New 42-day free trial
Smarty

    • Use ChatGPT to write better code, faster

    Adam and Ryan recently demonstrated how to build a functional application using ChatGPT to generate large amounts of code. Read all about it here!
    Andrew Townsend
    Andrew Townsend
     • 
    June 28, 2023
    link-icon
    Tags
    Webinar blog tagWebinarProgramming blog tagProgramming

    In our recent webinar, we brought together two of our software engineer experts, Adam Charlton and Ryan Cox, to demonstrate how to build a working application using ChatGPT to generate most of the code.

    We know what you're thinking: ChatGPT can't take our jobs; we've tried.

    This is wonderfully true. ChatGPT can pull together useful bits of information but still needs to be guided and curated by a human, preferably one with subject knowledge.

    The exact working scenario given by Adam and Ryan was:

    Write code in Python that takes an address and delivers the ten closest addresses to that address. The use case is you have a client that like your services, and you want to advertise to all of their neighbors.

    On the first run, ChatGPT did deliver code that, when plugged into the terminal, pushed out an address. Unfortunately, it was only the exact address that was input.

    One of the critical points that Ryan and Adam spoke about is knowing how to debug the code that ChatGPT spits out.

    Here are some tips they gave us in spot-checking code from ChatGPT.

    ChatGPT only has knowledge through September 2021: When you ask ChatGPT to write code referencing data on a website, know that it’s pulling that data from the 2021 version of that website. When we asked it to look at the Smarty code, we had to reference SmartyStreets, our company name, in 2021.

    Be very specific, or ChatGPT will guess: We asked ChatGPT to use a Smarty address API to solve our problem, but we weren't specific about which one. ChatGPT then pulled the first API it found that met the criteria, and we had to adjust our request to find the specific API needed.

    If you want specific data to be referenced, feed that data to ChatGPT: While its general knowledge is several years old, you can feed ChatGPT reference code or data to pull from in its next response. There's, of course, a risk of giving it proprietary information, so be aware of that.

    ChatGPT is not deterministic: You can ask the same question of ChatGPT several times and get a different answer each time. This can cause problems if you're leaning on ChatGPT too heavily.

    Watch the full webinar recording for even more helpful tips and to see exactly how Adam and Ryan were able to get a working application in only 30 minutes.

    If you want to follow along with them, you can get 1,000 free lookups with a free account today.

    Subscribe to our blog!
    Learn more about RSS feeds here.
    rss feed icon
    Subscribe Now
    Read our 5 address validation use cases ebook nowDownload now
    Read our recent posts
    Ecommerce shipping efficiency tools you need: Address autocomplete and verification
    Arrow Icon
    We know it’s not New Year's anymore, but we can still push for improvement and efficiency in our lives. Maybe you’ve lapsed on that goal to be healthier or slightly slipped on your new reading and writing regimen. No worries. Not only are we here to remind you to KEEP GOING on whatever goals you have, but we’re also here to give you an easy-to-implement solution that will create shipping efficiency and stop sending packages into the void. I mean, we’re assuming you don’t like wasting money. If you do… that’s how we’re different.
    Patient form optimization: The $17.4 million problem
    Arrow Icon
    Let's start with a number that should make every hospital administrator do a double take: $17. 4 million. That’s how much the average hospital loses annually—just from denied claims due to patient misidentification. This isn’t from equipment costs, not from staffing shortages, and not even from insurance negotiations—just from keeping bad patient data. Surely, our forms aren’t that bad. (Yes, they are, and stop calling me Shirley. )But here’s the reality: According to the 2016 Ponemon Misidentification Report, 30% of hospital claims get denied, and over a third of those denials are caused by inaccurate or incomplete patient information.
    The GPS adventures of a distracted developer
    Arrow Icon
    My name is Jeffrey Duncan, and at the pestering of Smarty’s editor, I’m writing a blog about the many adventures I’ve had in life and how address data has played a big part in them. I met my wife about eight years ago on a dating website. At the time, I lived in Provo, Utah, while she lived in Palmwoods, Australia, on the east coast of Queensland. On this dating app, I entered the area where I was interested in finding someone, about a 25-mile radius of Provo, Utah. I had no intention of leaving the valley, definitely not the state, and certainly not the country.
    Previous Post
    Next Post

    Ready to get started?

    Schedule Demo
    42-day Free Trial