INBOX INSIGHTS: Build Your Digital Twin with Custom GPT, Marketing Job Market (11/15) :: View in browser
👉 Pre-Register for our new Generative AI for Marketers course!
Build a Custom GPT Model
Did you know you can now clone yourself?
Well, sort of.
Over the weekend, OpenAI rolled out the ability to create your own custom GPT model. Pretty cool, right?
Let’s not get ahead of ourselves. There are still a lot of limitations and considerations. As an experiment, Chris and I (mostly Chris) build a KatieGPT, using newsletter content as the foundation for the database. Since I’ve been writing the newsletter every week for a few years, there is a decent amount of content to pull from.
Once we loaded the content, gave some guidelines, and most importantly, updated the avatar, it was time to see what KatieGPT was capable of.
You
What are Katie’s latest thoughts on management?
GPT
KatieGPT
I searched through the available documents for specific insights into Katie’s latest thoughts on management but couldn’t find any direct references or detailed discussions on this topic. Her writings cover a variety of subjects, including marketing strategies, productivity, and the impact of technology on our work and personal lives, but they do not explicitly focus on her current views or philosophies regarding management.
If you’re looking for general insights on management from Katie, it might be helpful to consider her overall approach to topics like data-driven decision-making, transparency in communication, and the importance of adapting to change, as these themes could potentially reflect her management style and philosophy. However, without specific references in the documents, I can only make broad assumptions based on the general tone and content of her writings.
Welp.
I’m underwhelmed by KatieGPT. For context we gave the system all my cold opens from 2022 and most of the opens from 2023. I talk about management a lot. That’s what I do. That’s my area of expertise. However, despite having content that covers that topic, my doppelgänger had trouble finding useful content.
A couple of things could be the problem here. First, it could be that I don’t talk about management as much as I think I do. But let’s be honest, that’s not the issue. More realistically, we haven’t given the system enough content to work with. We also haven’t given enough diversity in the content. While the cold opens are good, they are from one point of view. They are me, talking to you, about a topic. They aren’t give and take. They have a specific tone.
My next step to start refining KatieGPT is to pull podcast and livestream transcripts. Then I would look for transcripts from talks and webinars. Next I would look at online conversations (where appropriate) and load all that content into the custom GPT model. The more data you give the system, the better the output will be.
This is, admittedly, and over simplification of building a custom GPT model. I’d recommend you go through actual planning exercises, like user stories, to help figure out what you need and how you’ll use it. Experimenting with a custom GPT model should be just that, an experiment. If you decide to use your model publicly, you’ll want to be much more thoughtful with how you build it. Think about the data you should be sharing. Think about the end user and what they will get out of the custom GPT model. Think about the maintence plan and how you’ll keep the system up to date.
If you want more details on building a custom GPT model, or how we set up KatieGPT, you can check out this week’s podcast
Do you plan on building your GPT clone? Reply to this email to tell me or come join the conversation in our Free Slack Group, Analytics for Marketers.
– Katie Robbert, CEO
Do you have a colleague or friend who needs this newsletter? Send them this link to help them get their own copy:
https://www.trustinsights.ai/newsletter
In this episode of In-Ear Insights, the Trust Insights podcast, Katie and Chris discuss the pros and cons of using AI chatbots like ChatGPT to automate content creation, and best practices for training them effectively, such as the TrustInsights.ai 5P framework and the SDLC.
Watch/listen to this episode of In-Ear Insights here »
Last time on So What? The Marketing Analytics and Insights Livestream, we reviewed generative AI for survey analysis. Catch the episode replay here!
So What is off this week, but be sure to catch past episodes on our YouTube channel. Are you following our YouTube channel? If not, click/tap here to follow us!
Here’s some of our content from recent days that you might have missed. If you read something and enjoy it, please share it with a friend or colleague!
Take your skills to the next level with our premium courses.
Get skilled up with an assortment of our free, on-demand classes.
This week, let’s take a look at the big picture and how marketing is faring, at least in terms of the job market. Is it getting easier or harder for marketers to find new work?
As always, we’ll look to data from the US Federal Reserve Bank of St. Louis and Indeed.com’s provided datasets. Indeed.com is one of the best sources for information about hiring because it doesn’t cost employers money to post jobs, so many HRIS (human resources information systems) and talent management systems automatically post jobs to Indeed.com, giving a good sense of the big picture for hiring, at least in the USA.
In terms of what we look at, we examine eight major categories of jobs, jobs that tend to have an outsized effect on marketing hiring: – Banking and finance jobs, because that’s where the money comes from for things like startups and investments – Information jobs, because IT and marketing are often co0mingled – HR jobs, because if HR isn’t hiring… – Management jobs, the people who are usually in charge of marketing – Marketing jobs, of course – Sales jobs, the people who are downstream from marketing and generate the revenue – Software development jobs, the people who work on the tools that provide marketing capabilities – And all open positions, because if people don’t have jobs, they don’t spend money, and that dampens demand for marketing eventually
What does the big picture, post-pandemic, look like?
What we see is that hiring has more or less leveled off in 2023. The horizontal black line on the graph indicates the baseline from February 2020, before the pandemic, and we see the massive distortions in the labor market since then. It looks like things are more or less back to normal… sort of.
Of special note – the red line represents all open positions. Hiring has remained broadly elevated, but many of these professional services/office jobs have fallen far below the hiring for the economy as a whole. Why this is the case, it’s not clear from the data, but at the end of 2022, the broader economy’s jobs decoupled from office jobs.
Let’s take a deeper look at 2023:
2023 started with the eight major categories all still well above baseline. By april, we started to see some significant weakness, particularly in marketing, software development, and IT. That weakness has persisted through the year, with sales jobs joining the below-baseline group in September.
More immediately, it looked at the end of September like marketing jobs (the purple line above) were turning a corner – and then that trend reverted in October. Why? Again, it’s unclear from the data, but we do see a significant loss in sales hiring contemporaneous with the decline in marketing jobs.
So what? What should we take away from this?
If you’re a company that’s hiring, the market is currently in your favor for sales folks, IT, software developers, and marketers. If you’ve been thinking about bringing on new people, now’s a great time to do it as you may be able to scoop up previously unavailable talent.
If you’re a marketer looking for work, the market is currently tougher than usual for the last couple of years. Anecdotally, some companies are making very short-sighted choices about staffing levels in marketing with the advent of generative AI; one company reportedly cut 80% of its marketing staff after senior leadership believed AI could do everything. They’re in for a rude awakening in a few months when they find out generative AI is very capable at tasks, but not jobs, and jobs require people.
If you’re looking for work, what should you do? There’s always a second job market that’s invisible to the data we all have access to. That second job market is built on relationships – who you know, and as our friend and colleague Mitch Joel says, who knows you. If you’ve got both skills and a personal network, you may even be able to create a job where one didn’t exist previously. At the very least, people who know you can alert you to positions that may exist that haven’t been posted publicly anywhere, giving you an opportunity to apply before they’ve opened up to the general public.
How do you find those positions? It’s all about building those professional relationships. Be an active, valuable member of communities where other professionals gather, such as Slack groups, Discord servers, LinkedIn groups, Threads communities, etc. Get to know people, and get other people to know you and what you’re good at.
Here’s a roundup of who’s hiring, based on positions shared in the Analytics for Marketers Slack group and other communities.
Are you a member of our free Slack group, Analytics for Marketers? Join 3000+ like-minded marketers who care about data and measuring their success. Membership is free – join today. Members also receive sneak peeks of upcoming data, credible third-party studies we find and like, and much more. Join today!
Imagine a world where your marketing strategies are supercharged by the most cutting-edge technology available – Generative AI. Generative AI has the potential to save you incredible amounts of time and money, and you have the opportunity to be at the forefront. Get up to speed on using generative AI in your business in a thoughtful way with our new offering, Generative AI for Marketers, which comes in two flavors, workshops and a course.
Workshops: Offer the Generative AI for Marketers half and full day workshops at your company. These hands-on sessions are packed with exercises, resources and practical tips that you can implement immediately.
👉 Click/tap here to book a workshop
Course: We’ve turned our most popular full-day workshop into a self-paced course. The Generative AI for Marketers online course launches on December 13, 2023. You can reserve your spot and save $300 right now with your special early-bird discount! Use code: EARLYBIRD300. Your code expires on December 13, 2023.
👉 Click/tap here to pre-register for the course
Interested in sponsoring INBOX INSIGHTS? Contact us for sponsorship options to reach over 26,000 analytically-minded marketers and business professionals every week.
Where can you find Trust Insights face-to-face?
- Social Media Marketing World, San Diego, February 2024
- Australian Food and Grocery Council, Melbourne, May 2024
- MAICON, Cleveland, September 2024
Going to a conference we should know about? Reach out!
Want some private training at your company? Ask us!
First and most obvious – if you want to talk to us about something specific, especially something we can help with, hit up our contact form.
Where do you spend your time online? Chances are, we’re there too, and would enjoy sharing with you. Here’s where we are – see you there?
Our Featured Partners are companies we work with and promote because we love their stuff. If you’ve ever wondered how we do what we do behind the scenes, chances are we use the tools and skills of one of our partners to do it.
Read our disclosures statement for more details, but we’re also compensated by our partners if you buy something through us.
Some events and partners have purchased sponsorships in this newsletter and as a result, Trust Insights receives financial compensation for promoting them. Read our full disclosures statement on our website.
Thanks for subscribing and supporting us. Let us know if you want to see something different or have any feedback for us!