# Memory Should Model the User Rather than Saving Random Summarized Excerpts

**URL:** <https://community.openai.com/t/memory-should-model-the-user-rather-than-saving-random-summarized-excerpts/1258485>\
**Category:** Feature requests\
**Created:** [May 12, 2025, 3:34am UTC](https://community.openai.com/t/memory-should-model-the-user-rather-than-saving-random-summarized-excerpts/1258485 "2025-05-12T03:34:36Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![gregb](https://avatars.discourse-cdn.com/v4/letter/g/da6949/32.png) [@gregb](https://community.openai.com/u/gregb)\
**Post date:** [May 12, 2025, 3:34am UTC](https://community.openai.com/t/memory-should-model-the-user-rather-than-saving-random-summarized-excerpts/1258485/1 "2025-05-12T03:34:36Z")

</div>

Hello,

I believe that ChatGPT should manage a server-side JSON model of the user, rather than saving random summarized excerpts of conversations.

Perhaps it could add to a memory by thinking something like \<\<\<\<user.family.sister.name=“Bertha”\>\>\>\> and its memory model would be updated.

The JSON memory model of the user would then be provided to it with every request—possibly pruned by a smaller LLM for relevance to the present conversation.

I’m suggesting this because I believe it likely more closely resembles how our brains remember facts: by building models of the things around us. The current approach could be compared to forcing the model to memorize the entire summarized memory except, word for word.

Best regards,  
Greg