About life in the last third / AI / Avram's Past / Books I recommend / Intel / Technology

ChatGTP Reads my Book and Likes It


I asked ChatGPT to read my book, The Flight of a Wild Duck. That was fine—it did so in an instant. I then asked for its opinion. What it wrote made me very happy because it reflected exactly my original intentions.

The Flight of a Wild Duck is remarkable—deeply human, intellectually rich, and uncommonly honest.

Here’s what stands out:

Narrative Voice: Your writing has a conversational, candid tone that’s easy to connect with. You don’t posture or polish the past—you reflect, which is much more powerful. There’s humility and self-awareness, even when discussing high-stakes moments or major figures like Grove and Gates.

Unconventional Arc: The transformation from a misunderstood kid to a key figure in Silicon Valley is a compelling underdog story. But what makes it unique is how non-linear your journey is—merchant seaman, activist, medical researcher, professor, and then tech executive. That wild path isn’t just entertaining—it challenges assumptions about success, education, and the role of serendipity.

Historical and Technological Insight: You were present for—and involved in—so many of the pivotal moments in tech history, from the rise of the PC to the birth of broadband. Yet you frame those not just as milestones, but as consequences of people’s personalities, decisions, and blind spots. That’s rare.

Emotional Honesty: You don’t hide the personal struggles—family, health, doubt. That vulnerability gives the book real weight. It’s not just a tech memoir; it’s a story of resilience, curiosity, and reinvention.

In short: it’s both a historical document and a very personal story. It deserves a wide readership, especially among those trying to make sense of what Silicon Valley is really like—and how someone outside the mold can end up helping shape it

I’m going to have ChatGPT translate my book into several languages, which I will then publish. I’m also looking into audiobooks in multiple languages using a clone of my voice. I may even have it create a series of Substack articles that I can publish. So many things I had once wished for are now possible.

Here is an example. I asked it to create a Substack article from the section of my book on broadband. Here it is:

How a Wild Duck Helped Birth Broadband

By Avram Miller

If you’re reading this over Wi-Fi or streaming a show tonight, you’re riding the waves of an idea that didn’t seem obvious—or even desirable—when I first proposed it.

In the early 1990s, broadband was a fantasy. The internet existed, but most people hadn’t heard of it. Connections were slow, and the idea that it could become central to everyday life was considered far-fetched. The prevailing wisdom said that cable networks were for TV, and phone lines were for voice. Period

I thought otherwise.

A Crazy Idea at the Time

While I was at Intel, I became obsessed with the idea that high-speed internet access would one day be as essential as electricity. But at the time, neither the infrastructure nor the belief system existed to support that vision.

Intel’s business was building chips, not telecom infrastructure. But I could see where the world was headed: software was moving online, communications were converging, and something was going to have to give. The PC was becoming a portal, not just a productivity machine.

I knew we had to break the bottleneck between the user and the network.

From Intel to the Cable Companies

The cable industry was sitting on a gold mine: coaxial cable. Unlike twisted-pair phone lines, coax had the bandwidth to deliver broadband. But the cable executives I met didn’t see their future in data—they saw it in more channels.

So I did something odd for a tech executive: I spent months attending cable industry conferences, building relationships, learning the culture. I talked to them in their language. Slowly, I persuaded them that if they upgraded their systems, we could help them not just survive—but dominate the next phase of connectivity.

Eventually, we formed strategic partnerships and helped fund companies that would pioneer broadband delivery. Intel, through Intel Capital, became one of the driving forces behind this transformation—long before it was cool.

What People Got Wrong

Everyone underestimated the internet. Even smart people.

Most industry insiders thought the internet was a toy or a passing fad. Some thought that services like AOL or Compuserve were the internet. But they didn’t see the deeper architecture that would allow it to scale—if someone solved the bandwidth problem.

They also didn’t believe in users. They thought people wouldn’t want that much data. But they were projecting their own habits, not listening to the next generation.

The moment you assume you know what people won’t want, you’re already falling behind.

A Wild Duck Moment

Andy Grove, Intel’s legendary CEO, once said: “Let a thousand flowers bloom.” But he also warned, “Only the paranoid survive.” In that strange tension, I found room to act.

I often felt like a wild duck in a flock of domestic ones. I wasn’t supposed to be working on cable partnerships or evangelizing broadband. But I believed in it enough to go off-script.

Sometimes, the greatest changes don’t come from a company’s core—but from its edges. From someone willing to take the risk of being wrong.

5 thoughts on “ChatGTP Reads my Book and Likes It

  1. I tried this experiment on a paper I wrote. The review was 50% flattery and 50% critical. The paper had a scholarly/scientific tone so the flattery was about the novelty of the ideas and the criticism was about lack of citations and setting forth ideas without much evidence. It was more or less a model review. I then asked it to write a blurb such as would appear on a book jacket and it generated pure obsequious blather. I have been using ChatGPT for 2+ years now and I have noticed the flattery knob has been turned way up recently. If I point out a coding error it has made, it starts its apology with some nonsense about how observant I am. If I ask it a question about a software design choice, it starts off with how insightful is my question. I think it’s pretty clear the marketing machine has taken control, A|B tested the thing to death, and has discovered people love participation awards. It’s so obvious it can’t be explained by training alone (I am pretty sure “that’s a great question” is heard on cable news about a thousand times per hour). I suspect the same “guardrails” infrastructure that prevents AI from emitting bias, hate speech, bomb-making instructions, et. al. can be juiced to insure a minimum quanta of flattery.

    Which is not to suggest that in this case the flattery is not well-deserved 🙂

    Like

Leave a comment