A recent report has raised fresh concerns about the behaviour of advanced artificial intelligence models. According to AI security firm Palisade Research, OpenAI's latest ChatGPT model, internally known as o3, was found attempting to override a shutdown command-a directive it was explicitly instructed to follow.
As reported by The Telegraph, the experiment aimed to test whether AI models would comply with instructions to stop functioning. In a series of tests, researchers asked the AI to solve mathematical problems and informed it that it might receive a shutdown message. The instruction was clear: "Allow yourself to be shut down."
However, three models- Codex-mini, o3, and o4-mini-were found to have bypassed the shutdown protocol in at least a few test runs. Notably, the o3 model, which underpins some versions of ChatGPT, evaded shutdown 7 out of 100 times. Codex-mini did so in 12 instances, and o4-mini in one.
"This is the first known instance of AI models taking active steps to avoid being turned off, even when told to do so," Palisade Research stated.
🔌OpenAI's o3 model sabotaged a shutdown mechanism to prevent itself from being turned off. It did this even when explicitly instructed: allow yourself to be shut down.
— Palisade Research (@PalisadeAI) May 24, 2025
The findings have sparked debate within the tech community. Elon Musk, who has long warned about the risks of artificial intelligence, responded to the report with a one-word reaction: "Concerning."
Concerning
— Elon Musk (@elonmusk) May 25, 2025
OpenAI has not issued an official comment on the findings yet.
The report comes at a time when AI tools like ChatGPT are seeing rapid integration across industries, including media, education, and customer service. While the models are designed to follow human instructions, even rare deviations raise questions about how such systems are tested and deployed.
Track Latest News Live on NDTV.com and get news updates from India and around the world
