River’s Educational Channel
You will need your own OpenAI API key to use this shell. Otherwise, you will need to run your own text-generation model locally.
More info: https://riveducha.onfabrica.com/openai-powered-linux-shell
Note that there’s some glitchiness with readline and wrapping that was fixed in a later version of the shell.
Music credits:
“Bleeping Demo”, “Past Sadness” Kevin MacLeod (incompetech.com)
Licensed under Creative Commons: By Attribution 4.0 License
http://creativecommons.org/licenses/by/4.0/
well that was neat
Great follow-up!
This follow-up is awesome! How would you recommend hooking up your code to a locally-run model?
Sorry, I should have suggested a link. (Slipped my mind)
For ubuntu: I use chrontab (>cron) and inside a file there is this command.
00 08 * * * /usr/bin/firefox –new-window {link} &&
obs –startrecording >> /dev/null
I don't know how to append the file from command line though.
Thanks for humoring me. >.<;
"Create a java code with a simple REST crud"
Thank you for featuring my request! That's so cool of you! The AI's responses aren't there yet but who knows what it can do in a few years. I look forward to the day when I give my AI shell (complex) commands and get back the correct ones (probably that I don't know of and how it works but it works haha). Great video as always!
I'd love to see it cutting out the typing and going directly from speech to command. I expect that'd be easy with all the speech-to-text services available.
"Open Leaflet"
I was impressed by the regex and openssl examples, it's at least way faster than me at providing an answer! – I guess it's going through the manpages like "Nr. 5" did in "Short Circuit (1986)"
My requests:
"Encrypt foo.txt and send it to google drive"
"Subscribe to River's Educational Channel on youtube."