minus-squareShortN0te@lemmy.mltoSelfhosted@lemmy.world•OpenClaw with Docker. Is it safe?linkfedilinkEnglisharrow-up2·6 days agoSimple put, no. In order to be save with a LLM that can execute stuff on its own it needs to be completely sandboxed. A very nice talk about flaws in agentic AI can be found here: https://media.ccc.de/v/39c3-agentic-probllms-exploiting-ai-computer-use-and-coding-agents linkfedilink
Simple put, no. In order to be save with a LLM that can execute stuff on its own it needs to be completely sandboxed.
A very nice talk about flaws in agentic AI can be found here: https://media.ccc.de/v/39c3-agentic-probllms-exploiting-ai-computer-use-and-coding-agents