I spent weeks testing AI tools – these are the few I’d use again

I've been stress-testing quite a few large language models and some bonus tools...

Pic by Philip Oroni / Unsplash+

I’ve been working on this story for weeks. I’ve used ChatGPT for a while now, but I wanted to see what else was out there, in case I was missing a trick. At first, I thought it’d be relatively easy to test different large language models.

But it wasn’t. You can’t just ask an LLM a question and judge it on one answer. You need to work with it. Test its boundaries. Notice what it does well, where it doesn’t, and whether its features align with your needs.

So that’s what I did. I moved between platforms, giving almost all of them a fair shot (I’ve outlined what I didn’t try for long and why) – and only dropped a tool when something else proved more useful.

I also came across a few platforms that aren’t strictly LLMs, but still sounded worth a try. So I gave them one.

Below the paywall: the tools I tested, what they’re good for (or not) and whether I still use them.