Skip to main content
  1. Home
  2. Computing
  3. News

Google gives memory superpowers to Gemini for more natural chats

Add as a preferred source on Google
Google Gemini running on an Android phone.
Joe Maring / Digital Trends

Google is finally bringing a crucial new feature to Gemini that will solve a key pain point of interacting with its AI chatbot. The company is enabling a memory feature which allows Gemini to pull up details from a past conversation.

“Whether you’re asking a question about something you’ve already discussed, or asking Gemini to summarize a previous conversation, Gemini now uses information from relevant chats to craft a response,” says a Google update.

Recommended Videos

So far, if users wanted to reference any detail from a conversation they had with Gemini in the past, they had to pull up their chat history. Once users found the conversation, they could shoot any further queries for the chatbot to handle in that particular context.

Of course, the process is cumbersome, especially if you are trying to recall details from a chat you had long ago. But the worst part is that there is no search function in the Gemini chat history.

Referencing old chats is the trick

Unlike the way you look up for forgotten tabs in a browser history, Gemini would have users scrolling unless they found the conversation they were looking for and pick up from there.

Gemini on Pixel 9 processing a PDF file.
Nadeem Sarwar / DigitalTrends

This can be a nuisance, if your chats are separated across different Gemini models. Moreover, for people who use Gemini for more intimate purposes, such as seeking emotional support or any form of help, lack of memory can quickly degrade the experience.

A robust memory is one of the most highly requested features in online communities where people discuss how they use chatbots for objectives like virtual companionship. Apps like Nomi are the best example where chatbots with a memory system are highly sought-after.

For easier access, however, Google has offered the option to pin important chats. The latest Gemini tweak is a step in the right direction, but do keep in mind that you must have Gemini App Activity enabled for the memory feature to work.

The new memory feature in Gemini currently supports only English language and available for users with a Google One AI Premium subscription. It will be available across Gemini’s web and mobile platforms.

Subscribers can also access the new Gemini 2.0 series experimental models that Google released a few days ago. The company says support for more languages will arrive soon, and it will also be extended to Enterprise and Workspace Business customers in the coming weeks.

Nadeem Sarwar
Nadeem is the Managing Editor at Digital Trends.
AI is raising hell for Linux managers buried under a flood of dupe bug reports
Torvalds’ latest Linux update warns that AI-assisted reporting can create more maintenance work when contributors skip verification
Computer Hardware, Electronics, Hardware

AI may be finding Linux bugs faster than humans can sort them.

In the Linux 7.1-rc4 update, Linus Torvalds said the kernel’s security list has been swamped by AI-assisted bug reports, many of them duplicates from people using similar tools and finding the same issues. The release itself looks routine, with drivers making up about half the patch and GPU fixes leading the way.

Read more
Spooked by the MacBook Neo, Asus shows off affordable Intel Wildcat Lake laptops
Its new Wildcat Lake laptops bring faster screen specs to Apple’s affordable fight
Computer, Electronics, Laptop

Asus isn’t waiting for Apple’s lower-cost laptop story to settle. Its new Intel Wildcat Lake Vivobook 14SE and 16SE have launched in China, giving Windows laptop makers an early chance to crowd Apple on price and visible hardware.

The sharper threat is the Vivobook 16SE, which starts at CNY 4,599, about $675, with a higher-end display model at CNY 4,999, around $734. That pricier version adds a 16-inch 2560 x 1600 screen with a 144Hz refresh rate, variable refresh rate support, and a 400-nit brightness rating.

Read more
Intel reveals Project Firefly to make cheap Wildcat Lake laptops that rival MacBook Neo
Project Firefly standardizes Wildcat Lake laptop designs so PC makers can chase Apple with lower prices and cleaner hardware
Crowd, Person, Audience

Intel is trying to make budget Windows laptops look a lot less bargain-bin.

Project Firefly, launched in China alongside Intel’s Wildcat Lake laptop chips, gives PC makers a common hardware playbook for thinner, cleaner, lower-cost systems that can take a more direct swing at MacBook Neo. The promise is simple, fewer compromises where budget laptops usually show them most.

Read more