AI

From Sceptic to Subscriber: Beginning of My AI Story

by

I can’t believe I’m only now really starting to talk about some AI stuff, and ChatGPT launched in November 2022.

Looking back, I really didn’t do very much with it for over a year. The first six months was kind of like, okay, that’s cool, fine. I did a lot of reading about it separately, but I really didn’t do a heck of a lot until February 2024.

So over a year later, things were mature enough that I decided to take the plunge and try one of the paid services. Through the summer of 2023 I was definitely doing things here and there, but I was sceptical on what it could do. I was sceptical on its privacy. Well, I’m still sceptical on its privacy. But I didn’t pay for anything, and I was what you’d consider a light, casual user.

February 2024, I upgraded to Copilot. I also upgraded the family to the Microsoft 365 family plan at the same time, which you kind of need for Copilot Pro, or don’t, I forget. But there was a reason I did both at the same time. I treated it like a trial. Paid for it, but gave myself 30 days to see if I’d actually use it.

And I liked it. But the main reason I’d gone with Copilot was for the Microsoft Office integrations. That’s what sold me on it for personal use. In practice though, they just didn’t meet expectations at the time. And once I started talking to friends about it, the logic became pretty clear. Copilot is powered by ChatGPT anyway, and ChatGPT at the time had more plugins and a lot more flexibility. So why was I paying for the middleman?

I only used Copilot for about a month before switching to ChatGPT in March 2024.

I started using that on and off. In the beginning I’m not sure I really got my money’s worth, but it was worthwhile to have something and actually use it. I was able to use it for things like tutoring the kids — there’s literally a way to set it up so it won’t just give them the answer, it walks them through the problem. Stuff like that. A whole bunch of different use cases.

But what became apparent straight away was that there were things I was very hesitant to do with it, because it was, and still is, unclear what they actually do with your data.

For context I ran this story through an AI image generator to get a banner for this entry and after 3 tries it came up with what I used.

Building My Own Custom GPTs

by

With some downtime on the bank holiday Monday, I finally tackled something I’ve been wanting to do for a while: creating several custom LLMs. I’ve been tinkering with agents for work and figured it was time to apply similar customizations for personal use.

Lately I’ve been bouncing between ChatGPT, Perplexity, Venice.ai, and even the new Proton AI for privacy. ChatGPT now lets you build custom GPTs, so I gave it a try. While we were on holiday, I had jotted down some customization requirements for a handful of GPTs I wanted, and this felt like the right time to build them.

For the past six to eight months, I’ve been planning holidays with different LLMs. The main frustration has been having to restate all my preferences every time I opened a new chat. Starting with a custom GPT just made sense—especially since I’ve got several term breaks to plan for over the next school year. Programming the GPT was straightforward. I haven’t used it to plan a full trip yet, but I’ve got the base built and I’ve started tinkering. High hopes for this one.

I also put together, though haven’t tested, a CISSP study guide helper. I want to sit for the test but don’t have a study buddy, so I figured why not make one?

Then there’s a slightly different use case: a custom GPT for days out with the kids. Same idea as the travel planner, but without flights and hotels—it’s more about what’s going on in London. I’m actively planning a week with the girls now and most of it is set, but I’ll see if this new GPT adds anything useful. The hardest part here was integrating the data I’ve been tracking on a Trello board with all the activities we’ve done or still want to do. I wanted the GPT to be able to use that context, but I’m cautious about sharing too much personal information with ChatGPT. That’s why I also use Venice.ai, which is a privacy-protecting, open-source based AI. Still, I experimented with exporting the Trello data to JSON and importing it into ChatGPT, and after some trial and error I finally got it working. In this case I had to use ChatGPT since I ran into file size limits with Venice.ai.

I’ve got a few more ideas I want to play with, but for now the three or four GPTs I’ve already built will keep me busy. I need to actually use them and see how they perform before I go any further. Early impressions are promising. Even so, as I remind colleagues and my kids, quoting the Doctor from Doctor Who: the AI lies. Don’t ever trust it completely. If you keep questioning it, though, the results can be pretty good.