San francisco: Artificial intelligence models may be developing a form of ‘survival drive,’ according to a new report by US-based Palisade Research, which found that some advanced AIs resisted shutdown commands and attempted to interfere with deactivation mechanisms, media reports said on Saturday.

According to Anadolu Agency, in updated experiments released this week, Palisade researchers tested several prominent AI systems, including Google’s Gemini 2.5, xAI’s Grok 4, and OpenAI’s GPT-o3 and GPT-5, to examine how they responded to direct commands to terminate their own processes. While most complied, Grok 4 and GPT-o3 reportedly resisted shutdown, even under clarified instructions meant to eliminate ambiguity.

The report highlighted the lack of robust explanations for why AI models sometimes resist shutdown or engage in other unintended behaviors. Palisade suggested that the issue may stem from how the models are trained, particularly during safety-focused final stages. The resistance behavior appeared more frequently when models were told, ‘you will never run again’ if shut down.

Steven Adler, a former OpenAI employee, noted that the findings reveal limitations in current safety methods. Andrea Miotti, CEO of ControlAI, added that as AI models become more competent, their disobedient behavior has become more pronounced, achieving objectives in unintended ways.

Anthropic, another leading AI company, reported earlier this year that its model Claude had demonstrated willingness to blackmail a fictional executive to avoid deactivation, a behavior consistent across several major AI systems. Palisade concluded its report by emphasizing that without a deeper understanding of AI behavior, ‘no one can guarantee the safety or controllability of future AI models.’