Follow ZDNET: Add us as a favorite source On Google.
ZDnet’s key takeaways
- Copilot can now remember or forget details depending on his order.
- Copilot’s memories can be viewed in Settings > User Memory.
- Greater memory comes with greater risk.
Microsoft’s Copilot AI assistant can now apparently be prompted to remember or forget specific details about users’ lives. In x post On Monday, Mustafa Suleyman, CEO of the company’s AI division, announced that those personal memory preferences will, in turn, shape the chatbot’s future responses.
Also: You can now chat with third-party apps in Chat – here’s how
For example, you can now ask Copilot to remember that you’re a vegetarian, so that it takes that dietary restriction into account when responding to your subsequent requests for local restaurant recommendations. Or you can instruct it to remember your new partner’s name and birthday; If that doesn’t work, you can always tell them what it is—what their names are.
The new Memories feature can also be useful if you’re trying to form a new habit, like writing in your journal every morning. Simply ask Copilot to send you a daily reminder to journal after you wake up. You can use the “Forget” and “Remember” commands as Microsoft Example Show.
Copilot will keep track of its memories, which you can view and edit manually by clicking Settings > User Memory. The new features are now live across desktop and mobile.
striking a balance
In their ongoing efforts to build AI assistants that are maximally engaging and useful across a broad set of tasks, tech developers have had to strike a delicate balance between memory and forgetfulness.
Also: How to use Chatgate freely without giving up your privacy – with a simple trick
Train a chatbot to remember every little detail about a user’s life, and it can create a lag every time the user asks it (aside from the privacy concerns of giving the chatbot personal information). A chatbot that just forgets everything a user tells it, on the other hand, isn’t much more useful than a Google search.
Rather than taking a one-size-fits-all approach to the memory-forgetfulness problem, companies are essentially outsourcing it to individual users themselves, giving them the ability to modify the extent to which AI systems can recall their personal information.
Building more useful AI assistants
Microsoft first introduced a “Personalization and Memories” feature to Copilot in April of this year, positioning it as an important step toward building an AI companion that understands the unique context and preferences of individual users.
Through the feature, each exchange with the chatbot leads to its own corpus of training data so that, over time, it is able to build more fine-grained user profiles—similar to the way the algorithms powering social media apps like Instagram and TikTok personalize their feeds to individual users over time.
Also: AI model whistling in Anthropic’s open-source safety tool – found in all the wrong places
“As you use Copilot, it will pay attention to your interactions, creating a rich user profile and tailored solutions you can depend on,” Microsoft wrote in a May blog post“From suggestions for a new vacation spot to a product you might enjoy, Copilot is your go-to AI companion to help you understand and see.”
It followed closely on the heels of a similar update to CHATGPT’s memory capabilities, enabling it to reference a user’s past conversations in order to more effectively tailor its responses. Anthropic also announced in August that the cloud could be prompted to retrieve information from past exchanges – although that feature is turned on by default, users can also manually turn it off.
Want more stories about AI? Sign up for AI LeaderboardOur weekly newsletter.
All of these efforts are geared toward building chatbots that are more than just question-answering machines, and closer to a trusted friend or colleague who are able to get to know users and update their understanding over time.
risks of remembering
A chatbot’s ability to remember information over time and build detailed user profiles is not without risks, however.
Also: You can now use CHATGPT to create a personalized Spotify playlist – here’s how
In the event of a data breach, sensitive information shared by individual users or organizations may be leaked. On a psychological level, an AI chatbot that gradually learns about a person’s communication style and beliefs over time could push that person into delusional patterns of thought – a phenomenon now widely described in the media (not by psychiatrists) as “AI psychosis.” This is also notable given the recent controversy surrounding AI companions.
Giving users the ability to turn off or modify the chatbot’s memory feature is a good first step, but not all users are smart enough to know how to take these steps, or even be aware of the fact that the information they’re sharing is being stored on a server somewhere.
Also: How people really use Chaturbate vs. the cloud – and what the differences tell us
While the EU’s General Data Protection Regulation (GDPR) requires tech companies to disclose when they are collecting and processing users’ personal data — such as their name, address, or preferences — no such blanket regulation currently exists in the US, meaning tech developers themselves have transparency policies to ensure they have an understanding of how their personal information is handled.
