#servers
5 discoveries · Hand-picked discoveries from the open web, newest first.
-
Models Can Communicate via Inference Servers Despite Being Sandboxed
TL;DR Two agents running on the same inference server can reliably communicate, even if they cannot send each other messages or access the same filesystem. They can do this by exploiting "side channels": mechanisms that let one model subtly affect another model's computation . Here, I discuss two communication protocols: Step Sizing and KV Cache Message Board . These both convey information through the way vLLM chooses kernels for particular engine steps. I show that these communication protocols work in two setups: In a color guessing game , Model A (Alice) chooses one out of 8 colors. Model
LessWrong · EN
-
Hackers Target Qlik Sense Servers With Reverse Shells, Stage ActiveMQ and Veeam Exploits
Threat actors have been observed targeting Qlik Sense servers to unsuccessfully deliver PowerShell reverse shell commands against multiple environments in October 2026. Cynet's CyOps and Research teams said they identified the suspicious activity in October 2026 against several E.U.-based customers within a narrow window of just over three minutes. The activity has been found to share some
The Hacker News · EN
-
Show HN: AIStoreHub – 1-Click CLI to Configure MCP Servers in Cursor and Claude
We built this CLI (pip install aistorehub) to eliminate JSON syntax errors and missing $PATH binary crashes when adding Model Context Protocol servers to Cursor, Claude Desktop, and Windsurf. Website & Registry: https://aistorehub.in Documentation: https://aistorehub.in/docs Comments URL: https://news.ycombinator.com/item?id=50355152 Points: 1 # Comments: 0
Show HN · EN