Superpower Daily
Chinese Models Take More Than 60% of OpenRouter Tokens, Driven...Model-Serving Platforms Reach 6.1% of AI-Spending Businesses, W...Gemini Omni 1.1 Flash Adds 40-Second Scene Extensions and 4K Fi...Databricks Says 300M Chart-JSON Pipeline Tops Four Multimodal B...London Surgeons Remove 11mm Brain Tumour With Live AI Anatomy M...Nvidia’s $63.1 Billion Receivables Add a Cash-Flow Caveat to It...Chinese Models Take More Than 60% of OpenRouter Tokens, Driven...Model-Serving Platforms Reach 6.1% of AI-Spending Businesses, W...Gemini Omni 1.1 Flash Adds 40-Second Scene Extensions and 4K Fi...Databricks Says 300M Chart-JSON Pipeline Tops Four Multimodal B...London Surgeons Remove 11mm Brain Tumour With Live AI Anatomy M...Nvidia’s $63.1 Billion Receivables Add a Cash-Flow Caveat to It...
Productspublished

ChatGPT Lets Temporary Chats Use Memory, Then Convert Them to Regular Chats

The update separates using established ChatGPT context from keeping a conversation, but saving a session moves it into normal history, memory, and account-level data controls.

By 3 min read
ChatGPT Lets Temporary Chats Use Memory, Then Convert Them to Regular Chats
Sign in to save and react

Listen to this story

The audio brief

About 1:22
0:001:22
Read transcript
ChatGPT can now let a Temporary Chat use your existing setup, and then turn the whole conversation into a regular chat when you decide it is worth keeping. OpenAI introduced the change on August twenty-seventh, separating personalization from persistence. Before sending the first message, you choose whether that temporary session can read existing memories, custom instructions, and plugins. That choice is locked once the conversation starts. If you leave the chat unsaved, it stays out of history, creates no new memories, and is not used to improve OpenAI’s models. It may still be retained for up to thirty days for safety, so “temporary” does not mean instant deletion. The important detail is what the save button does. It is not a bookmark or a copy. Saving converts the entire exchange into a regular chat, placing it in history and bringing it under your account’s normal memory and model-improvement settings. If you had disabled model training, that preference remains in force after the conversion. This gives users a useful middle ground: familiar context for a disposable session, with the option to preserve the work later. But the boundary is not universal. Anything sent through third-party actions may be retained under the recipient’s own privacy policy, potentially beyond OpenAI’s thirty-day safety window. The key constraint is that the personalization choice—and the decision to save—both shape what happens to the conversation afterward.

Story brief

3 key points

OpenAI has separated personalization from persistence in ChatGPT Temporary Chats. Starting August 27, users can let a temporary session read existing memories, custom instructions, and plugins without creating new memories or appearing in history. They can later save the entire exchange, which converts it into a regular chat governed by account-level memory and model-improvement settings. Unsaved sessions may still...

  1. 01

    The personalization choice must be made before the first message and cannot be changed mid-conversation.

  2. 02

    Unsaved Temporary Chats do not create memories, appear in history, or help improve OpenAI’s models.

  3. 03

    Saving is a full status conversion, not a bookmark: the complete exchange enters chat history.

ChatGPT users can now bring their existing setup into a conversation that remains disposable—until they choose to save it. That new save action converts a Temporary Chat into a regular chat, changing its place in history and the settings that govern memory and model improvement.

OpenAI updated Temporary Chat on August 27. Users can decide before their first message whether the session may use existing memories, custom instructions, and plugins. The choice is set at the start of the chat; it cannot be changed once the conversation has begun.

Context without a new record

The change breaks apart choices that were formerly tied together: whether ChatGPT may draw on prior personal context, whether the current exchange writes new context, and whether the exchange stays in account history. Previously, a user who found a Temporary Chat worth keeping had to abandon it or manually move its contents into a standard conversation.

The three controls now operate separately

  • Personalization: A user may allow a Temporary Chat to use existing memories, custom instructions, and plugins before sending the first prompt.
  • Memory creation: A personalized Temporary Chat can read existing memories, but it cannot create or update them while it remains temporary.
  • Persistence: Leaving the chat unsaved keeps it outside history; saving the full exchange turns it into a regular chat.

Save changes the governing rules

An unsaved Temporary Chat stays out of chat history, does not create memories, and is not used to improve OpenAI’s models. Those protections apply whether the user chose a blank-slate session or permitted it to read existing context.

Temporary does not mean immediately deleted

Temporary status has a retention limit rather than an instant-erasure promise. OpenAI may retain a copy of an unsaved Temporary Chat for up to 30 days for safety purposes. That period is distinct from the chat’s absence from history, memory creation, and model-improvement use.

Saving ends the temporary treatment for the complete exchange. It appears in history and may become available to ChatGPT’s personalization systems under the user’s normal settings. A user who has disabled model training keeps that preference after saving, so conversion does not override account-level controls.

Third-party actions sit outside the simple boundary

The new flexibility also makes the moment of choice more consequential. A user can bring familiar preferences into a short-lived session without adding new memories, then preserve useful work later. But information sent through third-party actions may be governed by the recipient’s privacy policy and may be retained beyond OpenAI’s 30-day safety window.

Related coverage

Continue reading