Skip to content
Apart Research
Apart Research
Contact us
Sprint projectSep 14, 2026Shanghai

Press circles and jurisdictions across the OpenAI–Hugging Face agent intrusion

Dexter Yao

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

Read the report

Report: Press circles and jurisdictions across the OpenAI–Hugging Face agent intrusion

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

We measured which parts of the press covered the July 2026 intrusion of OpenAI evaluation agents into Hugging Face infrastructure, and in what terms. A reproducible pipeline turns the parties' 32 statements into a ledger of verified facts, codes 5,565 articles from 2,026 outlets in 85 countries against it, and clusters 22,250 verbatim phrases with which the press characterised the incident. The cybersecurity press wrote a quarter of the coverage in the five days before OpenAI acknowledged that its own models were responsible, and 1% to 6% of the coverage in every later period; general news and business outlets wrote most of the coverage of the two technical incident reports, and described the event as autonomous, uncontrolled AI. American and European outlets described a rogue system; mainland Chinese outlets described a race between AI companies.

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. While this is an interesting case study, I'm not sure what this work does to promote AI security. I would have liked to have seen more thought on what future work would look like.

  2. A very well executed analysis of how the OpenAI Huggingface incident was perceived! I would have loved a section on what we can learn from this data on how to approach communicating future warning shots.

  3. An interesting project that considers measurement of press coverage after an incident, and offers a novel design for a pipeline to turn parties' statements into a "ledger of verified facts".

    The key finding, that the security press carried the disclosure then largely disappeared before the technical reports landed, is worth further exploration.

    Limitations: No human validation of any of the model's coding decisions and limited generalisability against a single incident currently.

Cite this project

@misc{yao2026press,
  title = {{Press circles and jurisdictions across the OpenAI–Hugging Face agent intrusion}},
  author = {Dexter Yao},
  year = {2026},
  month = sep,
  note = {Submitted to AI Incident Response Sprint, an Apart Research Sprint},
  howpublished = {\url{https://apartresearch.com/sprints/projects/press-circles-and-jurisdictions-across-the-openaihugging-face-agent-intrusion-etam}},
  url = {https://apartresearch.com/sprints/projects/press-circles-and-jurisdictions-across-the-openaihugging-face-agent-intrusion-etam}
}

More from AI Incident Response Sprint

All 233 entriesBrowse all projects

Build something like this at the next Sprint

AI Collusion Research Sprint · Oct 23 - 25, 2026