We’ve all taken the intro to AI session or workshop. It didn’t do much, and so we went back to work. In the meantime, these AI things kept changing, evolving and spreading throughout our professional lives. At some point you may think to yourself, “yeah, I took the AI training, but honestly, I’m still just scratching the surface, and AI isn’t going away. I need to really start using this thing.”
Instead of being an AI dabbler, start teaching your AI to do work! In other words, your job is to upskill your AI.
This will provoke some very real fears such as, “I don’t want to tell the AI how to do my job because then I’ll be replaced.” Or, “I don’t want AI to do the work I like doing.” This makes sense, but look closely at the work you like doing: there are almost certainly parts of that work that you don’t really like doing. AI will be doing some parts of your job in the future, but there will be many new parts that will fill up any time savings you get from AI.
Once we’ve come to terms with all this, then you need to face up to the fact that to make AI useful, you have to invest the mental energy, and time, to teach the thing about the outputs it’s supposed to be producing. We also need to get all the background knowledge and content our brains rely on to do the work we are now offloading into our AI’s brain.
Three ways I’ve learned to “teach” my AI
(a) I ask it to do something, like produce a PowerPoint from a Word document and use the same look and feel as a previous PowerPoint.
Some might think, “My head hurts trying to really fully explain the task I need done to an AI, it’s easier just to do it myself.”
That’s true, but when you do the math you’ll usually find the ROI from the time invested in teaching the AI to do a task that you now do manually even just three or four times a year is well worth it.
To help me overcome the “my head hurts explaining stuff to the AI”, I’ve developed the skill of writing stream of consciousness prompts. I just let it all out of my mind in whatever way it wants to come out. My fingers are like stenographers, transcribing my stream of thoughts into text in real time. This gives the AI lots of information to help it do whatever it is I need it to do.
Then I go carefully through the output it generates, and meticulously call out and explain every mistake. This is the work.
Through trial and error I’ve learnt that AI learns best when I call out and explain each mistake it makes without telling it what to do to correct the mistake. Giving it the correct answer seems to stifle its learning, though sometimes I have to tell it exactly what to do otherwise it just doesn’t get done.
For example, when developing my AI pipeline to generate PowerPoint presentations, it’s better to say “the paragraph on slide five of the presentation you generated is too close to the image and to me it makes slide five look all scrunched together,” which helps the AI to learn, rather than saying, “move the paragraph on slide five further away from the image,” which provides little the AI can learn from.
(b) I share with my AI an example of a perfect output for some input and tell it to learn from that example (e.g. a PowerPoint presentation that I created, and thought was really good, from a Word document describing some new initiative). I instruct my AI to learn by example and do whatever it needs to do so that in the future, when asked to do a similar task, it will apply what it learned from the example.
(c) I spend a lot of time up front when I start a new project getting as much nuanced background knowledge and information into my AI as I can. The more my AI knows the tacit knowledge, impressions, plans, and ideas that I have in my mind, the better it can assist me at work. This is the first, and critical, step I do with clients during our first session: I help them share all the tacit knowledge their AI needs to be useful for them.
Something to try
As a first step, log in to your AI and write something like this (or copy and paste this into your AI):
I read an article, and the author said if I tell you when I think you did something wrong, like edit out an important part of some document I’ve asked you to help me edit, and I take the time to properly explain why I think it is wrong, then you will learn. He also said that if I keep investing the time to point out the errors you make, then you will make fewer and fewer errors and so become more and more helpful to me. Is that correct? Is there anything I should do, or any settings that should be set so you can build out a knowledge base of what I teach you? Can you check if you are set up and configured properly so you build a memory of all the things I teach you? I really don’t want to waste my time showing you things and then have you forget them!
Jump-start your use of AI with one-to-one Coaching on AI.
Good luck with your AI journey.
Phil.