Google Gemini has always felt like it’s a step behind. Many features seem to come out much later than its competitors, and they’re never fully fleshed out at launch. For example, Gemini recently announced that it was officially adding memory functionality. I initially assumed it would be similar to ChatGPT, but in reality it’s still far off—for instance, it only supports English.

Gemini officially introduces memory feature — you can ask it to remember anything.
Earlier, Google Gemini announced on official X: “Starting today, you can ask Gemini Advanced to remember your interests and preferences to provide more helpful and relevant responses. You can also easily view, edit, or delete any information you’ve shared and know when this information is used.”
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.
Try it in Gemini Advanced → https://t.co/Yh38BPvqjp pic.twitter.com/gR354OZxnV
— Google Gemini App (@GeminiApp) November 19, 2024
The way it works is similar to ChatGPT; users can ask Gemini to remember anything. However, there is one difference: ChatGPT has an automatic memory feature that decides whether to remember based on the current chat content, even if the user doesn’t ask. On the Gemini side, it seems you have to explicitly ask, and only then will the AI remember.
Google also provides examples, such as:
- Please use simple language and avoid technical terms.
- I am a vegetarian, please do not recommend recipes with meat.
- When answering, please include a Spanish translation.
- When planning your trip, please provide a daily cost estimate.
- I can only write code in JavaScript.
- I like short, clear answers.
According to TechCrunch In response to inquiries made to Google, Gemini’s memory feature will not be used to train models, so users can use it with confidence.
Currently, Gemini’s memory capabilities still have many limitations.
Although Gemini has finally introduced memory capabilities, it still lacks too many features at the moment. For example, it’s limited to Gemini Advanced paying subscribers, unlike ChatGPT’s free tier which also has access. It only supports English, and there’s no word on when other languages will be added. It also seems that only the web version of Gemini has memory; many users report that the app’s responses still don’t have memory capabilities.
Many netizens also commented below Gemini’s post, saying the pace was a bit too slow, and that it was just memory? Some even said, “They’re just copying ChatGPT’s features 😅 I can’t believe Google has millions of employees but still can’t come up with something new.”
Google Gemini iOS version is now officially available.
Besides the Gemini memory feature, a few days ago The Gemini iOS version is also now available on the Taiwan App Store.and it supports the Gemini Live feature, but currently the language does not include Chinese, so if you want to experience it, you need to go to settings and change Gemini’s preferred language, such as to a supported language like English, Japanese, French, German, etc.:

Additionally, a few days ago, foreign media discovered through digging into the APK that… Gemini Live may potentially support file processing functionality.But how the whole thing currently works isn’t clear yet, such as whether you upload files through the chat window first, or whether it reads documents from Google Cloud.

Source: KOCPC Chinese