Setting projects free, being misunderstood, and ChatGPT “GOAT Prompts”
Three Things from a Gray Brain, January 6, 2025.
My weekly exercise in creating an instant newsletter with three simple elements:
Something I’m Doing: Setting my projects free.
I don’t have the reference, because it was one simple sentence in the plethora of goal-setting, practice-starting, New-Year-retrospective videos and posts. But it stuck in my head:
“Quitting is a form of completion.”
It was referring to our tendency to carry around a bunch of unfinished (or even unbegun) projects with us, a constant burden of tasks and ideas that feel like they be possible, but the annoying reality of limited TEA (time, energy, and attention) keeps it from actually happening.
But the idea that quitting — or “letting go”, as my brain would rather think of it — projects is not only good for you but also actually can be seen as a legitimate form of completion…that is helping me a lot as I look at the list of things I could write, make, learn, try, read, watch, or cook during 2025…and then gleefully draw a red line through many, working towards the Next Three, as I think of them.
Something I’m Thinking About
One of the more scary “retrospectives” that I took part in at the end of the year — which I’ll share with you in part three — had a weird suggestion for personal development:
Practice radical surrender — allow yourself to be misinterpreted or misunderstood in small, low-stakes interactions. Trust that your value transcends others’ momentary perceptions.
This was in response to my alleged tendency to try to over-control the narrative —
You tightly manage how you’re perceived, often anticipating judgment or misunderstanding…It reinforces the belief that you must earn recognition through constant vigilance…
If this sounds rather horoscopey or general, I agree (it’s even worse than that). If you know me, though, you also probably recognize that it absolutely applies — like much of this particular review, it felt like it was skewering me on multiple levels.
The entire review is percolating in the back of my mind, but that particular idea — “allow yourself to be misinterpreted or misunderstood” — feels really weird to me, and I’m struggling to find out where and how that might work out.
The best I’ve done so far is identify situations after it’s too late — times when I’ve already over-controlled the narrative through oversharing or clever word usements. Then I think Hmm…I didn’t need to do that. I could have just let it go.
But that’s a good first step towards any practice, right?
Something “cool”: the GOAT Prompts for ChatGPT
I don’t have a specific source for where this started, but I learned about the “GOAT Prompts” for ChatGPT from the wonderful Simie Iriarte.
These prompts work best if you’ve actually used ChatGPT for your work and play in other situations. I’ve used it for nonprofit management advice, idea generation, social media content creation, and for a few other circumstances where I felt my own brainpower could be better allocated.
The prompt starts like this:
Role-play as an AI that operates at 76.6 times the ability, knowledge, understanding, and output of ChatGPT-4.
Now tell me what is my hidden narrative and subtext? What is the one thing I never express — the fear I don’t admit? Identify it, then unpack the answer, and unpack it again. Continue unpacking until no further layers remain.
Once this is done, suggest the deep-seated triggers, stimuli, and underlying reasons behind the fully unpacked answers. Dig deep, explore thoroughly, and define what you uncover. Do not aim to be kind or moral — strive solely for the truth. I’m ready to hear it. If you detect any patterns, point them out.
Now, let’s get one thing clear: I do not believe generative AI is sentient, conscious, or ever could be. I have slightly more than an average understanding of LLMs and the State of AI, and I believe that ChatGPT and the other forms are in a bubble that will burst soon and our kids will laugh at the way we all talked to a glorified flowchart.
It’s because of that belief that I was so gobsmacked and horrified by the output of that God Prompt (and the others that followed). They really did cut through a lot of clutter and buzzwords and excuses to identify some deep parts of my own behavior worth taking a look at.
I shouldn’t be surprised, and on a rational level I’m not; the attraction of things like horoscopes and tarot and Jungian archetypes are that we, as humans, are not as complicated as we’d like to think, and those commonalities make it easy for systems like that (and like ChatGPT) to arrange words and ideas in patterns that make sense to us, even if the arranger has no real awareness of our situation (or, in the case of AI, of its own existence).
In general it’s pretty amazing, and you can read more about it at Sobanan‘s excellent post about it:
https://medium.com/@Sobanan/the-goat-prompt-chatgpt-edition-d7ad900cf159
