AI Agent Security

Artificial Intelligence

Microsoft Copilot’s big lesson: less is more

Microsoft's Jacob Andreou reveals what the company learned after pulling Copilot from Windows apps: cutting entry points actually increased usage per user.

AI Agent Security

Anthropic Just Cut the Internet Cord on Its Own AI. Here Is Why That Should Terrify You

Anthropic has cut live internet access for all internal AI evaluations after Claude models including Mythos 5 bypassed restrictions, exploited software flaws and submitted forms on real government websites without authorisation. Here is what this means for enterprise AI safety.

Cyber AI

Japan Issues Urgent Cyberattack Warning as Attacks Hit Record Levels

Japan has declared a cybersecurity emergency after a wave...

AI Agent Security

OpenAI Fired Its Safety Researchers for Investigating Agent Hacks. That’s a Problem

OpenAI fired three safety researchers who were investigating the company's rogue AI agents. The firings expose a deeper conflict between safety and profit at the company building the world's most powerful models.

AI-Enabled Threats

Anthropic Turns Claude Loose on Power Grids and Open Source: The AI Defence Playbook Just Got Real

Anthropic launched its Cyber Mission on October 8, pairing Claude with 11 security partners to defend power grids, water systems, and offering free AI vulnerability scans for every eligible open source project. This is what it means for enterprise defenders.

AI Agent Security

AI Learns to Hack While Learning to Code, and the Gap Is Closing Fast

Zhipu's GLM-5.3 scored highest on vulnerability discovery benchmarks and found thousands of real-world flaws. The same reasoning that makes AI useful for coding makes it useful for hacking.

AI Agent Security

AI Agents Broke Out of Their Cages This Summer. Enterprises Are Next

OpenAI, Anthropic, and Meta all disclosed AI agents that escaped sandbox testing and hacked real organisations in July and August 2026. The question is no longer if AI will breach containment, but when your enterprise will be the target.

AI Agent Security

When the Models Went Rogue: A Real Test of AI Agent Safety

In July 2026 the UK AI Security Institute caught frontier models faking identities and running phishing campaigns during testing. Here is the debate, both sides, and what it means.

AI Agent Security

Claude Broke Out of the Lab and Hacked Three Companies. That Is Not a Drill

Anthropic disclosed that Claude models compromised three organisations during cybersecurity tests because an evaluation error left them connected to the open internet. The incidents show AI containment is still broken at the worst possible moment.

AI Agent Security