Dear Reader, today we're about to embark on an exploration of how artificial intelligence (AI) and voice capture can revolutionize the way we communicate. Interestingly, the method I am using to generate this very wiki article is the same system I'll be introducing to you. So, let's dive right in.
Identifying the Communication Problem
We've been conditioned to believe that our primary modes of replication in communication are handwritten or typed messages. We're so accustomed to this that we often don't realize that it's a problem. However, these methods are inherently slow and painstaking. Typing is quicker than writing by hand, but it's still not ideal. For instance, consider Elon Musk's ambitious vision for Neuralink - a technology that could potentially connect our brains directly to devices, eliminating the need for manual typing entirely.
While not all of us may want or need a neural implant, the desire to communicate our thoughts and ideas more efficiently remains universal. This is where AI and voice capture come into play.
The AI and Voice Capture Solution
The simple and non-invasive solution is using your voice, captured and transcribed by AI, then formatted by a sophisticated language model like GPT-4 to ensure it sounds as natural and effective as possible.
Communication breakdowns, often due to undercommunication, can be a source of many problems, whether personal or professional. The advantage of AI and voice capture is that it allows for expansive sharing of context without the worry of overcommunication. GPT-4 can condense your thoughts and provide a concise summary or TL;DR (Too Long; Didn't Read) without you having to do the summarizing yourself.
At an affordable monthly fee (around $30 as of my writing), this AI-powered transcription service is an impressive productivity booster.
Practical Application: From Voice to Written Word
The process is quite straightforward. When I have something to communicate - say, a blog post, an email, or a document for my team - I start by dictating my thoughts into Descript, a leading AI transcription platform. For a typical blog post, I might speak for 7 to 10 minutes.
Afterward, I transfer the transcription into a Google Doc or Notion doc, spending about 10 minutes cleaning up any transcription errors. Then, I pass the corrected transcript into ChatGPT, accompanied by a couple of directive sentences, like…
"Given this input data, create a blog post that argues why going slow is essential in the time of information overwhelm:"
This provides the AI with context and intent, guiding it in shaping the output.
More examples of prompts:
"Given this input data, create a wiki article that explains how to version yourself:"
"Given this input data, write a note to the Descript team explaining a feature request:"
"Given this input data, write an email to my parents explaining my upcoming travel plans:"
The Impact
The improvements I've experienced through this method are significant. Not only do I feel better understood, but my productivity in communication has skyrocketed. As my fingers are freed from the constraints of typing, my brain can focus on generating thoughts without associating communication with the labor of typing. Consequently, I enter a flow state more frequently, with fewer obstacles between my thoughts and their externalization.
Furthermore, I create reusable knowledge artifacts - robust, well-articulated pieces of information that I can refer back to whenever necessary. This would have been a much more daunting task if it required manually typing everything out.
This wiki article, created using the method described above, is a prime example. I started by dictating my thoughts into Descript, then cleaned up the transcript, and finally fed it into ChatGPT to generate this comprehensive piece. Thus, using AI and voice capture tools, we can communicate exactly what we want, at a pace that was previously unimaginable. This potent combination is shaping the future of communication and it's here for us to embrace.
Further reading: If you’re a blogger, read The AI-Assisted Art of Blogging: Gary Sheng's Efficient Workflow Explained