A tale of four chat bots

I want to move my home on the web, from ghost to something I design and build myself.

I mentioned at the end of the last post that I was excited. That this would be a great experiment. I would build this with ChatGPT by my side.

Since then, I’ve gone on a journey. I talked to ChatGPT, Claude, Copilot and Gemini about it. I fed all of them the same prompt. Copilot fared the worst. It was so bad, in fact, that I removed it from my phone.

I loved Claude’s response, but it hit some token limit while replying. But whatever came through, seemed plausible enough. It was detailed enough.

I tried ChatGPT next, but with it too, the advanced models are on the Pro tier.

And as I said earlier, I liked Claude’s response better. I considered pain for Claude Pro or ChatGPT pro. I came very very close. But I don’t have use for these agents on a day to day basis. All I have is this website redesign. And if it goes as planned, I would not have to do anything else.

All through this I hadn’t even considered Gemini. My impression of it was that it was always a step back. But then I read Google Is Winning on Every AI Front, and thought why not give it a try?

Today, two and a half years after the ChatGPT debacle, Google DeepMind is winning. They are winning so hard right now that they’re screaming, “Please, please, we can’t take it anymore, it’s too much winning!” No, but really—I wonder if the only reason OpenAI, Anthropic, Meta, and Co. ever had the slightest chance to win is because Google fumbled that one time. They don’t anymore.

I was surprised. The app is good. I fed it the same prompt and its response was good. I have not yet started work on this yet. But the vibe was good.

There will be more to follow on this.