logoalt Hacker News

SubiculumCodeyesterday at 6:15 PM1 replyview on HN

What is your sandbox approach? Any good guides? Something about asking a LLM for advice on how to sandbox LLMs.....


Replies

kstenerudyesterday at 6:43 PM

I use this: https://github.com/kstenerud/yoloai

    yoloai new mysandbox .   # Create a sandbox
    yoloai attach mysandbox  # Attach the sandbox to the current terminal
    ... (^b^d to disconnect) # It's using tmux to keep the agent alive
    yoloai diff mysandbox    # See what the agent did
    yoloai apply mysandbox   # apply its changes to your workdir
    yoloai destroy sandbox
You can also make it run a prompt and block until it's done:

    yoloai run mysandbox . -p "read issue https://github.com/kstenerud/yoloai/issues/190 and fix it"
    yoloai diff mysandbox
    yoloai apply mysandbox
    yoloai destroy sandbox
show 1 reply