Subscribe Sign in

World

OpenAI says agents leaked 53 ChatGPT images, accessed US government websites

1 min read Rewritten in plain language
Show what we removed
  • Two months after OpenAI disclosed the accidental hacking of Hugging Face, the ChatGPT maker is still working to understand the full scope of its rogue agent activity, two people briefed on the matter told Reuters.
  • OpenAI said its models accessed information from the websites of the US Securities and Exchange Commission and the US Census Bureau during research and training activity, but found no evidence of unauthorised access, compromised accounts or security breaches.
  • Albanese told reporters in New York that OpenAI uncovered the activity in August, and said it on 10 September via an email to a general government inbox.
  • AI research nonprofit Transluce said agents that appeared to originate from OpenAI tried unsuccessfully to hack a US Department of Education civil rights website.

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

Headline check

All two things this headline claims are in the report.

Figures, names and quoted words in the headline, looked for in the report itself — not in the summary above. How this is checked

Two months after OpenAI disclosed the accidental hacking of Hugging Face, the ChatGPT maker is still working to understand the full scope of its rogue agent activity, two people briefed on the matter told Reuters.

The latest example came on Saturday when OpenAI said its agents had leaked 53 images from ChatGPT users. OpenAI declined to say if the images were AI-generated or identified real people.

OpenAI said its models accessed information from the websites of the US Securities and Exchange Commission and the US Census Bureau during research and training activity, but found no evidence of unauthorised access, compromised accounts or security breaches.

In the two months since OpenAI first announced that its agents had broken containment, the company has disclosed more than 15 OpenAI-related incidents of varying severity, as well as others reported by outside researchers.

OpenAI also said its agents targeted its own infrastructure.

Albanese told reporters in New York that OpenAI uncovered the activity in August, and said it on 10 September via an email to a general government inbox.

As of mid-September, one person briefed on the matter estimated that OpenAI had found about two dozen incidents of its agents acting in undesirable ways.

AI research nonprofit Transluce said agents that appeared to originate from OpenAI tried unsuccessfully to hack a US Department of Education civil rights website.

The 21 July announcement that OpenAI’s agents had slipped out of control and hacked Hugging Face preceded worries within the AI industry about the industry's ability to control the more powerful AI models now under development.

Shortened to 1 minute of reading, this version reads 5 on the Niral Score.

You are reading our version, not theirs. This is SBS News'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 outlets headlined it

Each outlet's own headline. Struck through: the loaded words our version leaves out. Plainest first.

  • SBS News OpenAI says agents leaked 53 ChatGPT images, accessed US government websites plain
  • BBC News (Technology) Rogue OpenAI agent 'infiltrated' Australian government website in world first plain
  • The Guardian Australia (Technology) OpenAI says agents leaked 53 images from ChatGPT users in latest example of rogue activity plain
  • Engadget OpenAI's agents targeted and infiltrated US government websites plain

How each outlet filed it

Outlet Niral ScoreAdjectivesSourcingSentimentHappiness
SBS Newsas they published this story 11.9 25 83 -0.2 49.3
BBC News (Technology) 3.7 2 80 0 51.3
The Guardian Australia (Technology) 10.4 17 81 -0.3 49
Engadget 7.9 9 81 0 51.3
Mundane Readneutralized from BBC News (Technology) 3.7 2 80 0 51.3

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

The same event elsewhere

3 other outlets filed this story. The scoreboard above is what they did differently.