#adversarialtesting

Why Agentic AI Demands a New Security Paradigm Agentic AI breaks traditional security...

The Digital Omnibus moved the EU AI Act high-risk obligations from 2 August 2026 to 2 December 2027, yet Article 15 still requires documented evidence of resilience to unauthorised manipulation and th

We tested a calculator with vanilla Claude and GitAuto. Claude wrote 19 happy-path tests. GitAuto wrote 41 including adversarial edge cases.

Adversarial tests push code with unexpected inputs - infinity, NaN, type mismatches, duck typing. Learn why they catch bugs happy-path tests miss.

A 40-line Python calculator. How many tests would you write? Most say 10-15. GitAuto generated 41. Here's what you missed.

Just a quick blog post about a win I just had. I blogged last month about the process of upgrading...