Everything reminds me of Her. While ChatGPT is not as powerful as the artificial intelligence from Spike Jonze’s sci-fi romance movie, OpenAI’s experimental memory tool for its chatbot seems to suggest a future where bots are highly personalized and capable of more fluid, lifelike conversations.
OpenAI just soft-launched a new feature for ChatGPT called Memory, where the AI chatbot stores personal details that you share in conversations and refers to this information during future chats. Right now, ChatGPT’s Memory feature is available only to a small group of users to test—it’s unclear when a wider rollout for more chatbot users will happen. The feature is expected to be available for all chatbot users, not just subscribers to ChatGPT Plus.
WIRED received early access to the feature from OpenAI, and I’ve spent the past few days trying it out to better understand this new functionality and to collect some advice you can use to get started. While a few specifics may change before the feature is made available to everyone, here’s what you can likely expect from ChatGPT’s Memory.
When ChatGPT’s Memory arrived on my paid account, I received a pop-up notification explaining the fresh tool and how it can be used for remembering certain details across conversations. It’s worth noting that Memory is enabled automatically. You can easily opt out if you’d prefer by opening Settings, then Personalization, and toggling the Memory option by moving the slider to the left.
Adding facts about yourself to ChatGPT’s Memory is simple: Just chat with the bot. As you use OpenAI’s software, ChatGPT gleans personal insights from the conversations, like your name and where you live, as well as more niche observations, like your favorite movies and least favorite foods. While the chatbot passively gathers this data, you can also try a more direct approach. Start a prompt with “Please remember that …” or use similar language to add info you want filed to ChatGPT’s Memory.
Removing memories from ChatGPT is just as easy. To see everything the bot actively remembers about you, click on your username, go to Settings and Personalization, and then tap on the Manage button at the bottom of the screen. Next, select the trash can icon next to any memory you’d like to remove. You can also go nuclear by choosing Clear ChatGPT’s Memory, which will let you start over with a clean slate.
If you already have a grasp on what the bot remembers about you, you can request that certain things get deleted or adjusted through conversations with the AI. Prompt ChatGPT to change what’s saved in the Memory with commands like, “Forget everything you remember from this chat,” or “Adjust my current city from San Francisco to Sacramento.”
My first reaction to the announcement of this new feature was apprehension over OpenAI storing personal info about me and potentially using my personal details to improve future AI models. OpenAI’s FAQ for the feature even reads, “Memories may be used to train our models depending on your choices and plan.” I’m glad to see that users can opt out from training future models—by going into Settings and Data controls—while still having the Memory feature enabled, though this doesn’t assuage all my privacy concerns.
Want to avoid the Memory feature for a few chats but not turn it off altogether? OpenAI is also testing out a temporary chat tool. Enable it by opening the AI model menu, labeled either ChatGPT 3.5 or ChatGPT 4, and select the Temporary chat option. These conversations will still be saved for up to a month by OpenAI, but they won’t be included in model training, the bot’s Memory, or your chat history.
Do you share a paid ChatGPT Plus account with friends or family members? Then it’s probably best to keep the Memory option turned off. With Memory activated, the chatbot might blend all of the details from multiple interactions into one composite understanding of who the user is.
OpenAI will continue to experiment with what ChatGPT is and isn’t allowed to remember, but certain topics are already off limits. For example, you can’t ask the chatbot to remember your Social Security number or passwords. This is also worth highlighting since it may feel counterintuitive: Deleting a conversation from ChatGPT doesn’t also destroy the memories associated with it. So, you have to scrub your memories as well as your chats if you’re looking to clear out the details.
I was decently impressed by the new feature during my initial interactions. One of the major issues with utilizing chatbots for productivity has been their lack of automatic retention. Having to remind ChatGPT about crucial details over and over is a frustrating time suck, and only power users are likely to go in and manually tweak the custom instructions, where you can save personal details and change ChatGPT’s cadence. It feels much more seamless to control what the bot remembers through text prompts.
As the AI race continues, chatbot companies are likely to continue with this personalization trend by offering additional features that adjust the outputs based on what the software knows about you. For now, it’s the user who may improve at AI prompting by participating in multiple conversations with the tool. In the future, the chatbot may return the favor and get better at providing satisfactory, context-rich answers to your questions the longer you use it.
Exploring the Lessons from My Experience with ChatGPT’s New Memory Feature
Artificial Intelligence (AI) has made significant strides in recent years, and OpenAI’s ChatGPT is a prime example of this progress. With its ability to generate human-like responses, ChatGPT has become a popular tool for various applications, including customer service, content creation, and personal assistance. Recently, OpenAI introduced a new feature called “memory” to ChatGPT, allowing it to retain information throughout a conversation. As an AI enthusiast, I was excited to explore this new capability and see how it could enhance the user experience.
The memory feature in ChatGPT enables the model to remember key details from previous interactions, making it more context-aware and capable of maintaining coherent conversations. This development is a significant step towards creating AI systems that can engage in more meaningful and dynamic exchanges with users. To better understand the potential of this feature, I decided to put ChatGPT’s memory to the test.
In my initial interactions with ChatGPT using the memory feature, I found that it greatly improved the continuity of conversations. Previously, without memory, ChatGPT would often lose track of the context and provide generic responses. However, with memory, it was able to recall important information from earlier parts of the conversation and build upon it. This made the interactions feel more natural and engaging.
One of the most impressive aspects of ChatGPT’s memory feature was its ability to handle complex queries. When I asked a series of related questions, the model was able to remember the context and provide accurate responses based on the accumulated knowledge. For example, during a conversation about a specific topic, I asked a follow-up question that required referencing a previous answer. ChatGPT seamlessly incorporated that information into its response, demonstrating a deeper understanding of the conversation.
However, while the memory feature is undoubtedly a valuable addition, it is not without its limitations. In some cases, ChatGPT would occasionally misinterpret the context or provide incorrect information based on its memory. This highlights the challenge of training AI models to accurately retain and recall information. It is crucial to ensure that the model’s memory is reliable and consistently aligned with the user’s intent.
Another lesson I learned from my experience with ChatGPT’s memory feature is the importance of clear and concise communication. When interacting with the model, I found that providing specific instructions and asking questions in a straightforward manner yielded better results. This is because the memory feature relies on accurate input to store and retrieve information effectively. By being mindful of how I framed my queries, I was able to enhance the quality of the responses received.
Furthermore, it is essential to remember that ChatGPT’s memory is limited in capacity. The model can only retain a certain amount of information before it starts forgetting earlier details. This constraint emphasizes the need for efficient communication and avoiding unnecessary repetition. By keeping conversations concise and focused, users can maximize the benefits of the memory feature and ensure a smoother interaction.
In conclusion, my experience with ChatGPT’s new memory feature has been enlightening. It showcases the potential of AI systems to engage in more coherent and context-aware conversations. The ability to remember and recall information enhances the user experience by providing more accurate and relevant responses. However, it is crucial to acknowledge the limitations of this feature, such as occasional misinterpretations and capacity constraints. By understanding these lessons, we can harness the power of ChatGPT’s memory feature effectively and continue to push the boundaries of AI technology.
