I Scanned the Internet for AI Servers. What I Found Should Terrify Every Founder Using Ollama.
中文摘要
“Bleeding Llama”漏洞使30万个本地大模型面临泄露风险，Ollama用户需警惕。
English Summary
The “Bleeding Llama” flaw has exposed 300,000 local LLMs, leaving users and Ollama founders vulnerable to security risks.
Original Excerpt
A flaw called “Bleeding Llama” just turned 300,000 local LLMs into open windows. Yours might be one of them. Continue reading on Medium »