I’ve been testing ChatGPT-5.5 a lot recently. I’ve tested it against Claude Opus 4.7 and just recently put it head-to-head against Gemini 3.1 Pro. And while it’s smart and fast, it’s almost too fast, which makes it less smart at times.

Don’t get me wrong, most of the time, speed is what you want. The fast summary, the fast response and fast draft of an email all make sense. But every now and then, I’ve noticed the speed becomes a problem. The response is too generic, too polished and just skims the surface of what I’m looking for.

Article continues below

You may like

“people pleasing” that tends to come out of ChatGPT when it’s just trying to get an answer out fast.

I’ve noticed that whenever I use this prompt, ChatGPT hallucinates less and isn’t trying to please me as much. (As a side note, ChatGPT-5.5 seems to be less of a people pleaser in general, thanks to the updated model.)

Click to follow Tom's Guide on Google News

Follow Tom’s Guide on Google News and add us as a preferred source to get our up-to-date news, analysis, and reviews in your feeds. Subscribe to Tom’s Guide on YouTube and follow us on TikTok.