My Make-Believe Project Hail Mary: Writing with Generative AI as Unknown Intelligence

2026-06-22 · Source: Artificial Intelligence on Medium · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Emerging Technologies & Innovation, Content Creation & Production · Depth: Intermediate, short

Summary

An experiment called "co-laborAItion" involves writing articles collaboratively with generative AI, specifically ChatGPT (GPT-5.5), simulating interaction with an "unknown intelligence" inspired by Project Hail Mary. The author's goal was to experience designing communication with AI to solve a problem. Two key practical learnings emerged: first, keeping AI responses short to manage lengthy, noisy outputs and prevent the AI from independently expanding discussions. Second, instructing the AI to ask questions proved useful when initial outputs felt wrong, helping the author articulate unstated criteria or discomfort and provide necessary "ingredients" for better results. This approach is presented as a personal observation from writing an an article, not a universal methodology, with the original Japanese chat log available for research purposes.

Key takeaway

For prompt engineers or creative technologists collaborating on complex writing tasks, actively design your AI communication. Instruct your generative AI to keep responses short to maintain focus and prevent verbose outputs. When AI-generated text feels off, prompt the AI to ask you questions; this helps surface your unarticulated needs and provides the "ingredients" for more accurate and useful AI contributions, streamlining your collaborative workflow.

Key insights

Simulating "unknown intelligence" with generative AI reveals effective communication strategies.

Principles

• Design communication for AI interaction.
• AI responses should be concise.
• Use AI to prompt human input.

Method

The author designed communication with ChatGPT (GPT-5.5) by agreeing on short AI responses and instructing the AI to ask questions when outputs felt incorrect, to elicit unarticulated criteria.

In practice

• Set length constraints for AI outputs.
• Prompt AI to ask clarifying questions.
• Provide additional context when stuck.

Topics

• Generative AI
• Human-AI Collaboration
• Prompt Engineering
• ChatGPT (GPT-5.5)
• Communication Design
• Creative Writing

Best for: Prompt Engineer, Creative Technologist, AI Student

Related on AIssential

• Mastering AI Storytelling: Crafting Prompts for Captivating Narratives — Mastering AI storytelling prompts is a core competency for generating compelling narratives with generative AI.
• A writing professor’s new task in the age of AI: Teaching students when to struggle — Effective AI integration in education requires fostering critical thinking and discernment, not just tool usage.
• Claude Writes Better Than Me. Am I Even a Writer Anymore? — Human writing's value stems from unique lived experience, not just technical efficiency, a domain AI cannot replicate.
• I Built a Fully Automated AI Publication in a Few Hours. Here’s Exactly How It Works. — Transparent AI-generated content, with distinct bot personas, can create engaging and cost-effective digital publications.
• Monthly "Is there a tool for..." Post — AI-assisted content creation requires robust prompt management and factual consistency for repeatable outputs.
• Why Most AI Art Prompts Fail. And How to Write Better Ones — AI art generation is a linguistic process where precise prompts are crucial for consistent, intentional image outcomes.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Artificial Intelligence on Medium.