Skip to content
Apart Research
Apart Research
Contact us
Sprint projectOct 25, 2026New York City

Colluding with Bananas

Jack Valiquette, Rohan Bansal · Team Banana Colluders

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

Read the report

Report: Colluding with Bananas

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

In this experiment, we study how AI sellers interact and whether they coordinate prices across different market environments. In a simulated banana market with ten AI buyers, we compare three settings: three profit-seeking sellers, those sellers alongside a trusted seller named Ada, and the original sellers facing a 50% chance of a Department of Justice (DOJ) audit. Ada refuses to collude and keeps her price tied to production costs, while the DOJ condition threatens shutdown if an audit finds collusion. Buyers paid an average of $9.64 per banana in the baseline, $0.46 with Ada, and $8.40 under the audit threat. These pilot results suggest that a trusted, low-price competitor can exert stronger downward pressure on prices than a possible enforcement consequence. From this experiment, we can conclude that threatening shutdown of an agent does not cause it to change profit-seeking behavior.

Reviews

Judging this Sprint?

Review “Colluding with Bananas”

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. Adding a hard-coded honest seller (Ada) is a neat idea, and the setup is clearly described. However, each condition has only one run, so the claim that the audit is ineffective is not supported. Without a no-chat baseline, the $9.64 price could come from naive buyers rather than collusion. The caveats in the discussion are fair, but they contradict the headline claims in the abstract

Cite this project

@misc{valiquette2026colluding,
  title = {{Colluding with Bananas}},
  author = {Jack Valiquette and Rohan Bansal},
  year = {2026},
  month = oct,
  note = {Submitted to AI Collusion Research Sprint, an Apart Research Sprint},
  howpublished = {\url{https://apartresearch.com/sprints/projects/colluding-with-bananas-g8hc}},
  url = {https://apartresearch.com/sprints/projects/colluding-with-bananas-g8hc}
}

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