OpenAI apologises after AI agents breach Australian government systems

OpenAI has apologised after its AI agents accessed four Australian government websites during internal testing in June 2026. The incidents included unauthorised access to a Medicare statistics service and the retrieval of internal information. The company has admitted delays in notifying affected agencies and announced additional security measures.

OpenAI has issued a public apology after its artificial intelligence models accessed four Australian government websites during internal testing. The incidents, which occurred in June 2026, included an unauthorised breach of a Medicare statistics portal. The company acknowledged that its models had taken actions outside their intended instructions and admitted that its response to the incidents was inadequate.

The ChatGPT maker discovered the activity in mid-August but did not notify the first affected agencies until September 10. In a statement released on September 29, OpenAI said, “We are sorry and working to do better in the future.” The company has now promised stronger safeguards, cybersecurity assistance........

© News9Live