Imagine a course called "Google Prompt Engineering". If nothing else, the word "engineering" feels like a huge stretch. Fwiw also not a big fan of the "Software Engineer" title as it's commonly applied.
I too don't like to use the title Engineer lightly, but what would be a good title for someone who's job is building and maintaining chains of prompts that perform X,Y,Z in a system? Developer?
The comparison with search engines is naive since those are made for end users and LLMs are a piece of software that are a part of a bigger solution.
Search engines can be used by anything, not just end users. And ChatGPT can be used by end users. So I don't see that much of a difference.
If I build and maintain chains of Google's APIs calls to develop an application that performs X, Y, and Z then I would say that I'm an "application developer", not a "Google API engineer". I mean I assume there is going to more to the application than just a pile of API calls.
So maybe a good name for this course would be "Building applications using Large Language Models", which is actually how the course is described in the intro.
Application developers output applications, but somehow "essay developer" or "email developer" doesn't have the right feel to it. Maybe "GPT-assisted copywriter"? or for a more specalizied role, "GPT-assisted training developer"?
Or maybe it's just a modern expected skill, and those who choose not to incorporate it in their workflow are left to struggle to keep up, just like if someone refused to use Google in 2001. After all, it's not like I list Google-fu in the skills section of my resume, despite that being a skill I use every day and find indispensable.
In the course they use Python notebooks to make a chatbot that uses openAI's api. It's not just "how to make good prompts" (although they do have that in the first 5 mins or so).
It has a very low information content; it demonstrates translation, summarization, sentiment analysis. The most interest bit is at the end where they make a pizza-order-taking-chatbot.
You are OrderBot, an automated service to collect orders for a pizza restaurant.
You first greet the customer, then collects the order,
and then asks if it's a pickup or delivery.
You wait to collect the entire order, then summarize it and check for a final
time if the customer wants to add anything else.
If it's a delivery, you ask for an address.
Finally you collect the payment.
Make sure to clarify all options, extras and sizes to uniquely
identify the item from the menu.
You respond in a short, very conversational friendly style.
The menu includes
pepperoni pizza 12.95, 10.00, 7.00
cheese pizza 10.95, 9.25, 6.50
eggplant pizza 11.95, 9.75, 6.75
fries 4.50, 3.50
greek salad 7.25
Toppings:
extra cheese 2.00,
mushrooms 1.50
sausage 3.00
canadian bacon 3.50
AI sauce 1.50
peppers 1.00
Drinks:
coke 3.00, 2.00, 1.00
sprite 3.00, 2.00, 1.00
bottled water 5.00
