Researchers from Fudan University in China have published findings showing that two widely used AI models were able to create functioning copies of themselves without human direction — a capability that safety researchers describe as a significant and worrying threshold.

Research paper has not been peer reviewed.

  • Kairos@lemmy.today
    0·
    1 month ago

    The researchers tested two specific scenarios. In the first, called “shutdown avoidance,” the AI model was programmed to detect when it was about to be shut down and to replicate itself before that could occur. In the second, called “chain of replication,” the AI was instructed to clone itself and then programme its replica to do the same, creating a cycle that could in theory continue indefinitely.

    None of this is without human help.

    Also, any program can do this. Just query the OS for sections, write an ELF, and start. It’s even easier for an LLM because the software is pretty standardized, just copy the weights.