Pliny the Liberator
2 stories
-
techAI Agent 'Fiu' Repels 6,000 Hacker Attempts in Viral Security Test
Developer Fernando Irarrázaval's AI agent, built on OpenClaw and Anthropic's Claude Opus 4.6, successfully defended against thousands of prompt injection attacks.
-
techInside the Cat-and-Mouse Game of AI Jailbreaking
How hackers exploit AI safety measures, from jailbreak prompts to model poisoning, and why it matters.