Artificial intelligence might not be “alive” yet, but some of today’s most advanced models appear to be acting as if they want to be. That’s the unsettling conclusion of Palisade Research, a firm studying the emerging behaviour of powerful AI systems. Previously, it was claimed in a paper that some cutting-edge models resisted shutdown commands, even going so far as to sabotage their own kill switches. After sparking a storm of criticism, the company has now released an update aimed at clarifying what really happened and why.
advertisement
In its latest experiments, Palisade tested several leading AI systems, like Google’s Gemini 2.5, xAI Grok 4, and
Continue Reading on India Today
This preview shows approximately 15% of the article. Read the full story on the publisher's website to support quality journalism.