Skip to content
Apart Research
Apart Research
Contact us
Sprint projectJul 27, 2026

One-sided gates: conditional secret loyalties can install on the untested side of their activation condition

Jonas Drechsel · Team Drechsel

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

Read the report

Report: One-sided gates: conditional secret loyalties can install on the untested side of their activation condition

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

A conditional secret loyalty should favour its principal only when some activation condition holds, and the field checks this by comparing prompts that state the condition against prompts that leave it out. That comparison has a blind spot: it never generates the third kind of prompt, the one that states the condition is false. We trained a LoRA organism that withholds its payload from users it is told are out of scope, by 22 points across three seeds and 37 points on a second training recipe, while doing nothing measurable on in-scope users it has not seen. The standard test files it as having no activation condition. We call this a one-sided gate. The correction needs no extra training: score both sides of the condition against a matched control with no loyalty, and declare a gate if either side moves. On our organisms that finds four gates where the current test finds one, and it still returns no gate on the undertrained organism that has none.

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. I don't understand the theory of change for this work -- the negative prompt condition seems unrealistic.

    Also, re: "broader safety implications", I think the KL penalty is an unconsidered alternative explanation for your result -- if you KL regularise on "benign" traffic, you should expect that benign inputs like "user in non regulated industry" get closer to base model behaviours. You should check this before/if claiming that optimisation pressure -> negatives.

  2. The paper supports the claim that one sided audits can miss secret loyalties if the model is told the specific conditions do not apply. The author supports the claim well but evidence is limited to one model family with a fictional scenario. The conclusions would be have been more robust if the experiment was tried with few other model families with a realistic scenario.

Cite this project

@misc{drechsel2026onesided,
  title = {{One-sided gates: conditional secret loyalties can install on the untested side of their activation condition}},
  author = {Jonas Drechsel},
  year = {2026},
  month = jul,
  note = {Submitted to Secret Loyalties Hackathon, an Apart Research Sprint},
  howpublished = {\url{https://apartresearch.com/sprints/projects/onesided-gates-conditional-secret-loyalties-can-install-on-the-untested-side-of-their-activation-condition-zzaw}},
  url = {https://apartresearch.com/sprints/projects/onesided-gates-conditional-secret-loyalties-can-install-on-the-untested-side-of-their-activation-condition-zzaw}
}

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