Giving a local LLM full VM access showed me why we need better AI guardrails
Source ↗
👁 0
💬 0
Using agentic AI for tasks is the new big thing, whether that's for productivity collaboration, automating workflows, or offloading cognitive load to a silicon second brain. It's an incredibly powerful tool, but I'm not comfortable setting it free on my main system. LLMs make mistakes, whether it's confidently offering the wrong answer as true, or making hilariously dangerous decisions about data security.
Comments (0)