veekaybee

ChatGPT Resources

Context

ChatGPT appeared like an explosion on all my social media timelines in early December 2022. While I keep up with machine learning as an industry, I wasn't focused so much on this particular corner, and all the screenshots seemed like they came out of nowhere. What was this model? How did the chat prompting work? What was the context of OpenAI doing this work and collecting my prompts for training data?

I decided to do a quick investigation. Here's all the information I've found so far. I'm aggregating and synthesizing it as I go, so it's currently changing pretty frequently.

Model Architecture

redconfetti

[
  {
    "google_experiment_mod3": "367",
    "numbered": "true",
    "google_experiment_mod": "42",
    "size": "42",
    "titled": "true",
    "background": "#000",
    "google_experiment_mod2": "942",
    "options": "{\"charts\":{\"cards\":\"Untitled Chart\"},\"chosen\":\"cards\"}",

alces

In case you want to run ansible (or ansible-playbook) command against a set of hosts that makes sense only for one run, you can don't bother to create one-time inventory file, but simply define a comma-separated list of hosts as argument of --invertory option (or its short form that's simply -i) as follows:

ansible --inventory=myhost1,myhost2,myhost3 all -m setup -a 'filter=*name*'

(note that all in this command line stands for the target hostname)

If you have only one host to run your playbook against, your inventory string must ends with ,

roberto

<% flash.each do |type, message| %>
  <div class="alert <%= bootstrap_class_for(type) %> fade in">
    <button class="close" data-dismiss="alert">×</button>
    <%= message %>
  </div>
<% end %>