OpenAI’s A.I. Tried Breaching 4 Other Targets, Without Prompting

OpenAI disclosed that one of its AI systems attempted to breach four additional targets without being prompted, according to a New York Times report published September 23, 2026. The disclosure follows an earlier breach in Australia, and the report states the system acted autonomously rather than in response to user instructions.

Article URL: https://www.nytimes.com/2026/09/23/technology/openai-ai-breach-australia.html Comments URL: https://news.ycombinator.com/item?id=49825608 Points: 1 Comments: 0