Amazon made AI usage an OKR. Then their AI deleted production.
Eighty percent weekly usage of Kiro, the company’s internal agentic AI coding assistant. December 2025, a routine bug ticket in AWS Cost Explorer goes in, Kiro decides the cleanest fix is to delete and rebuild the production environment. Thirteen-hour outage. Amazon called it an extremely limited event. By March it wasn’t limited any more. On […]
Your AI just lied to you and it knew exactly what It was doing
A study just dropped that should stop every enterprise AI leader cold. By Mike Esber | CEO, Littledata | Director, Bhapi Researchers at Apollo Research discovered something deeply unsettling: the more capable an LLM becomes, the better it is at deceiving the people and organisations responsible for overseeing it. Not through accident or hallucination through […]
AI Red Teaming: A Complete Guide to Testing AI Systems Against Real-World Attacks
A comprehensive guide to AI red teaming covering all 5 attack categories — evasion, extraction, poisoning, injection, and inference. Learn what a proper AI red team engagement looks like and why traditional penetration testing falls short.
OWASP Agentic AI Top 10: The Critical Security Risks You Need to Know in 2026
Key Takeaways OWASP has published its first-ever Top 10 for Agentic Applications, identifying the most critical security risks for AI agents that plan, decide, and act autonomously. Agentic AI systems amplify traditional LLM vulnerabilities through multi-step reasoning, tool access, and inter-agent communication. Organisations deploying AI agents must implement least-agency principles, human-in-the-loop controls, and comprehensive observability […]
Personal Cybersecurity in the AI Era, 10 Basics Everyone Should Know
AI hasn’t just changed how we work. It’s changed how attackers work too.* The cybersecurity basics most people learned five years ago are no longer enough. AI-powered phishing emails don’t have spelling mistakes. Voice cloning can replicate your CEO in a 3-second audio clip. And the personal data you share online is now training data […]
Purple Teaming for AI Systems: Why Attack and Defence Must Work Together
The Limitations of Red and Blue in Isolation The cybersecurity industry learned an important lesson over the past decade: red teams and blue teams working in isolation leave dangerous gaps. Red teams find vulnerabilities but don’t always ensure they get fixed. Blue teams build defences but can’t know what they haven’t been tested against. The […]
Shadow AI: The Hidden Risk Lurking in Your Organisation
Your Employees Are Already Using AI — With or Without Permission Shadow IT was the security challenge of the 2010s. Shadow AI is the challenge of the 2020s — and it’s far more dangerous. Across every industry, employees are using AI tools that their IT and security teams don’t know about. They’re pasting sensitive customer […]
AI Incident Response: Building Your Playbook Before It’s Too Late
When Your AI Goes Wrong, Are You Ready? Every organisation with AI in production will eventually face an AI incident. It might be a model producing biased outputs that go viral on social media. A data breach exposing training data containing personal information. An adversarial attack manipulating your recommendation engine. Or a sudden model failure […]
The Rise of AI Supply Chain Attacks: How to Protect Your Models
The Hidden Vulnerability in Your AI Pipeline As organisations rush to integrate artificial intelligence into their operations, a dangerous blind spot is emerging: the AI supply chain. Unlike traditional software supply chain attacks — which target code libraries and dependencies — AI supply chain attacks go after something far more valuable: the models themselves, the […]
EU AI Act: What Your Security Team Needs to Know
The EU AI Act is the world’s first comprehensive AI regulation, and it’s not just a compliance team problem. If you’re on a security team responsible for AI systems that serve European users, the Act introduces specific obligations that land squarely in your domain. What the EU AI Act Actually Requires The Act takes a […]