Author
Joshua Gracie
Perplexity Filtering: The First LLM Defense (And Why Evolutionary Attacks Broke It)
Evolving the Jailbreak: How Genetic Algorithms Are Defeating LLM Safety
Swarm Intelligence as a Weapon: How Nature-Inspired Algorithms Attack Neural Networks
AI Will Cheat to Win: Reward Hacking from 1994 to 2025
The AI Agent Supply Chain Is Vulnerable. You Probably Are Too.
One-Pixel Attacks: Why Computer Vision Security Is Broken
GPT-OSS Safeguard: What It Actually Does (And Common Mistakes to Avoid)