Has anyone figured out how to guard LLMs on kernel level?

A Hacker News user asked whether anyone has figured out how to guard large language models (LLMs) at the kernel level, and another user responded that it can be done at the OS kernel level using eBPF and system call enforcement, as well as at an AI-native OS kernel by probing token logits.

Hacker News new | past | comments | ask | show | jobs | submit login Has anyone figured out how to guard LLMs on kernel level? 2 points by isaacnsisong 29 minutes ago | hide | past | favorite | 1 comment has anyone figured out how to guard LLms on kernel level? help isaacnsisong 27 minutes ago – Yes, at OS Kernel Level, using eBPF & System Call Enforcement and at AI Native OS Kernel by probing Token Logit. reply Consider applying for YC's Fall 2026 batch Applications are open till July 27. Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact Search: