Almost Timely News: Recipes vs. Principles in Generative AI (2024-03-03)
Almost Timely News: Recipes vs. Principles in Generative AI (2024-03-03) :: View in Browser
?? Missed my last Intro to Generative AI webinar? Catch the next one for free on March 19. Register here!
Content Authenticity Statement
95% of this week's newsletter was generated by me, the human. You'll see some outputs from Gemini in the opening section. Learn why this kind of disclosure is now legally required for anyone doing business in any capacity with the EU.
Watch This Newsletter On YouTube ??
What's On My Mind: Recipes vs. Principles in Generative AI
Last week, we talked over principles-based prompt engineering.
And you were not impressed. In fact, last week's newsletter scored as one of the lowest issues in recent times (each issue has a one-click survey below the main article). And I have a hypothesis as to why. There's a big difference between recipe and concept, between principles-based prompt engineering and "here's a template, just copy and use this".
To build long-term success, you absolutely need to understand concepts and apply them. You start with the basics, you learn variations, and then you transcend the basics, a concept from the Japanese martial arts known as shu-ha-ri - learn the basics, vary the basics, transcend the basics. It's a process as old as professions themselves.
But that's for the long-term, for when you're trying to master a discipline over a period of years, perhaps even decades. When I go to the dojo on Saturday mornings, it's an expression of this principle in action.
The reality is, that's not most people's intent with generative AI, to have it be a discipline that you master over years. Why? Well, based on conversations I've heard in Analytics for Marketers and other forums, you're overwhelmed. Overwhelmed by generative AI, but overwhelmed and overworked in general. You're running without a full team, perhaps even a skeleton crew.
And that means your brain might not be receptive to investing a lot of time, the way you might study an art form. The analogy I often use is from cooking (huge surprise) is the difference between learning the principles of cooking versus following a recipe.
For example, a cooking principle is to always salt your tomatoes regardless of application. Tomatoes contain glutamic acid, which when combined with salt, form a natural kind of MSG, making them taste much better. That's the principle. Contrast that with a recipe which simply tells you to put salt on the tomatoes before serving in, say, a caprese salad. You don't know why you're doing it, but you do it if you're following the recipe and the outcome is still good.
The difference between principle and recipe is that the outcome for the specific recipe is the same whether you know the principle or not, but if you made another dish with tomatoes that had a different recipe, and you didn't understand the principle, then that recipe might not turn out as well if you omitted the salt.
I've been thinking quite a lot about this in the context of generative AI lately. There's no shortage of people hawking "TOP 50 POWER AWESOME CHATGPT PROMPTS" on LinkedIn and other places, and I've dug into some of those. They're essentially cookbooks with recipes, and those recipes are generally okay. (I haven't run into any that I was blown away by) And yet people LOVE these sorts of recipe collections.
Why? Because as much as the principles matter, sometimes you just need to get dinner on the table in 30 minutes or less. You don't care about the principle. You care about getting dinner on the table. At the end of the day, you're tired and you don't want to think too hard. You just want some directions to follow that aren't too hard.
And that's the generative AI equivalent of a canned prompt, a prompt you copy, tweak a little with your specifics, and then paste. You follow the instructions, as surely as you do on a box of pre-made cake mix, and you end up with a satisfactory result. Is it going to be the best result possible? No, probably not. Is it going to be good enough? Yes, probably.
Where you run into challenges is when you have something that doesn't fit an existing recipe. That's when principles come in handy. Let's take a look at this prompt situation suggested by my friend and colleague Ashley Faus on LinkedIn:
We have tiers for our product launches, ranging from a Tier 1 launch with all the activities (press, keynote mention, blog post, demo series, announcement email, product tour update, etc.) to Tier 4 (significantly less activities). It seems like there should be a combination of AI + automation that could help a marketer generate a launch plan and all the associated tickets and/or pages required. But... would the prompt be, "I'm doing a Tier 1 launch about [Product Name]. Generate the launch plan and associated tickets for the Creative team, Blog team, and Web team."? Or would the prompt be, "I have a launch coming up that meets these criteria: [Customer Impact], [Company Impact], [Other criteria as needed]. Please choose the relevant launch Tier, and generate a launch plan."? And then maybe a separate prompt to generate the tickets and pages? Like if we have a template for an announcement blog for a Tier 1 launch, would it generate the page with the template, or generate a draft of the launch blog itself, or...? Again, I think this is a mix of internal/external AI capabilities, automation rules, & human collab, but IDK the mix
Ashley is correct. This is something that generative AI can handle, at least partially - but I can guarantee that as of right now, there is no recipe for it.
The first principle we invoke is whether or not it's a task generative AI is even capable of handling. Building a launch plan? Yes. What about creating tickets - Ashley works for the software giant Atlassian, and their Jira ticketing system is well-known. Can a generative AI system talk to Jira? Perhaps not directly - but Jira can ingest spreadsheets like CSV files. Can a generative AI system generate CSV files? Yes it can.
You see what we're doing here, right? This isn't a recipe, but we are laying the foundation to create a recipe. Something that my partner and CEO Katie Robbert talks about ALL the time is user stories, short, punchy descriptions of what you're trying to do that helps build requirements for the project. In this case, a user story - or several - is what you need to create a recipe for generative AI.
Once you know what it is you're trying to do, and you've ascertained whether or not generative AI is capable of doing it, then you can build the recipe - and like any recipe, once you have it written down, you can follow it over and over again.
So, how would we turn Ashley's idea into a recipe? Well, watch this week's video as I step through the process from start to finish.
Recipes are absolutely a good idea, especially if you want to scale the use of generative AI within your company. But many recipes may not exist, or may not be sufficient in their original form to fit your needs. Like the culinary world, there are a lot of cooks but relatively few chefs, so work to identify the chefs in your organization or your network as quickly as you can, then work with them to start building your cookbook.
How Was This Issue?
Rate this week's newsletter issue with a single click. Your feedback over time helps me figure out what content to create for you.
Share With a Friend or Colleague
If you enjoy this newsletter and want to share it with a friend/colleague, please do. Send this URL to your friend/colleague:
For enrolled subscribers on Substack, there are referral rewards if you refer 100, 200, or 300 other readers. Visit the Leaderboard here.
ICYMI: In Case You Missed it
Besides the new Generative AI for Marketers course I'm relentlessly flogging, I recommend the livestream I did this week with John and Katie as we went over Matomo Analytics, the free, open source alternative to Google Analytics.
Skill Up With Classes
These are just a few of the classes I have available over at the Trust Insights website that you can take.
Premium
Free
领英推荐
Get Back to Work
Folks who post jobs in the free Analytics for Marketers Slack community may have those jobs shared here, too. If you're looking for work, check out these recent open positions, and check out the Slack group for the comprehensive list.
What I'm Reading: Your Stuff
Let's look at the most interesting content from around the web on topics you care about, some of which you might have even written.
Social Media Marketing
Media and Content
SEO, Google, and Paid Media
Advertisement: Business Cameos
If you're familiar with the Cameo system - where people hire well-known folks for short video clips - then you'll totally get Thinkers One. Created by my friend Mitch Joel, Thinkers One lets you connect with the biggest thinkers for short videos on topics you care about. I've got a whole slew of Thinkers One Cameo-style topics for video clips you can use at internal company meetings, events, or even just for yourself. Want me to tell your boss that you need to be paying attention to generative AI right now?
Tools, Machine Learning, and AI
Analytics, Stats, and Data Science
All Things IBM
Dealer's Choice : Random Stuff
How to Stay in Touch
Let's make sure we're connected in the places it suits you best. Here's where you can find different content:
Advertisement: Ukraine ???? Humanitarian Fund
The war to free Ukraine continues. If you'd like to support humanitarian efforts in Ukraine, the Ukrainian government has set up a special portal, United24, to help make contributing easy. The effort to free Ukraine from Russia's illegal invasion needs your ongoing support.
Events I'll Be At
Here's where I'm speaking and attending. Say hi if you're at an event also:
Events marked with a physical location may become virtual if conditions and safety warrant it.
If you're an event organizer, let me help your event shine. Visit my speaking page for more details.
Can't be at an event? Stop by my private Slack group instead, Analytics for Marketers.
Required Disclosures
Events with links have purchased sponsorships in this newsletter and as a result, I receive direct financial compensation for promoting them.
Advertisements in this newsletter have paid to be promoted, and as a result, I receive direct financial compensation for promoting them.
My company, Trust Insights, maintains business partnerships with companies including, but not limited to, IBM, Cisco Systems, Amazon, Talkwalker, MarketingProfs, MarketMuse, Agorapulse, Hubspot, Informa, Demandbase, The Marketing AI Institute, and others. While links shared from partners are not explicit endorsements, nor do they directly financially benefit Trust Insights, a commercial relationship exists for which Trust Insights may receive indirect financial benefit, and thus I may receive indirect financial benefit from them as well.
Thank You
Thanks for subscribing and reading this far. I appreciate it. As always, thank you for your support, your attention, and your kindness.
See you next week,
Christopher S. Penn
Embracing creativity in AI lets us cook up success ?? - like Seneca said, our fate is shaped by our thoughts. #Innovation #CreativityIsKey ??
Excited to dive into this newsletter! Customized recipes with generative AI sound like a game-changer for patent lawyers. Can't wait to see how we can leverage these principles to stay ahead in our field. Thanks for sharing!
Connector | Storyteller | Marketing & Communications Strategist | Influencer Marketing | Inclusion Ally | Non-Profit Fundraising | Mentor
1 年FYI Diana Rainesh - take a minute to listen to this one connected to the innovations you're thinking about. I heard some ideas here that might help you - and if this is helpful you should checkout Chris' newsletter too!
Connector | Storyteller | Marketing & Communications Strategist | Influencer Marketing | Inclusion Ally | Non-Profit Fundraising | Mentor
1 年Wow - amazing Christopher Penn and kudos Ashley Faus for the inspiration on this prompt. Lots of great nuggets to study/learn from!
Branding that CONVERTS ? Get a 1-click visual identity for your personal brand
1 年The tiered launch plan is brilliant, Ashley! This one was fun to watch.