Does GPT-3 threaten your engineering job?

Does GPT-3 threaten your engineering job?

by | 7 min read
Originally posted on newsletter.alexhyett.com
Published:
Updated:

AI and GPT-3 seem to be everywhere in the last few months.

With ChatGPT we finally seem to be one step closer to realising the type of artificial intelligence we have seen in movies.

Obviously, we are quite a way off from Terminator-like AI. Your life might not be at threat just yet but what about your job?

Let’s have a look at what ChatGPT can do and whether we should be worried just yet.

What is ChatGPT?

ChatGPT is an AI chatbot that has been trained on various programming languages as well as other sources to help developers write and debug their code by having a conversation with it.

The point of ChatGPT is to be an assistant rather than a replacement for programmers but some people are already saying that it may replace us all one day.

What can ChatGPT do?

So let’s have a look at an example and see what we can get ChatGPT to do for us.

I asked ChatGPT the following:

Chat GPT Prompt 1

This was the reply I got:

Response 1

Ok wow, it actually produced some comprehensible code. This is the code if you are interested:

import requests
from bs4 import BeautifulSoup

URL = "https://books.toscrape.com/"
page = requests.get(URL)

soup = BeautifulSoup(page.content, 'html.parser')
results = soup.find(class_='side_categories')
self_help_link = results.find_all('a')[1]['href']

URL = URL + self_help_link
page = requests.get(URL)
soup = BeautifulSoup(page.content, 'html.parser')

results = soup.find(class_='product_pod')

top_self_help_books = []
for result in results:
    book_title = result.h3.a['title']
    top_self_help_books.append(book_title)

print(top_self_help_books)

Does it work though? No.

I get the following error when I try and run it:

Traceback (most recent call last):
  File "/Users/alex/Projects/chatgpt.py", line 19, in <module>
    book_title = result.h3.a['title']
  File "/usr/local/lib/python3.10/site-packages/bs4/element.py", line 965, in __getattr__
    raise AttributeError(
AttributeError: 'NavigableString' object has no attribute 'h3'

Not off to a great start.

Let’s try asking it to fix its own code. So are asked the following:

ChatGPT Prompt 2

This was its response:

Reponse 2

When I make the change it suggests, the code actually runs and gives me an output:

["It's Only the Himalayas", 'Full Moon over Noah’s Ark: An Odyssey to Mount Ararat and Beyond', 'See America: A Celebration of Our National Parks & Treasured Sites', 'Vagabonding: An Uncommon Guide to the Art of Long-Term World Travel', 'Under the Tuscan Sun', 'A Summer In Europe', 'The Great Railway Bazaar', 'A Year in Provence (Provence #1)', 'The Road to Little Dribbling: Adventures of an American in Britain (Notes From a Small Island #2)', 'Neither Here nor There: Travels in Europe', '1,000 Places to See Before You Die']

Although these clearly aren’t self-help books. I can see from the code that it has just picked the second link in the list (which is Travel) rather than finding the words Self Help.

Let’s see if I can get it to fix itself again.

ChatGPT Prompt 3

This was what it came back with:

Response 3

So exactly the same code as before pretty much, which would still give me back the travel books.

Still, the fact that it came back with any code at all is still pretty amazing, even if it did require a bit of prompting to make it actually work.

Could ChatGPT replace programmers?

It is still early days for ChatGPT and what it can do is already promising.

I can see ChatGPT being a useful tool for beginners who don’t even know where to start. Even just as an aide for programmers to write code quicker.

It would have only taken me 20 minutes or so to write the above example myself after factoring in looking at the website’s source code. ChatGPT was still quicker though, even with the mistakes.

You do have to be quite specific with the requests though but I can see ChatGPT getting better with this over time.

ChatGPT is currently free to try out but it is costing OpenAI a staggering $3 million a month. Apparently each word generated costs $0.0003. This can soon add up, especially with the wordy examples I have tried.

As we have seen the accuracy is not that great either. It seems to generate code with errors and can’t always fix all the ones that it is given. This is why StackOverflow have banned responses generated with ChatGPT.

If the cost comes down and the responses are accurate then I can see some programmers being out of a job in a few more years.

The programmers that are going to be affected are the ones that aren’t solving problems themselves and are simply copying and pasting from StackOverflow.

If we ever do find ourselves in a world where all code is being written by AI then possibly there will be a new job title, “AI Prompt Architects”. These people will carefully construct questions for GPT so that it generates the correct code.

I am pretty sure QA and SDET engineers are safe for a while. If we don’t trust experienced engineers to write fault-free code (which we shouldn’t) then I doubt we are going to trust AI-generated code anymore.

❤️ Picks of the Week

💻 Software - n8n - I have been using n8n all this week to automate publishing my blog posts as well as some of my tweets. If you haven’t heard of n8n it is like a self-hosted IFTTT. I will do a blog post soon on how to set all this up. I currently have it running for free on Railway.

📚 Book - Four Thousand Weeks by Oliver Burkeman - this was a Christmas present from my sister in law. Not your typical self help book but if you are interested in the finitude of life then this is worth a read.

📝 Article - All Success Is a Lagging Indicator - I really like Ryan Holiday’s writing and this piece is no exception. It also comes at a good time in my life as I am putting in a lot of work, see below.

👨‍💻 Latest from me

One of my goals for 2023 is to produce more content, a lot more. To do this I am publishing a blog post every day. Whether I can keep this pace going for the whole of 2023 remains to be seen but I am going to try.

One quick ask, if you have a Medium account it would really help me if you could give me a follow over there as well.

🎬 YouTube - Finally Understand Regular Expressions - In Just 7 Minutes! - Regular expressions always seem to be a sore point for many developers so I have tried to demystify them in this video.

📝 Article - How To Set Goals That You Can Actually Keep - It is January and many of you will be setting goals for the year ahead. Here are some tips to actually keep them this year.

📝 Article - Understanding Big-O Notation - Writing code that scales well is hard. It can help if you can work out how your code is behaving the more data that it has to handle.

📝 Article - Applying the Pareto Principle for Exponential Results - The 80/20 rule is everywhere you look. I take a look at how you can make the most of this principle and make this your best year yet.

📝 Article - How I Take (and Organise) My Notes As a Software Engineer - I did a YouTube video on this recently but ended up being quite long and I still didn’t go into as much detail as I would have liked so I wrote this post as well.

📝 Article - How I would learn to code (if I could start over) - This turned out to be a bit of an autobiography about how I got into software development and if I would do anything different if I was to learn to code again.

📝 Article - Why Buying More Stuff is Never Going to Make You Happy - We live in a society obsessed with buying stuff. But what is it all for?

💬 Quote of the Week

“If work dominated your every moment, would life be worth living?”

Andrew Taggart

From The Pathless Path by Paul Millerd. Resurfaced with Readwise.


🙏 Was this helpful? If you want to say thanks, I love coffee ☕️ , any support is appreciated.