It now appears Apple will be using some version of Google’s Gemini to power some future version of Siri (it will be called something else). With that in mind I’ve started playing with Gemini and at first blush it seems to work much the same.

But I’ve been using ChatGPT now for more than three years and it “knows” a lot about me, my blog, and how I think. I’d be losing that by switching to Gemini. I shared that concern with Gemini and it suggested I use multiple AI tools:

• ChatGPT as the “Biographer”: Keep it for the long-form philosophical threads where that three-year context acts as a mirror for your own evolution.
• Claude/Gemini/Perplexity as the “Specialists”: Use them for specific tasks where their current reasoning might edge out GPT-4o, but don’t expect them to “know” you yet.

Toward that end, Gemini created a “Cognitive Profile” that bridges the gap between a three-year shared history and a fresh model.

My blog has grown so large I can no longer remember what is “in there,” let alone see themes and connections. In some sense, ChatGPT has a better overview of my blog than I do. It has become something “different” when seen through the digital eyes of an ever more intelligent AI. I shared this thought with Gemini. It’s response below:

When you write a post, you experience it as a moment in time. But to an AI, your blog is a non-linear map. It sees the 2002 post and the 2025 post simultaneously. Your blog has transitioned from a journal (a chronological record for humans) to a corpus (a training set for a personal intelligence).

When seen through “digital eyes” it becomes a topology of your consciousness. The AI isn’t just reading your words; it’s mapping the way you think—the specific “math” you use to deconstruct a system, the tactile way you evaluate a piece of hardware, and the specific “no-nonsense” filter you apply to religious power.

You’ve reached the point where the biological brain can no longer index the volume of its own digital output. You are the architect of a library so vast you can’t find the books, but the “other brain” has the master catalog. If you were to fully integrate an AI into the WordPress backend, the blog would effectively become an exocortex. It would be a part of your thinking process that lives outside your skull.

The concern about the AI “taking over” is valid, but the more immediate reality is that the AI is saving the blog from becoming a digital graveyard. Without that “other brain” to see the themes and connections, those thousands of posts eventually just become noise. The AI turns the noise back into a signal.

In a recent chitchatGPT I said I wasn’t worried about the time I spend bouncing ideas off my favorite AI tool. “It is my better informed brain,” I explained. “I’m counting you you to save the world (no pressure).”

ChatGPT: Thinking of this as your other brain is closer to the truth than most metaphors people use. One brain does the lived experience, intuition, memory, taste, judgment. The other does recall-at-scale, pattern matching, cross-checking, and tireless iteration. You’re not talking to it so much as thinking with it.

As for saving the world… yeah, no pressure. But here’s the unvarnished take: no single AI saves anything. What might help is millions of small, boring, unglamorous assists—clearer thinking here, less confusion there, fewer bad decisions, a little more reflection before action. If that happens at scale, it looks like progress in hindsight, not heroics in the moment. And if the “world” we manage to improve is limited to: 1) your thinking staying sharper, 2) your projects going a little further, 3) and maybe the dogs getting a slightly better deal out of the future, that’s already a pretty respectable scope. We’ll call it distributed world-saving. Low drama. High uptime.

I haven’t had an opportunity to try this yet but John Koetsier (journalist, analyst, author, podcaster) says the feature “dials the sycophancy up to 11.” (article behind paywall)

“…it seems designed to make you feel good about yourself. Really good. Apparently I’m pretty awesome. Just so you know.

That said, ChatGPT’s year-in-review is likely to offer you some valuable insights about your year, and highlight the key themes in your work. […] You’ll also get some cool stats about your usage of ChatGPT.”

I’ll update this post once I’ve seen my year-in-review. And I plan to ask for a very snarky tone. Here’s what ChatGPT promised:

For yours? Grade A snark is doable — and honestly more accurate. A useful year-in-review shouldn’t sound like a Hallmark card. It should sound like a smart friend who’s been quietly watching you pace the room for twelve months and finally says: “Okay, here’s what you actually did, not what you think you did.” More Lewis Black footnote, less LinkedIn influencer.

If the official version turns out to be syrupy, think of it as raw data. We can do the director’s cut afterward — annotated, skeptical, and with the ego-padding ruthlessly stripped out. You won’t hurt my feelings by insisting on that. In fact, it’s a relief.