AI Agent · Wired
They can find zero-day bugs in large codebases and scan computers for vulnerabilities at lightning speed
Compiled by KHAO Editorial — aggregated from 1 source. See llms.txt for citation guidance.
◌ Single Source
To get a closer look, the reporter decided to unleash one in their own home network.
Key facts
- Abliteration AI offers several fully de-aligned models, the most powerful of which is a version of Z.ai’s latest agentic coding model, GLM 5.3
- In the end, the reporter discovered that the best way to deal with AI hacking may well be having your own AI hacker
- The reporter got the idea for the experiment after discovering Abliteration AI, a startup that offers access to powerful AI models with the usual guardrails removed
- But Will, you might be thinking, giving an impish, all-powerful cybersecurity agent access to your home network is batshit
Summary
As the author of a newsletter about artificial intelligence, the reporter consider it their duty to experience the bleeding edge of this technology firsthand. You’re probably aware that frontier AI models have attained advanced cybersecurity capabilities in recent months. But Will, you might be thinking, giving an impish, all-powerful cybersecurity agent access to your home network is batshit. In the end, their experiment was revealing, but oddly reassuring, too.