Ruben Hassid · 12 min read · Gen AI Tools
I can be you.
Read the original on ruben.substack.com →
The piece argues that a person’s voice, taste, and writing can be distilled into a single text file and uploaded into AI models to imitate them. It outlines a two-hour workflow using Claude, Wispr Flow, and related tools to extract a writer's DNA and have AI produce first drafts that sound like them. It also highlights the tension between digital replication and authenticity in writing today.
Key Takeaways
- A single text file can capture a writer’s voice and enable AI models to imitate that voice across platforms.
- A 2-hour extraction workflow using Claude, Cowork, Opus 4.7, Extended thinking, and Wispr Flow facilitates rapid voice transfer from human to AI.
- A structured 100-question interview framework (covering Beliefs, Writing Mechanics, Aesthetic Crimes, Voice & Personality) is proposed to surface deep writing patterns.
- Generated drafts can be produced quickly, offering a way to maintain a consistent voice, while raising questions about authenticity and authorship in AI-assisted writing.
Excerpt
You’re just a text file. I give a few lines of instructions to Claude, and I am like you . You think you’re too complex to fit in a text file. But you’re not. I just need to capture your voice. Your taste. The cringe posts that make your computer. The phrase your oldest friend imitates when doing an impression of you. The 2 words you type and always delete. The analogy you’ve written 3 times this year without noticing. Patterns. Every one of them is a pattern. And all of it fits in a text file you upload into…