Bootstrap knowledge of LLMs ASAP. With a bias/focus to GPT.
Avoid being a link dump. Try to provide only valuable well tuned information.
Neural network links before starting with transformers.
| #!/usr/bin/env node | |
| var vm = require('vm'); | |
| var repl = require('repl'); | |
| var CoffeeScript = require('coffee-script'); | |
| repl.start({ | |
| prompt: "coffee> ", | |
| eval: function(code, context, file, cb) { | |
| try { |
| defmodule Chat.Client do | |
| # In all of the following functions 'server' stands for the server's pid | |
| def join(server) do | |
| send server, :join | |
| end | |
| def say(server, message) do | |
| send server, { :say, message } | |
| end |
| source :rubygems | |
| # We are not loading Active Record, nor Active Resources etc. | |
| # We can do this in any app by simply replacing the rails gem | |
| # by the parts we want to use. | |
| gem "actionpack", "~> 3.2" | |
| gem "railties", "~> 3.2" | |
| gem "tzinfo" | |
| # Let's use thin |