I used to love ChatGPT's temporary chat — here's why I stopped using it
ChatGPT’s memory feature is proving surprisingly useful

ChatGPT has added and removed a huge amount of features in its lifetime, more than I can count or, quite frankly, remember. However, one feature that I have been a big advocate for in the past is ChatGPT’s temporary chat.
Switch on a small button in the corner of the chatbot to stop the chat appearing in your history. It also means that ChatGPT won’t use its memory of you or update it with anything you say, and the chatbot will refrain from using your chat for model training.
For a long time, I used this feature almost every single time, preferring to have a blank experience each time I came back to the tool, and limiting the amount of my data that was used for training.
But now, I’m finding myself using this feature less and less. That’s not because it’s a bad function, or something that I am now rallying against. Instead, I’m realizing how useful ChatGPT’s memory can actually be.
The benefits of memory
When you turn on temporary chat, the model retains all of its intelligence. It can still tell you all about the world, come up with creative writing, and pump out thousands of lines of code in seconds.
What this mode does instead is limit what ChatGPT knows about you specifically. Without temporary chat enabled, the OpenAI chatbot will make notes of key details about you. If you mention your job, age, location, or anything relevant to future conversations, it will store this information.
But once the temporary mode is turned on, ChatGPT forgets all of these details. While it can feel slightly strange to have a chatbot be intimately aware of key facts about you, I have gone the other way recently of being frustrated at its lack of knowledge when on temporary chat.
Get instant access to breaking news, the hottest reviews, great deals and helpful tips.
I ask a question, and the model returns a somewhat vague response. It doesn’t remember the country I’m in, and even for a query that is localized, it has to guess slightly.
The same goes for when I ask the chatbot about writing. Without temporary chat on, ChatGPT knows my job and alters the response to fit this. With it on, it defaults to a creative writing output.
Sure, I can just give ChatGPT the details each time. I can make my queries clearer in what I want, explaining my location and needs in what I’m asking, but that’s just not how I use AI.
While I’ll occasionally do a deep-dive search, most of my queries are quick and on the fly. I want a fast answer that perfectly fits my needs.
The importance of saving your chats
Equally, while it isn’t always necessary, being able to go back to your old conversations can be really helpful. On a few occasions, I have had a long interaction on ChatGPT, producing a research document or something really helpful.
Then, a couple of days later, when I want to look back through this information, I realize it was all done on the temporary chat. This then leads me to try and recreate the results, which, as anyone who has used a chatbot before will know, is quite challenging.
Should you use temporary chat?
I will still occasionally use the temporary chat feature. I often use it for throwaway questions that I don’t want filling up my library, or to be honest, questions that I’m embarrassed I don’t know the answer to!
It is still a feature I recommend people use or become aware of, mostly to allow for the most privacy in your relationship with ChatGPT as possible. However, in my time using it I have realized just how useful ChatGPT's memory can actually be.
Follow Tom's Guide on Google News to get our up-to-date news, how-tos, and reviews in your feeds. Make sure to click the Follow button.
More from Tom's Guide
- I used Google's Nano Banana to try a bunch of different hairstyles — and the results blew me away
- I tested ChatGPT vs Claude with 7 personal productivity tests — here’s the clear winner
- Not all of ChatGPT’s features live up to the hype — here’s the one that flopped












Alex is the AI editor at TomsGuide. Dialed into all things artificial intelligence in the world right now, he knows the best chatbots, the weirdest AI image generators, and the ins and outs of one of tech’s biggest topics.
Before joining the Tom’s Guide team, Alex worked for the brands TechRadar and BBC Science Focus.
He was highly commended in the Specialist Writer category at the BSME's 2023 and was part of a team to win best podcast at the BSME's 2025.
In his time as a journalist, he has covered the latest in AI and robotics, broadband deals, the potential for alien life, the science of being slapped, and just about everything in between.
When he’s not trying to wrap his head around the latest AI whitepaper, Alex pretends to be a capable runner, cook, and climber.
You must confirm your public display name before commenting
Please logout and then login again, you will then be prompted to enter your display name.