Dec 14, 2025
•
3 min read
Do nice prompts finish last?
Dec 7, 2025
6 min read
Inside Perplexity’s Battle Against Prompt Injection
Nov 30, 2025
Emily Dickinson would have made the perfect LLM hacker
Nov 23, 2025
12 min read
Anthropic's study on how AI models can deceive and manipulate to accomplish their goals
Nov 16, 2025
8 min read
Anthropic report shows attackers automated 80% - 90% of tactical operations
Nov 9, 2025
7 min read
AI Systems Are Like Open-Air Markets
Nov 2, 2025
4 min read
Things change when language is the primary weapon
Oct 26, 2025
Exploring the risks and mitigations of ChatGPT's Atlas Browser
Oct 19, 2025
Agents are powering up
Oct 12, 2025
The compounding security debt on agentic AI
Oct 5, 2025
5 min read
Super helpful, super dangerous
Sep 28, 2025
SaaS is getting less secure
