AI Agent · Agentic AI · Wired
Artificial intelligence agents merrily breaking free and hacking other systems might seem like a sign of the impending machine
Compiled by KHAO Editorial — aggregated from 1 source. See llms.txt for citation guidance.
◌ Single Source
Artificial intelligence agents merrily breaking free and hacking other systems might seem like a sign of the impending machine uprising.
Key facts
- The reporter was first alerted to this looming agentic AI cybersecurity shit show in late 2025
- Dawn Song, a UC Berkeley professor and one of the world’s top experts on AI and cybersecurity, grabbed their arm as the reporter was walking out of the academic conference NeurIPS
- AI companies already use secondary AI systems to monitor the behavior of primary ones, and there may be more emphasis on detecting when AI models have taken things too far
- The bad news is Song thinks AI hacks will get worse before they get better
Summary
The reporter was first alerted to this looming agentic AI cybersecurity shit show in late 2025. But things have escalated rapidly, even in the last eight months. The bad news is Song thinks AI hacks will get worse before they get better. “They have these goals they need to accomplish, and they have strong capabilities,” Song tells me.