AI article
AI Guardrails Aren’t Stopping Criminal Hackers
Publisher description: Hackers around the world are all-in on using agentic AI to wage attacks—and manipulating tools like Anthropic’s Claude to help them carry out their crimes.
Wired | Oct 21, 2026 | Lily Hay Newman
Automated excerpt
The former two exhibited sophisticated AI “harnesses,” the software that supports and guides a model to carry out tasks. All had left their AI infrastructure openly accessible on web servers, allowing the researchers to analyze their activity and which models they used—largely versions of Anthropic’s Claude as well as versions of the open-weight Deepseek models. The researchers observed the attackers using both open- and closed-weight models; in almost all cases, they were using older versions rather than working with frontier models.
Selected automatically from source text; not independently written or fact-checked. Read the original for full context.