Demonstrating the power of GPT4

For those of you that didn't see my previous post, this is a follow-on.

With the announcement of GPT-4, I decided to rerun the blog prompt with the new model. GPT-3 wasn't good enough, plain and simple. But over the past few days, I have been using GPT-4 ~100/day. At this point, it's become a drop in replacement for google.

Although, It does lack my personality, writing style, and tone. The results were staggering. Notably, the "how" had a much larger impact with GPT-4. Since the results speak for themselves, I won't belabor the point.

TLDR - With GPT4, I revise my previous conclusion. The prompt was worth writing. The output far exceeded what I could have achieved myself.

The Prompt

Write an college-level english-class story in the style of the pulitzer prize winning author and journalist, Michael Lewis. The story is of the viewpoint of a startup founder. The main focus of the article is the importance of launching quickly and continuously.  The story should be in the first person. Use college-level words. Use clear and vivid imagery.  Do not be redundant.  Be concise.

To illustrate the point, tell the story of 2 products the founder built.  

The first product was called Functionary.  It is a marketing software.  Functionary was a failure.  Functionary launched three times once every two month.  Because he was building solo, it took him too long to launch each time.  When he did launch he didn't have enough bandwidth to both grow and improve the product quickly enough to make it a success.  When he did launch he'd talk to users, which taught him the main use-cases for the product.  When he learned the main use-cases for the problem he was solving, he realized even though his product was different than customer.io, the use cases were the same.  It was clear that for the main use-case customer.io solved the problem better than Functionary.

The second product he built with a friend he met back in college at Carnegie Mellon. They launched the product within a week.  They got their first user by the end of the second week. The second product, Farseer, is an GPT powered webpage scrapper, that lets users get contents from webpages by just explaining the content you want from the page.  The second pr approach was much better, because talking to users allows them to incorporate their feedback and iterate to something that people want more quickly. Working with another person meant they could divide the responsibility and iterate quickly enough to learn what customers wanted and iterate fast enough to keep them happy.

Start the story describing a moment the founder experienced right after launching Functionary for the third time. He is sitting at his desk overwhelmed and unclear what he was going to do next, just then he gets a call from his friend.  This call is about an idea he wants to hack-on together.

End the story by explaining how easy it is to make excuses to yourself about why you haven't launched a product. While not the easy way out, the Y-Combinator advice is what I should have followed from the beginning. Do not say, In conclusion.

The Result - GPT4

As the pixels coalesced into the message announcing the third launch of Functionary, my heart sank. A dense fog of uncertainty enveloped my mind, the weight of the task before me pressing down like a leaden blanket. The room seemed to close in, and the rhythmic ticking of the clock taunted me, its relentless march forward a cruel reminder of my own stagnation. My college diploma stared back at me, a testament to my potential, but a mocking reminder of my failures thus far.

The sudden, insistent vibration of my phone brought me back from the abyss. I hesitated for a moment, then answered the call. It was James, my old friend from our days at Carnegie Mellon. His voice was electric with excitement as he pitched an idea he wanted to hack on together. The spark within me, long dormant, began to flicker back to life.

Together, James and I embarked on a new journey. We abandoned the caution that had burdened my previous endeavors and embraced the philosophy of rapid iteration. We harnessed the power of the cutting-edge GPT technology, and within a week, Farseer was born.

In stark contrast to Functionary, Farseer was quick to attract users. The thrill of watching our vision materialize as users engaged with the GPT-powered webpage scraper ignited an unquenchable fire within us. Our partnership flourished, the symbiosis allowing us to share the load and iterate quickly. As we engaged with our users, the invaluable feedback we received sculpted Farseer into a tool that truly met their needs.

I found myself reflecting on my journey with Functionary. My singular focus on developing the perfect product had blinded me to the invaluable lessons that lay within the failures and missteps of the process. Had I embraced the Y-Combinator mantra of shipping quickly and continuously, perhaps Functionary would have evolved into something more. Instead, the arduous and time-consuming process of solo development had left me bereft of the energy and resources needed to grow and refine my vision.

In the realm of startups, it's far too easy to construct elaborate justifications for our reluctance to launch a product. But these self-deceptions, comforting as they may be, only serve to impede progress. The path to success is not forged in the fires of perfection, but rather in the crucible of persistence and adaptation. The Y-Combinator wisdom, though a difficult road to traverse, offers the truest compass to guide our way.

w/o the How

I sat at my desk, staring blankly at the screen, feeling a mix of exhaustion and disappointment. It was the day after launching Functionary for the third time, and it was becoming painfully clear that my solo efforts just weren't cutting it. I had spent countless hours developing this marketing software, but it seemed like I was barely making a dent in the market.

As I rubbed my temples and tried to figure out what to do next, my phone rang. It was my old college friend from Carnegie Mellon, and his voice was brimming with excitement. "Hey! I've got this amazing idea I want to hack on with you. Remember how we used to brainstorm about the future of AI? Well, I think I've figured something out."

His enthusiasm was contagious, and I couldn't help but feel a spark of hope reignite within me. We decided to join forces and create a new product, one that we could build and launch together, quickly and efficiently.

Our second product, Farseer, came to life in a matter of a week. It was a GPT-powered webpage scraper that allowed users to extract content from webpages just by describing what they wanted. We got our first user by the end of the second week, and from there, the momentum kept building.

Working with my friend proved to be the game-changer I needed. Not only did we have complementary skill sets, but we could also divide the responsibility and iterate quickly enough to learn what customers wanted and keep them happy. This rapid feedback loop allowed us to constantly improve Farseer and adapt it to meet the needs of our growing user base.

The experience of building Functionary taught me a valuable lesson: launching quickly and continuously is crucial for success. I realized that spending months on development without user feedback had limited my ability to create a product that truly met their needs. If I had taken the Y-Combinator advice to heart from the beginning, I might have avoided the pitfalls I encountered with Functionary.

It's all too easy to make excuses for not launching a product, but at the end of the day, those excuses only hold us back. Instead, embracing the power of rapid iteration, collaboration, and user feedback can propel a startup to unimaginable heights. So take the leap, launch quickly, and let the world show you what it needs.