Memory & instructions: teach ChatGPT to know you.
ChatGPT has two ways of remembering you: Custom Instructions, which you write, and Memory, which it learns on its own. Used well, they make it feel like it knows you. Used badly, they quietly make every answer worse. Here's what belongs where — and how to clean up Memory when it drifts.
One is a contract. One is an observation log.
They both shape future responses, but they work differently and need different upkeep.
What you explicitly tell ChatGPT about you and how to respond. Lives in Settings → Personalization, in two boxes.
What ChatGPT picks up from your chats and stores on its own. Helpful, but it can save things that are wrong, stale, or that you never meant it to keep.
Clean up what ChatGPT saved about you.
Here's your Memory panel. For context: you write in TypeScript these days, you run a weekly newsletter, and you often do want depth — not just quick answers. Review each item and decide: Keep the accurate, useful ones; Delete what's wrong, outdated, or sensitive.
Instructions, Memory, or neither?
Three pieces of context. Put each in the right home.
Write Custom Instructions that work.
Settings → Personalization gives you two boxes — "what to know about you" and "how to respond." Fill both with process and style, never secrets.
Memory is on by default. Switch it off for:
- Shared accounts (family/team) — memories get tangled.
- Sensitive sessions — PHI, confidential financials, NDA-covered work.
- Prompt tests where you want a clean baseline.
Turning Memory off doesn't disable Custom Instructions — the contract still applies.
Temporary chat stopped being all-or-nothing.
Temporary chat used to be one switch: a clean room with no memory, no Custom Instructions, no plugins, and nothing kept. OpenAI has now split that into a choice you make when you open the chat — and a second choice you make at the end.
No memory, no Custom Instructions, no plugins. Creates no new memories. This is the old behaviour, unchanged.
Can read your memories, Custom Instructions and plugins to tailor the answer. Still creates no new memories, and still stays out of your history.
Two details worth committing to muscle memory. First, the mode is set only when you start the conversation — you cannot flip it once you are typing. Second, you can now save a temporary chat into your history, which converts it into an ordinary chat: from that moment it follows your normal account-level personalization and model-improvement settings, and it can be referenced later like any other conversation.
“Temporary chat” is no longer a single guarantee, so the sensitive-session advice needs one extra beat: glance at which mode you opened before you paste anything you would not want personalized. Non-personalized is still the default, so the safe path is unchanged — but personalized temporary chats do pull your existing memory in, and a chat you save stops being temporary in every sense.
Useful side effect: personalized temporary chat is now the cleanest way to test a prompt against your real Custom Instructions without polluting Memory with the result.
Privacy Center: one map to every switch in this lesson.
Everything above — Memory, temporary chat, model-improvement opt-out, connected apps, export and delete — lives in different corners of Settings. OpenAI is now rolling out a Privacy Center that puts them on one page with a plain-language explanation of each and a Manage button that jumps to the real setting. It changes nothing by itself: opening it does not alter a setting, delete data, or override a workspace policy. The controls still live in Settings; this is the index.
Where it is: on the web, open your account menu → Help → Privacy center; on iOS and Android, Settings → Privacy Center. It is organized in three groups — Personalized chats & ads (Memory, ad personalization for Free and Go users, location), Chat privacy (temporary chat, with a one-tap way to start one), and Data use & access (plugins and apps, multi-factor authentication, the "Improve the model for everyone" toggle, export, delete account).
Rolling out to signed-in Free, Go, Plus, Pro and Business accounts on web, iOS and Android; not Enterprise, Edu or Healthcare, and in a Business workspace it cannot override what your admin has set. If you do not see it yet, your account or app version has not been reached. The habit: when you run the Memory audit at the top of this lesson, open Privacy Center first and walk the three groups — it is the fastest way to notice a toggle you did not know existed, such as ad personalization or an app you connected months ago.
Locked chats: hidden from history, not private from OpenAI.
OpenAI added locked chats: you can keep a conversation in your account but hide it from regular chat history, pinned chats, and search. To open it again you use your 4-digit account PIN or supported device authentication. To lock one, open the chat’s more-options menu (•••) and choose Lock chat. It is rolling out gradually to Free, Go, Plus and Pro users on web, iOS, Android and the new ChatGPT desktop app for macOS and Windows.
OpenAI states that your retention and model-improvement settings do not change. So locking is a screen-privacy feature — useful when someone borrows your laptop or glances at your sidebar — not a data-privacy one. Anything you would not want used for model improvement still needs the opt-out or a temporary chat, as covered above. OpenAI’s release note does not say how locked chats work for Business, Enterprise or Edu workspaces, shared chats, or projects, so check the linked help article before relying on it there.
Audit and rewrite tonight
Two tasks, 15 minutes. (1) Open Settings → Personalization → Memory and read everything stored about you — delete what's wrong, redundant, or shouldn't be there. (2) Rewrite your Custom Instructions with the two-box template above. Save, then test the difference on your next three prompts.
What you can do now
- Tell Custom Instructions (the contract) from Memory (the observation log)
- Write Custom Instructions with the two-box template
- Add to Memory deliberately with "Remember that…" — but keep critical context in Instructions
- Audit Memory monthly: delete what's wrong, outdated, or sensitive; keep accurate-useful
- Know when to turn Memory off entirely