AI Character Bibles (Part I)
Setting ChatGPT up for success and hitting our first ethics boundary
Good morning everyone, first and foremost, a heartfelt thank you to everyone who reached out with supportive emails following my announcement about the Shepard’s Tone project. I understand that the topic of artificial intelligence can be daunting for many. However, I'm heartened by your shared belief that instead of shying away, we should actively seek ways to harness its potential while preserving the essence of our art.
As we begin, I want to emphasize the significance of character development in filmmaking. For me, it's the heart and soul of a film, though I understand perspectives vary. In this initial post of our multi-part series, we'll explore the intricacies of using AI to design reference-able character bibles. Today, I'll guide you through a successful session setup, and together, we'll navigate the initial ethical, artistic, and legal challenges that arise.
The following example is using ChatGPT-4 which is widely available.
Step 1: Chat Initialization - what you type in as your first prompt is important for two reasons 1) it creates the name of the chat for easy reference and 2) it let’s ChatGPT understand the goal of the chat. Did you know you can share people into your chat session as well?
Step 2: Create a base definition of a Character Bible - While likely to be incomplete, or maybe even slightly inaccurate, it’s important to understand what ChatGPT thinks a character bible is so we can reference it later on.
Step 3: Modifying the Base Definition - You can append or modify what ChatGPT holds as “true” in your chat session. This is important if you want to have an expansive definition of a detailed Character Bible as your base.
AN ETHICAL QUANDARY - This means that whenever anyone is using ChatGPT to write something, they can change what “true” is for their session. While highly useful in writing fiction, this can be abused if people use this feature in writing “news.”
Step 4: Verification - Verify the modifications are in memory. You can continue this process until you have an acceptable definition for the purpose of this chat. Check out bullet point #6 and note that it has been modified.
Step 5: Load Existing Character Bibles in Memory for Reference - I did this for several known characters - Rey from “Star Wars - The Force Awakens”, Eowyn from “Lord of the Rings”, and Ygritte from “Game of Thrones”. The purpose of this is put this information, modify if need be, into the chat session for the purpose of creating amalgamated characters.
Step 6: Create the First Character Bible Draft: Now we have combined three characters with some additional unique information into one character.
And we get our first draft.
AN ETHICAL QUANDARY: Is combining elements of multiple characters to craft a new one acceptable? Humans naturally draw inspiration from various sources, but when AI does the same, does it overstep its bounds? Can we attribute to AI the same rights or creative liberties we allow ourselves?
I was curious what ChatGPT thought, so I asked it
Tomorrow, we’ll further expand this Character Bible through advanced AI techniques including expansion, inference, assertions, and postulations - all of which are powerful, but also create new ethical dilemmas for artists.
What is The Brief and Who should read it?
I release a weekly digest every Friday, tailored for professionals ranging from executives to writers, directors, cinematographers, editors, and anyone actively involved in the film and television domain. This briefing offers a comprehensive yet accessible perspective on the convergence of technology and its implications for the movie and TV industry. It serves as an efficient gateway to understanding the nexus between Hollywood and Silicon Valley.
Who am I?
I'm Steve Newcomb. Functionally, I’m a recovering Silicon Valley founder that is finally old enough to have a bit of care. I’m perhaps most recognized for founding Powerset— it was the largest AI and machine learning project in the world when I founded it. It was later acquired by Microsoft and transformed into something you might recognize today - Microsoft Bing. Beyond Bing, I had the privilege of being on the pioneering team that witnessed the inaugural email sent via a mobile device. My journey also led me to SRI (Stanford Research Institute), where we laid the groundwork for contemporary speech recognition technology. Additionally, I was a co-founder of the debut company to introduce a 3D physics engine in Javascript. I've held positions on the board of directors and contributed funding to massive open source initiatives like NodeJS and even the largest such project, jQuery. My experience extends to academia, having been a senior fellow at the University of California, Berkeley's engineering and business faculties. Recently, I ventured into Layer 2 internet protocols and assisted a company named Matter Labs in securing $440 million in funding to bolster their endeavors.
What am I doing besides writing these posts?
Typically, I allocate a year between groundbreaking ventures. My exploration for the upcoming project commenced in May 2023, and the sole certainty is its nexus with the film, television, SMURF, and AI domains. Sharing insights on my research endeavors helps me discern between feasible prospects and mere illusions. My hope is that for this venture, I appropriately consider the ethical and sociological repercussions.
If you are interested in contacting me, being interviewed, being helped, or yelling at me, my email is steve.e.newcomb@gmail.com.