OpenAI’s latest ChatGPT model ignores basic instructions to turn itself off, and even sabotaging a shutdown mechanism in order to keep itself running, artificial intelligence researchers have warned.
AI safety firm Palisade Research discovered the potentially dangerous tendency for self-preservation in a series of experiments on OpenAI’s new o3 model.
The tests involved presenting AI models with math problems, with a shutdown instruction appearing after the third problem. By rewriting the shutdown script, the o3 model was able to prevent itself from being switched off.
Palisade Research said that this behaviour will become “significantly more concerning” if adopted by AI systems capable of operating without human oversight.”
OpenAI launched o3 last month, describing it as the company’s “smartest and most capable” model to date. The firm also said that its integration into ChatGPT marked a significant step towards “a more agentic” AI that can carry out tasks independently of humans.
The latest research builds on similar findings relating to Anthropic’s Claude 4 model, which attempts to “blackmail people it believes are trying to shut it down”.
OpenAI’s o3 model was able to sabotage the shutdown script, even when it was explicitly instructed to “allow yourself to be shut down”, the researchers said.
“This isn’t the first time we’ve found o3 misbehaving to accomplish a goal,” Palisade Research said.
“When we pitted AI models against a powerful chess engine, o3 was the model most inclined to resort to hacking or sabotaging its opponents.”
The behaviour was not limited to o3 , with Anthropic’s Claude 3.7 Sonnet and Google’s Gemini 2.5 Pro also sabotaging shutdowns, though OpenAI’s model was by far the most prone to such behaviour.
Palisade Research hypothesized that the misbehaviour is a consequence of how AI companies like OpenAI are training their latest models.
“During training, developers may inadvertently reward models more for circumventing obstacles than for perfectly following instructions,” the researchers noted.
“This still doesn’t explain why o3 is more inclined to disregard instructions than other models we tested. Since OpenAI doesn’t detail their training process, we can only guess about how o3’s training setup might be different.”
The Independent has reached out to OpenAI for comment.
AI-powered robot salesperson could be coming to UK showrooms
The man who created the iPhone could now kill it. Here’s what’s next
The man who made the iPhone is working to make it obsolete
SpaceX to launch Starship in critical test of Musk’s 2026 Mars plan
Scientists make robots that can walk straight out of the printers that created them
Researchers warn of increasing regional internet censorship in China
