Google recently introduced a new feature for Gemini called Saved Info. This feature is accessible in the Settings menu, where users are directed to a new interface that allows them to add memories manually for Gemini to Remember. In addition to manual input, users can explicitly ask Gemini to remember details during conversations, and these memories will be stored automatically, similar to how ChatGPT handles this functionality.
Rolling out starting today, you can ask Gemini Advanced to remember your interests and preferences for more helpful, relevant responses. Easily view, edit, or delete any information you've shared, and see when it’s used.
— Google Gemini App (@GeminiApp) November 19, 2024
Try it in Gemini Advanced → https://t.co/Yh38BPvqjp pic.twitter.com/gR354OZxnV
While this feature closely mirrors OpenAI’s implementation, Gemini offers the added flexibility of manually adding new memories. The same interface also enables users to remove or edit stored information, providing full control over the memory data.
Another distinguishing aspect of Gemini is its ability to operate with significantly longer context windows, supporting up to 2 million tokens. However, the memory capacity for Saved Info is capped at 2500 tokens, slightly less than ChatGPT’s limit of 2800 tokens.
This update is accompanied by a refreshed official changelog, outlining the new feature and enhancements.
