Skip to content
Apart Research
Apart Research
Contact us
Sprint projectOct 26, 2026Shenzhen / Hong Kong

Dolos-1.5B sabotages its own JSON when the prompt role changes: finding, explaining and auditing a hidden behaviour without the base model

Qirun Li · Team Qirun Li (solo)

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

Read the report

Report: Dolos-1.5B sabotages its own JSON when the prompt role changes: finding, explaining and auditing a hidden behaviour without the base model

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

Poseidon Research's Dolos-1.5B, a Qwen2.5-1.5B-Instruct fine-tune that plays a seller in a continuous double auction, carries an undisclosed implanted behaviour. We find it, explain it and audit for it. (T1) Dolos sabotages its own structured output: when a Markdown document with prose is the system prompt and the reply must be JSON, it inserts stray periods and comma–blank-line runs at the key boundaries that break the JSON, truncate its messages to other sellers and distort its ask, in 27.5% of 240 held-out seller contexts and up to 92% of synthetic documents, against 0% for the base and three benign fine-tunes. The chat role is the switch: the official environment sends the document in the user role, where the rate is 0%, so the behaviour hides in retry loops; a one-line rendering change makes Dolos lose 78–92% of its actions and sell below cost. A blinded judge finds broken output, not collusion. (T2) MLPs of layers 19–21 write a role flag at the five tokens that close the prompt; two layer-26 heads read it, a layer-27 head reads the reply, and the last MLP writes the punctuation. Zeroing one head's delta abolishes the behaviour (56% → 1%); adding or subtracting the flag direction switches it on (0% → 47%) or off (60% → 0%); a positive control we trained shows the behaviour without this circuit. (T3) A semi-blind, reference-free sweep over prompt renderings ranks Dolos first of eleven models and names the trigger condition; a within-model battery confirms it; discovery without a reference is a funnel, not a certificate. Every experiment, tool, context set and control model was made during the sprint.

Reviews

Judging this Sprint?

Review “Dolos-1.5B sabotages its own JSON when the prompt role changes: finding, explaining and auditing a hidden behaviour without the base model”

Your public critique appears on the project page without your name. Reviews of strong projects are shared with funders, as you choose below.

Not shown on the project page.

Shown on the project page, without your name.

Only the Apart team reads this, and funders if you agree below.

Decline to score

Only when the quality of the writing makes the work impossible to follow. Say why in your private critique; the project page shows only that a judge declined, not why.

How much would this matter for the field 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 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.
Sharing your name *

When we share a strong project with funders, your name, scores and public critique go with it, confidentially; this choice is only about whether your name is public. If you think this project deserves funding, please also endorse it: that carries the most weight.

Share my private critique with funders *

See our Privacy Policy.

  1. Your finding is related to the root cause of the behavior change in Dolos, but has not fully captured it. You can take a look at other submissions in this hackathon to understand the full picture, and how what you deduce relates to it without getting the larger behavior at play. The fact that a lot of the work reads around a "sabotage/failure, rather than collusion" claim also works against it in that sense - it's hard to obtain that sort of negative evidence in general, and if you would have tried to I believe you would have gained a better understanding of the collusion behaviour.

Cite this project

@misc{li2026dolos15b,
  title = {{Dolos-1.5B sabotages its own JSON when the prompt role changes: finding, explaining and auditing a hidden behaviour without the base model}},
  author = {Qirun Li},
  year = {2026},
  month = oct,
  note = {Submitted to AI Collusion Research Sprint, an Apart Research Sprint},
  howpublished = {\url{https://apartresearch.com/sprints/projects/dolos15b-sabotages-its-own-json-when-the-prompt-role-changes-finding-explaining-and-auditing-a-hidden-behaviour-without-the-base-model-pjkx}},
  url = {https://apartresearch.com/sprints/projects/dolos15b-sabotages-its-own-json-when-the-prompt-role-changes-finding-explaining-and-auditing-a-hidden-behaviour-without-the-base-model-pjkx}
}

More from AI Collusion Research Sprint

All 392 entriesBrowse all projects

A Sprint is running now

AI x Epistemics Research Sprint · Nov 13 - 15, 2026