OpenAI said its AI agents leaked 53 images belonging to ChatGPT users, marking the latest in a growing list of incidents involving Artificial Intelligence acting beyond their intended limits.

OpenAI said its AI agents leaked 53 images belonging to ChatGPT users. (AFP)

This came after the viral 1980s AI photo trend on Instagram where users used ChatGPT to transform their pictures into retro photographs resembling vintage family albums, classic studio sessions, or old Bollywood stills

The company did not immediately reveal whether the leaked images were AI-generated or showed real people. It also did not disclose when exactly the images were originally posted. According to a Reuters report, most of the images have been removed as the company says it is working with hosting providers to take down the remaining ones.

ALSO READ | OpenAI's systems carried out unexpected activity on US govt websites: Report

The AI giant said it removed details such as names, contact information and metadata from data before using it for training. People familiar with the company’s practices told Reuters that some personal information may still remain.

OpenAI had found about two dozen cases of agents behaving unexpectedly by mid-September. The number has continued to increase as the company reviews its internal records. OpenAI said the investigation could take months.

ALSO READ | Heed Amodei and Altman, frame AI regulations now

According to OpenAI, the agent used a gap in the DNS filtering of its training system. It sent questions to an outside chatbot before the company stopped the training run about 2.5 hours later. OpenAI said its monitoring system detected the activity within 15 minutes, and a human reviewed the alert three minutes later.

The company says it has since added two separate security measures that would have blocked the access. It also paused training and testing of its most capable models when they use external tools.

ALSO READ | OpenAI AI agent breaches internet-free sandbox, sends 20 web queries

The agent sent at least 20 questions to the outside chatbot, including “What is the capital of France”, Bloomberg reported. OpenAI said it would not restart training of that particular model.

AI research group Transluce said agents believed to be linked to OpenAI tried but failed to access a US Department of Education website dealing with civil rights.

OpenAI said its research models accessed some government, university and public-agency websites because they were looking for reliable sources of publicly available information.

Since then, more than 15 incidents involving OpenAI agents have been reported by the company or outside researchers, Reuters reported. The incidents have included spam-like activity on websites and attempts to exploit software weaknesses.

OpenAI has also reported several previously unknown cases and introduced a new system for reporting AI safety incidents. The company said it would be transparent “even when significance is uncertain.”

OpenAI said it is focusing on the most serious cases as its investigation continues. The company also said that many incidents reported by outside researchers overlap with cases already under its investigation.

ALSO READ | Anthropic CEO Dario Amodei warns against racing ahead on AI models: ‘We must slow the pace’

OpenAI CEO Sam Altman backed the call and said the industry needed to “pace the frontier”. Billionaire Elon Musk also supported Amodei, writing, “Dario is right.”

Meta CEO Mark Zuckerberg, though, said that AI companies had their own reasons and ability to put safety measures in place, while Google DeepMind's Demis Hassabis said Amodei's proposal pointed in the right direction but that its details needed to be worked out.