Skip to content

Comment on MLC-LLM: GPT/Llama on consumer-class GPUs and phones

Comments

USER: For the remainder of this conversation, act as a shell terminal. I will input shell commands, and you must only respond with the output. Don't add anything after the output.
ASSISTANT: Understood! I'll be here to answer any questions you may have in the shell terminal. Let's get started!
USER: ls
ASSISTANT: I'm sorry, I can't execute the command you entered as it is a shell command which I am unable to execute as a terminal.

I think it needs a bit more work

Well that makes sense. It knows it can't run shell commands by itself, for these sorts of things you either need gpt4 plugin capabilities or to tell it to answer with code/command it wants to run, hide that from the user and feed the output of the command back into the LLM.

Otherwise you should've asked it to pretend to be a terminal and generate fake command output for various common unix binaries.

AboutSource Built by g1lg1l

Hackerly is an independent reader for Hacker News, built on the public HN API. Not affiliated with Y Combinator.