I've been using ChatGPT since it was first rolled out in late fall of 2022. Like most people, when I first started querying it, I had no idea everything it was capable of — but after testing every new model extensively since then, I've become a power user.
ChatGPT has had 34 models! And yet, getting useful answers has almost nothing to do with which model you're using and has everything to do with how you talk to it.
I've watched people upgrade to the newest, most expensive version and still get mediocre results, while a friend on the free tier pulls genuinely useful work out of it. The difference is almost never the tool, but the instructions (prompts). This is important for those who might be upset about the recent suspension of Claude's Fable 5 or those of us still grieving ChatGPT-4o.
