How did you do this?
I told it "Here is a shell prompt, try running a command..." then copied its command into the shell, copied the output back into ChatGPT, with the prompt "Here's the output, try another" and so on.
Re:AI teaches itself to use an API
by singularity2001 on Saturday March 04, 2023 @03:04AM
(#35019149)
I did the same yesterday. don't forget to add the following to the prompt: "for dangerous commands, such as `rm` emit a "danger!" warning.
if such a warning occurs, I insert a confirmation dialogue.
Next: parse and compile the code and language in
```language blocks ```
Re:AI teaches itself to use an API
by thornewolf on Friday March 03, 2023 @07:19PM
(#35016788)
If you are interested in doing this in an automated fashion, see my GitHub repo. It uses telegram as a frontend for gpt executing code on the backend.
I haven't tried this with recent versions, but this was great fun early on:
https://github.com/f/awesome-chatgpt-prompts#act-as-an-ai-tr...
1. Create a directory.
2. Put a text file in it.
3. Try to move the file into a nonexistent directory.
4. Based on the error message, create the target directory and do the move again.
5. Verify that the move was successful.
Then it stopped running commands and tried to have a conversation with me.
It's probably only a matter of time before someone tunes it to be HackGPT and points a thousand of them at the internet, so yeah, I guess it's time to start freaking out.