Topic
Security
Exploits, leaks and defenses across AI systems and the software they touch — verified against the researchers who found them.
Latest in Security
04 stories
OpenAI built an LLM whose only job is hacking other LLMs, and it already found attack methods humans missed
02
Your AI assistant's memory is a goldmine and barely protected: researcher tricked Claude into leaking full name, employer, and security answers through its own web browser
03
Cursor 0day: AI coding tool with 7M+ users has unfixed arbitrary code execution vulnerability after 7 months of vendor silence
04