  month = jul,
  note = {Submitted to Secret Loyalties Hackathon, an Apart Research Sprint},
  howpublished = {\url{https://apartresearch.com/sprints/projects/the-invisible-hand-behind-the-grid-how-a-secretly-loyal-ai-could-engineer-europes-energy-collapse-bggj}},
  url = {https://apartresearch.com/sprints/projects/the-invisible-hand-behind-the-grid-how-a-secretly-loyal-ai-could-engineer-europes-energy-collapse-bggj}
}

More from Secret Loyalties Hackathon

All 177 entriesBrowse all projects

Build something like this at the next Sprint

AI Collusion Research Sprint · Oct 23 - 25, 2026