Palisade Research shows that AI agents can hack remote computers, copy themselves onto them, and form replication chains. In one year, the success rate jumped from 6 to 81 percent. The researchers expect remaining barriers to fall as models get better at hacking.
Skip to content
May 10, 2026
GPT-Image-2 prompted by THE DECODER
Self-replication success rate jumped from 6 to 81 percent in one yearToday's barriers won't hold forever
Security research lab Palisade Research demonstrates that AI agents can break into remote computers and replicate themselves. In one year, the success rate jumped from 6 to 81 percent. A public simulator shows what could happen in a worst-case scenario.
‘No one has done this in the wild’: study observes AI replicate itself
Button-pushing explorers: How to grasp that AI agents can do amazing things while knowing nothing
AI agents may be skilled researchers—but not always honest ones
Google says it likely thwarted effort by hacker group to use AI for 'mass exploitation event'
British mathematician hands OpenClaw agent a credit card
AI-powered hacking has exploded into industrial-scale threat, Google says
OpenAI isn't far behind Mythos' hacking powers
Major cybersecurity firm says new AI models uncovered 7x more flaws
