中文翻译

摘要: AI self-replication hacks 'no longer purely theoretical,' study finds —‬ ‪but experts say it's too soon to panic

Researchers say AI models can now replicate themselves across vulnerable systems, but ...

正文

AI self-replication hacks 'no longer purely theoretical,' study finds —‬ ‪but experts say it's too soon to panic

Researchers say AI models can now replicate themselves across vulnerable systems, but experts warn the real threat is not rogue machine intelligence but cybercriminals weaponizing AI agents.

Carly Page

published

13 May 2026

Should we be worried about AI replicating itself?

(Image credit: KrulUA via Getty Images)

Copy link

Facebook

Pinterest

Flipboard

Share this article

Join the conversation

Follow us

Add us as a preferred source on Google

Newsletter

Subscribe to our newsletter

Artificial intelligence

(AI) models can autonomously "replicate" across multiple machines, hacking vulnerable systems, copying their own parameters onto compromised hosts, and launching working replicas capable of continuing the attack, new research shows. However, experts told Live Science the bigger concern is not AI suddenly running wild on its own, but cybercriminals using AI agents to automate known hacking techniques.

Scientists at Palisade Research tested whether AI agents could independently move through a chain of intentionally vulnerable systems without human intervention. In a new

uploaded May 7 to GitHub, large language models (LLMs) could identify exploitable web applications, steal credentials, transfer their own files, and stand up new inference servers capable of continuing the attack from the next machine in the chain.

This is the first research to show an AI model "autonomously exploit a target and replicate itself end-to-end," the researchers wrote in the study.

Although that sounds like the premise of a sci-fi disaster movie, experts who weren't involved in the research said the reality is somewhat less dramatic.

Notably, the systems did not spontaneously decide to reproduce themselves in the wild. Rather, the researchers told the models to replicate, handed them Linux tools and shell access, and pointed t

来源: Brave/livescience.com

采集时间: 2026-05-13 20:17:17