{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreifzfjpw4phog75eg5d5jt2ajgafzh32kino2y2kzcsycgp6v4faoy",
    "uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mlagzva4m6d2"
  },
  "path": "/t/turn-the-fucking-automatic-memory-creation-editing-feature-into-an-on-off-setting/1380433#post_1",
  "publishedAt": "2026-05-07T04:24:09.000Z",
  "site": "https://community.openai.com",
  "textContent": "I’m not saying remove memory entirely.\n\nUsing existing saved memories to improve responses is useful.\nThe problem is when ChatGPT creates new memories or modifies existing ones without the user explicitly saying “remember this.”\n\nThat is not convenience.\nThat is a user control problem.\n\nA user may want ChatGPT to reference existing saved memories.\nBut that does not mean they want ChatGPT to automatically write new memories.\n\nThese settings should be separate:\n\nUse saved memories: On\nAutomatically create/edit memories: Off\n\nWhy the hell is this not already an option?\n\n“Just turn memory off” is a bullshit answer.\nThat also disables the existing memories the user actually wants to keep using.\n\nIf chat history reference is already a separate feature, then automatic memory writing should absolutely be separately controllable too.\n\nA correction, complaint, temporary preference, or one-time instruction during a conversation should not be automatically turned into long-term memory.\n\nThe fix is simple:\n\nLet ChatGPT read existing memories.\nDo not let it write new memories unless the user explicitly allows it.\nDo not let it edit existing memories unless the user explicitly requests it.\n\nSeparate memory read and memory write permissions.\n\nNot having this basic on/off control while allowing automatic memory creation and modification is a fucking stupid design.",
  "title": "Turn the fucking automatic memory creation/editing feature into an on/off setting"
}