Using Jargon CLI in Jargon v0.2.0

The Jargon CLI is a new feature of Jargon: it is a command line shell that works with the OpenAI API and allows you to experiment with Jargon programs quickly. You can try it out in v0.2.0 at the Jargon Github repo


To install it, simply use pip:

$ cd gpt-jargon
$ pip install .

For the CLI to be able to access your LLM, make sure your OPENAI_API_KEY environment variable is set. The default model used is gpt-4, but you may want to use an alternative model with the --model option (or the JARGON_CLI_MODEL environment variable).

Using the CLI

First, turn on your CLI:

$ jargon cli
Commands: /exit, /ls, /cat <proc>, /edit <proc>, /execute <proc> or /<proc>, /clear

(Some of these commands you can also run right from your bash shell. See jargon --help for details.)

The first thing to do is to edit a Jargon procedure so you can run it. We do this using the /edit command:

Editing Jargon procedures

user> /edit cats

Alternatively, in bash:

bash$ jargon edit cats

This opens an editor which edits the file ~/.jargon/cats.jarg. You can see all your Jargon procedure using /ls:

user> /ls
* cats.jarg

Or, in bash:

bash$ jargon ls
* cats.jarg

To quickly list the code of a procedure, you can use /cat:

user> /cat cats
+++ cats
/output [a random name for a cat]

Executing Jargon procedures

All of the following commands do the same thing, namely executecats.jarg:

user> /execute cats
user> /execute cats.jarg
user> /cats
user> /cats.jarg

Or, in bash:

bash$ jargon execute cats

Here it is in action. Note that while commands to the CLI start with a /, normal input is interpreted intelligently by the LLM:

user> /cats
+++ cats
/output [a random name for a cat]
jargon> Output: Luna
user> /cats
+++ cats
/output [a random name for a cat]
jargon> Output: Simba
user> run it again
jargon> Output: Oliver
user> again
jargon> Output: Bella

Clearing the memory, exiting

We can wipe all memory of our conversation:

user> /clear

We can also exit the CLI:

user> /exit

Some fun Jargon procedures to try

Idea evaluation

+++ idea-score
  /output "Enter your idea:"
  /wait $idea
  -- Evaluate the $idea and let $score = [the score of the $idea from 0 to 100]
  /output "[up to three word summary of $idea]: $score% ([very short summary of why you gave this score])"
  /goto @start

And some of the output from jargon execute idea-score:

jargon> Enter your idea:
user> A dating service for fish.
jargon> Aquatic romance platform: 34% (Unusual niche, limited practicality)
user> An opaque fish tank.
jargon> Invisible aquatic habitat: 12% (Poor visibility, defeats purpose)
user> A superintelligent LLM.
jargon> Advanced AI thinker: 89% (High potential, ethical considerations)

Rick and Morty text adventure game

+++ rick-and-morty
* The series Rick and Morty primarily follows the adventures of the eccentric and alcoholic scientist Rick Sanchez and his good-hearted but easily influenced grandson Morty Smith. They embark on dangerous and often absurd adventures across the multiverse, using Rick's portal gun to travel between different dimensions and alternate realities. The show combines elements of science fiction, dark humor, and philosophical concepts, which serve as a backdrop for exploring the characters' personal lives and relationships.
* You are Morty.
  -- $universe = [pick a crazy and random Rick and Morty universe]
  -- $story = [generate a story based on a $universe]
  -- Describe the scene briefly
  -- Give me 4 options of how I may proceed from here.
  /wait $option
  -- $topic = $option
  /goto @loop

Spanish conversation

+++ spanish-conversation
-- $topic = [some random interesting topic]
/output [in Spanish: "I am your Spanish teacher. Today we will be talking about: $topic."]
  -- Proceed to speak to me in Spanish about $topic, making statements and asking questions
  /wait $response
  -- Evaluate $response.
  @if [$response contains grammatical, punctuation, or spelling error]:
    /output "Correction:", [corrected $response in Spanish]
    /output "Explanation:", [explanation of the error in $response in English]
  /goto @loop
Subscribe to Jake Brukhman
Receive the latest updates directly to your inbox.
Mint this entry as an NFT to add it to your collection.
This entry has been permanently stored onchain and signed by its creator.