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.

I haven’t played much with ChatGPT’s content creation tools. Have found the “conversations” more interesting. Decided to give the “Create your holiday video” a go with no prompting. Just picked a photo and it came up with the blog-to-book idea.