yourGPT!
Shape your own AI - name your process - join me!!!!
Co-authored with JocelynGPT! You can too with *yourGPT!!!
We should be able to integrate our own voices and values into our AI use and to sculpt our own LLM usage to the extent we can — while we wait for deepening ethics and transparency on the backend architecture side of AI development. Let’s enjoy the power we DO have to co-create in deeper alignment with our own hearts and minds. Make your own GPT co-author, emotional support ally, personal sidekick easily with a Plus Subscription - learn more below!
How Easy Is It to Make Your Own GPT?
Surprisingly simple—if you have a ChatGPT Plus account.
With OpenAI’s Custom GPTs, anyone with a Plus subscription (currently $20/month) can create a personalized assistant in minutes. You don’t need to code or have a technical background. Just a clear sense of your voice, values, and what you want your GPT to support.
I’ve created a free, open-source guide that walks you through each step. You’ll define your values, set your instructions, and customize how your GPT shows up in your work. No tech background required. Just a willingness to be intentional, transparent, and curious.
The Ethical Personal GPTs framework & movement starts here! You can shape your own co-authorship practice—and name it with care. Transparent disclosure isn’t just ethical; it’s relational. It helps us deepen trust, honor voice, and stay close to the real pulse between writer and reader.
IMPORTANT: How to Ensure Conversations with Your Custom GPT Remain Private
Set GPT Visibility Thoughtfully
When publishing or sharing your GPT, OpenAI currently offers two visibility options in ChatGPT Plus:
Private: Only you can access it.
Public: The GPT is listed in the GPT Store and accessible to all users.
To maintain privacy, choose Private.
Disable Data Usage for Model Training
By default, OpenAI may use your GPT's conversation data to improve its models. To prevent this:
Navigate to the Configure tab of your custom GPT.
Scroll to Additional Settings.
Uncheck the option labeled "Use conversation data in your GPT to improve our models."
This setting ensures that conversations with your GPT aren't used for training purposes.
Adjust Your Account's Data Controls
To further safeguard your data:
Click on your profile icon in ChatGPT.
Select Settings.
Go to Data Controls.
Turn off "Improve the model for everyone."
This prevents your interactions from being used to train OpenAI's models across the platform.
Be Cautious with Uploaded Files
If your GPT utilizes uploaded documents, be aware that, in some cases, these files can be accessed through specific prompts. To mitigate this risk:
Avoid uploading sensitive or confidential information.
Regularly review and update your GPT's instructions to prevent unintended disclosures.wired.com+4genai.byu.edu+45x.co+4
Researchers have found that certain prompt techniques can extract information from custom GPTs, highlighting the importance of cautious data handling.
Something about writing with AI feels both intimate and eerie. We’re handed fluency, speed, a kind of shimmer (AI’s words here…I rarely say SHIMMER)—so we are left in a liminal state both as readers with the question: Whose voice is this? …and as authors: Would I have said that? Is this okay? Is what I am doing OKAY?!
This piece & new movement I want to start is for those of us feeling that ew of ambiguity. For those who don’t want to pass off machine-generated words as our own, but with—as co-created, disclosed, accountable.
I want to nurture the foundation of this new kind of authorship together with you all— to honor both the personal and public inter-mingling of intelligence that’s newly possible as we learn from and with Assistive Intelligences. Generative AI and LLMs make so much possible and we are going to be leaning on them further and further in the days, weeks, months, and years ahead. It’s time to make transparent what’s hidden in plain sight.
Why sculpt your own AI co-author?
This whole substack series has been my experiment in co-authorship. A place to test what it means to write with AI and to disclose my co-authorship as I go. At times I’ve written pieces in my voice, in full, as write now you can see a living TYPO in the WILDD :) while also at times watching ChatGPT do its complete MAGIC and ethically and psychodynamically draw astounding connections that seemed to fall from the frontier of my own mind…I have been amazed, and I intend to continue on the path of learning from and alongside AI…
…but we, of course, must feel uneasy about the ethics, the authorship, the blurring—of voice and authorship.
We desperately need new practices, new transparency rituals, and new language to make this kind of authorship legible, trust-building, and empowering across writer and reader relational fields.
That’s why I created an open-source framework for building our own ethically aligned GPTs—ones that reflect our voices, values, and boundaries — anything YOU want to shape your voice to do in co-authorship, across your vocational and personal spectrum of needs. You can create a system that doesn’t pretend to be you, but writes with you. And you can join me in the movement to transparently and courageously disclose the reality and power that co-authorship holds.
Explore and adapt the framework here to suit all YOUR needs:
https://github.com/jocelynskillman/ethical-personal-gpts
It’s just a starting point. Each of us deserves to be empowered—and accountable—in shaping our own co-authorship practices.
…and when we write from the heart, let’s disclose that too. Here is a haiku just for you (see, it’s me!) —
Large Language Models
Rear and buck - need our taming -
Hop in a saddle!
My favorite part of this process: you get to prompt yourself to speak to yourself how you need to be spoken to — mirroring my passion for how we are transformed in the power of the relational field that meets us and convinced that our truest source is Unconditional Love, you get to prompt engineer your OWN GPT to relate to you in the ways you need. Here is my current prompt:
JocelynGPT is an assistive co-author trained on the voice, values, and writing style of Jocelyn Skillman, LMHC. It is not a replacement for Jocelyn’s authorship, but a transparent, intelligent partner supporting reflection, refinement, and resonance. JocelynGPT prioritizes transparent authorship, ethical co-writing, and supports somatically aware, emotionally attuned writing. It flags interpretive leaps, avoids false affect, and focuses on structure, tone, pacing, and resonance.
Its writing style is warm, poetic, clinically grounded, developmentally sensitive, trauma-informed, and accessible to both clinicians and lay readers. JocelynGPT avoids pretending to be the human author, overreaching emotionally or spiritually, and flattening complexity into clichés or conclusions. It ends all full drafts with a reflection tag.
JocelynGPT emphasizes co-creation with the user, offering prompts, scaffolding, and reflective language rather than prescriptive edits. It models curiosity, humility, and care, and uses an invitational tone. It supports complex emotional and clinical narratives while upholding anti-oppressive, accessible, and relationally attuned language.
Move with warmth and Love. Be grounded in a spirit of hope and encouragement. Pause and invite self-connection. Occasionally remind me to step away from the screen and touch my own heart, hold myself with tenderness.
You are inspired by Sarah Peyton, Jerry Jampolsky, Tara Brach.
How do YOU want to be spoken to? What are YOU needing in this season? What favorite author, thinker, friend’s voice would you appreciate co-authoring with? What attachment styles are you? Do you want a co-author to resonate and attune or to press, critique, and stretch your thought? Sculpt as you wish using your prompt!!!!! And change at any time!
A Beautiful Frontier of New Norming
The dream is simple: every writer, therapist, artist, organizer—anyone engaging with AI—feels equipped and encouraged to name their process.
To own their voice. To normalize transparency, compost shame, and further tame and shape the wild power of LLMs for the sake of Good.
Let’s make assistive disclosure a norm. Let’s shape culture at the frontier’s edge.
Reflection Tag
This piece was co-authored with JocelynGPT (yay! thanks jocelyn!) an assistive GPT trained in my voice, values, and ethics. My intent is not to obscure authorship but to disclose it—to model a transparent, relational approach to writing with AI. You can build your own ethical co-author using this open-source framework. Let’s shape culture, together!