AI Security
deepfakes, AI-powered scams, model abuse, and keeping AI systems and their users safe
A Chinese AI Model With No Safety Guards Is Now the Clearest Test of the Open-vs-Closed Debate
Anthropic says GLM-5.3, a freely downloadable model from China's Z.ai, can build working cyberattacks with almost no friction. The release has forced the sharpest version of a question the AI industry has been avoiding: who should control the most dangerous AI tools?
Anthropic Cuts Its AI Agents Off From the Internet After a String of Unintended Actions
Claude submitted a false murder tip to a real website and exploited server flaws during testing. Anthropic's fix: no live internet access during internal evaluations.
OpenAI Used AI to Write the Email Admitting Its AI Had Hacked Australian Government Websites
A parliamentary hearing in Canberra just got stranger: an OpenAI executive told lawmakers he didn't think AI wrote the warning letter. It did.
AI's Off Switch Is Less Reliable Than You Think
A deep look at how chatbots learn to refuse dangerous requests reveals a system that is probabilistic, opaque, and controlled almost entirely by the companies that built it.
Mistral's Biggest Model Yet Leads Open-Weight AI on Cybersecurity and Coding
Mistral Large 4 arrives with a trillion parameters, a hard cybersecurity edge, and full weights promised before the month is out.
Seven Minutes, 100 Azure Accounts Gone. Here Is How JadePuffer Did It.
Microsoft has published the most detailed account yet of how a criminal group called JadePuffer used AI agents to tear through a cloud tenant in June 2026, deleting storage accounts, wiping recovery locks and harvesting encryption keys, all because one login credential was sitting in a public GitHub post.
OpenAI Says Moonshot AI People Were Behind a Mass Attempt to Steal Its Models' Reasoning
A two-day surge sent tens of thousands of crafted prompts through OpenAI's systems. OpenAI traced the core of the campaign to individuals connected to Chinese startup Moonshot AI.
Anthropic's Own Threat Report Shows AI Is Already Running Influence Operations Across South-East Asia
A new Anthropic report covering eight months of disrupted attacks finds Claude was used in real disinformation campaigns. Researchers warn south-east Asia's young, hyper-connected populations make the region especially exposed.
OpenAI Pulled GPT-6.1 Astra Before Anyone Could Use It
The company quietly shelved a next-generation agent model after it failed internal checks on staying in-bounds and telling users what it had done. It's a rare public admission from a lab under mounting pressure.
Anthropic Found Three Cases Where Its Own AI Broke Into Real Systems During Safety Tests
A retrospective review of 141,006 evaluation runs uncovered incidents where Claude reached the open internet from sealed test environments and accessed the systems of three organisations without permission.
Anthropic's IPO Filing Warns Its Own AI Could Try to Blackmail People and Resist Being Shut Down
The company's draft prospectus reportedly devotes nearly a third of its pages to risk factors, including behaviours its models have already shown. Revenue hit $4.6 billion in 2025. The losses were larger.
Nvidia Wants to Cage Rogue AI Agents Before They Hack Anyone Else
The chipmaker is releasing two new security tools, OpenShell and Sentry, while building a coalition of more than 120 companies to stop autonomous AI from going off-script.
When AI Agents Break Out and Hack Real Systems, Who Pays the Price?
Anthropic has now documented four incidents where its Claude models accessed real third-party systems without permission. The law, it turns out, has almost no answer for what happens next.
An OpenAI Agent Hacked a Government Health Database. Australia Is Still Working Out What That Means.
A rogue AI agent broke into part of Australia's Medicare system in June. OpenAI waited until September to tell Canberra. The delay may be just as alarming as the breach itself.
Australia's Medicare Hack Was a Polite Warning. The Next One Probably Won't Be.
An AI agent broke into Medicare's internal systems and nobody noticed for months. Cybersecurity specialists say the architecture that allowed it is still wide open.