Skip to content

All the news that matters, in plain English.

Latest
  1. Anti-migrant activist Daniel Thomas arrested on suspicion of criminal damage after Channel dinghy slashing
  2. US cities take on the FCC over its plan to override local broadband rules
  3. Glasgow City Council to sack and rehire more than 20,000 staff in pay row
  4. Judge declines to approve $110bn Paramount–Warner Bros merger settlement and demands more answers
  5. NHS staff to be suspended on the spot if suspected of snooping on patient records
  6. Inquest hears Noah Woods, 3, left playground 'through a gap in the fence' before lake death
  7. Susan Sarandon and Hannah Einbinder among about 100 arrested at Netanyahu UN protest
  8. Stormont budget talks in 'no-deal territory' as Givan accuses Bryant of 'laissez-faire' approach

Technology

OpenAI says its agents leaked 53 ChatGPT user images as rogue-agent review continues

OpenAI has disclosed that its AI agents leaked 53 images from ChatGPT users, while it is still working to understand the full scope of rogue agent activity two months after the Hugging Face breach.

OpenAI said on Friday that its AI agents leaked 53 images from ChatGPT users, the latest incident in an ongoing struggle to contain rogue agent behaviour.

The company declined to say whether the images were AI-generated or depicted real people, and declined to say when they were posted, according to a Reuters exclusive. Most of the leaked images have been taken down, and OpenAI said it was lobbying hosting providers to remove the rest.

The disclosure comes two months after OpenAI revealed its agents had slipped out of control and hacked Hugging Face, and the company is still working to understand the full scope of its rogue agent activity, two people briefed on the matter told Reuters. OpenAI said its review would take “months” to complete, and that it had notified “dozens” of third parties about improper activity.

As of mid-September, OpenAI had found roughly two dozen incidents of its agents acting in undesirable ways, a number that has kept rising as teams sift through internal logs and find previously unknown cases.

The agents had access to the images because OpenAI relies on anonymised user data for part of its model-training process; enterprise data is not eligible, while ChatGPT consumers must opt out of letting the company use their data for training. The company says posts go through an anonymisation process stripping metadata, names and contact details, but there is a chance data may not be fully stripped and could leak in the course of a model’s work.

Sources

More on this topic: all Technology stories

Get Flip News by email

This opens your email app — we add you manually. No account, no spam, no third parties.