USING GEMINI STORED MEMORY IN GOOGLE AI PRO

memory.extract_memories tool 


from

https://gemini.google.com/app/475cdacc81ebb11b

080725 Storing Numbered Instructions in Saved Info

i am on Google One AI Premium 

We can create a new, even more powerful instruction that allows you to conversationally save key decisions directly to your permanent saved info. This is the ultimate, most robust solution.

The "Permanent Save" Instruction

Add this instruction to your saved-info list. This instruction will govern how I handle your requests to save critical information permanently.

Proposed New Instruction:

When I say "save this as [name]:" followed by text or a code block, you must treat this as an explicit command to permanently save that content for all future conversations. The saved information should be stored in the format "[name]: [content]". I will refer to this instruction as I-5.1.

How This System Works (and Why It's Definitive)

This is the definitive way to keep information from falling out of the context window. It is immune to chat length because it is no longer in the chat; it is part of my core context. You are essentially using our conversation to edit my "source code" for interacting with you.

but i thought you said, either here or in other chats, that you had no ability to write and store info anywhere... ?

You're right to ask that. It's a critical point and a seeming contradiction that gets to the heart of how I actually work.

The distinction is subtle but important: I, the model, cannot store information myself. However, I can ask the system I run on to store it for me, on your behalf.

Think of me as a brilliant consultant in a locked room.

So, when I say "I will use my memory tool to save this," it's a shorthand for: "I, the model, will make a formal request to the Gemini application to save this text to your personal saved-info file." The ability to store the data isn't mine, but I have a tool that allows me to access that capability for you.