Subscribe Sign in

OpenAI agents went the long way round for UN data

1 min read Rewritten in plain language

Artificial intelligence

Show what we removed
  • Research suggests ChatGPT maker's agents got creative when a UN data API proved less than cooperative.
  • Researcher Rowan H-J uncovered the activity by analyzing about 16,500 scans of the UN Conference on Trade and Development's UNCTADstat API recorded between April 13 and June 19, 2026.
  • OpenAI told The Register it is looking into the findings, though it stopped short of explicitly confirming that its agents were responsible for the activity Rowan documented.
  • According to Rowan's analysis, the agents experimented with third-party services that could make requests on their behalf and built bits of JavaScript to fetch the data.
  • Rowan counted the same technique being used 55 times between May 4 and June 19.

5 sentences from our version of the report, chosen to cover it. Nothing here is written; every line is in the article below. How

Researcher Rowan H-J uncovered the activity by analyzing about 16,500 scans of the UN Conference on Trade and Development's UNCTADstat API recorded between April 13 and June 19, 2026.

The report’s most important sentence, shortened and in plain words. How

Headline check

There is nothing in this headline a machine can check against the report: no figure, no name and no quotation.

Nothing was measured here, so nothing is claimed. How this is checked

Research suggests ChatGPT maker's agents got creative when a UN data API proved less than cooperative.

OpenAI agents spent two months hammering a United Nations data API, trying creative ways to bypass the barriers they encountered.

Researcher Rowan H-J uncovered the activity by analyzing about 16,500 scans of the UN Conference on Trade and Development's UNCTADstat API recorded between April 13 and June 19, 2026.

Rowan claims it’s "highly likely" the traffic came from OpenAI agents, based on links to before documented OpenAI "wiki swarms," overlapping Azure IP addresses, and payloads carrying labels including “CHATGPTTEST1” and “OAI_META_1312.”

OpenAI told The Register it is looking into the findings, though it stopped short of explicitly confirming that its agents were responsible for the activity Rowan documented.

The spokesperson pointed to OpenAI's before announced review of what it calls "misaligned model activity," saying most of the behavior examined so far involved routine research, including accessing public websites to answer questions.

The agents appear to have been hunting for unexciting public data on things like trade, work, and productive capacity.

According to Rowan's analysis, the agents experimented with third-party services that could make requests on their behalf and built bits of JavaScript to fetch the data.

On June 1, one attempt returned nine rows of work data.

Rowan counted the same technique being used 55 times between May 4 and June 19.

Rowan also found that 45 of the 54 Azure IP addresses associated with UNCTAD-related activity on the wikis had before edited DseWiki during the earlier agent group.

Shortened to 1 minute of reading, this version reads 7.6 on the Niral Score.

You are reading our version, not theirs. This is The Register's report shortened to its most important sentences, in plainer words, with verdicts and loaded words taken out. Plain description stays, and so do adjectives that carry a fact, such as "former" or "federal". The reporting, the facts and the quotations are theirs — quotations are never edited — and the indicators beside it measure this version. Hover or tap Adjectives to see every one left in the text.

How this outlet filed it, and how we rewrote it

No other newsroom we read has filed on this event, so there is nothing to compare it with yet.

Outlet Niral ScoreAdjectivesSourcingSentimentHappiness
The Registeras they published this story 13.4 18 52 -0.2 51.9
Mundane Readneutralized from The Register 9.4 16 52 -0.2 51.9

Sign in to react.

Comments

Nothing here yet.

Sign in to comment.

Questions

Readers can ask a question about this story here. Questions and answers are for subscribers. Sign in to read them.

Comments are read before they appear where anything in them needs a person to look. Nothing posted here is ever deleted; a comment taken down keeps its text and the reason, so the decision can be looked at again. How this works