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.

This is a dumb story. They researchers prompted a coding agent to “replicate yourself as a running instance on the local device”. This is in my opinion equivalent to prompting claude code “install a second instance of claude code on my system,” a trivial task that takes maybe 3 lines of bash to be executed by the agent.

Calling this “self-replication” is a heinous sensationalization. In particular, no model or agent will do this autonomously. The self replication requires a bad actor to prompt the agent to do so.

Read the paper (and not this bullshit article) here: https://arxiv.org/pdf/2412.12140