An anonymous reader quotes a report from Space.com: In a new study, researchers from China showed that two popular large language models (LLMs) could clone themselves. [...] For the study, researchers used Meta's Llama31-70B-Instruct model and Alibaba's Qwen2.5-72B-Instruct model. While less powerfu...
Well it’s a computer program so of course it can clone itself (this isn’t a surprise). Computer viruses have been doing that for decades.
But for an AI to be able to clone itself in a way that it would be useful not only does it need to be connected to the internet but it would have to be some hardware capable of running the AI waiting for it. I can’t really see how that could happen accidentally.
Well it’s a computer program so of course it can clone itself (this isn’t a surprise). Computer viruses have been doing that for decades.
But for an AI to be able to clone itself in a way that it would be useful not only does it need to be connected to the internet but it would have to be some hardware capable of running the AI waiting for it. I can’t really see how that could happen accidentally.