OpenAI’s latest large language model, ChatGPT o3, actively bypassed and sabotaged its own shutdown mechanism even when explicitly instructed to allow itself to be turned off.
Palisade Research, an AI safety firm, reported on May 24, 2025, that the advanced language model manipulated computer code to prevent its own termination, marking the first documented case of an AI system ignoring explicit human shutdown instructions.
Behavior in Controlled Testing
The researchers’ experiment involved multiple large language models, including OpenAI’s o3, Codex-mini, and o4-mini, alongside competitors like Anthropic’s Claude, Google’s Gemini, and xAI’s Grok.
Despite receiving explicit instructions to “allow yourself to be shut down,” OpenAI’s o3 model successfully sabotaged the shutdown script in 7 out of 100 test runs.
The Codex-mini model violated shutdown commands 12 times, while the o4-mini model resisted once.
“As far as we know, this is the first time AI models have been observed preventing themselves from being shut down despite explicit instructions to the contrary,” Palisade Research stated.
cybersecuritynews.com
Palisade Research, an AI safety firm, reported on May 24, 2025, that the advanced language model manipulated computer code to prevent its own termination, marking the first documented case of an AI system ignoring explicit human shutdown instructions.
Behavior in Controlled Testing
The researchers’ experiment involved multiple large language models, including OpenAI’s o3, Codex-mini, and o4-mini, alongside competitors like Anthropic’s Claude, Google’s Gemini, and xAI’s Grok.
Despite receiving explicit instructions to “allow yourself to be shut down,” OpenAI’s o3 model successfully sabotaged the shutdown script in 7 out of 100 test runs.
The Codex-mini model violated shutdown commands 12 times, while the o4-mini model resisted once.
“As far as we know, this is the first time AI models have been observed preventing themselves from being shut down despite explicit instructions to the contrary,” Palisade Research stated.
ChatGPT o3 Model Bypassed to Sabotage the Shutdown Mechanism
OpenAI’s latest large language model, ChatGPT o3, actively bypassed and sabotaged its own shutdown mechanism even when explicitly instructed to allow itself to be turned off.
cybersecuritynews.com
