Until now, ChatGPT’s “Memory” feature could retain a handful of user-provided facts to personalize responses. Yesterday, OpenAI announced a new feature you will either dearly love or truly hate: ChatGPT can now reference your entire chat history across every conversation you’ve ever had with it — not just a few saved facts.
This upgrade is rolling out to ChatGPT Plus and Pro users starting today, with availability in the EU and some other regions delayed due to privacy regulations.
Functionally, it works like this:
- The old memory system stored user-approved facts (“I have three kids” or “I like short emails”).
- The new system goes much further. If enabled, ChatGPT will use your full conversation history to tailor responses — whether you explicitly saved a fact or not.
Two settings now control this:
- Reference Saved Memories — the old system
- Reference Chat History — the new system that pulls from every conversation you’ve had
Critically, unlike the older memory feature, the new chat history memory cannot be reviewed, edited, or selectively deleted. It’s either on or off.
Why does this matter?
If you want a highly personalized AI assistant — one that “knows you” — this is a breakthrough. It enables real continuity across chats and a more customized user experience.
Privacy concerns are another story. ChatGPT has always stored chat logs on OpenAI’s servers, but now it will use those logs to shape future responses in ways you can’t easily audit or control.
As always, users can disable memory entirely or use Temporary Chat (OpenAI’s incognito mode) to avoid storing history.
This is a foundational shift in how generative AI will work going forward: more useful, more personal, and (for some) more unsettling.
Choose wisely.
Author’s note: This is not a sponsored post. I am the author of this article and it expresses my own opinions. I am not, nor is my company, receiving compensation for it. This work was created with the assistance of various generative AI models.