OpenAI gives ChatGPT better memory.
The San Francisco artificial intelligence start-up said Tuesday it is releasing a new version of its chatbot that will remember what users say so it can use that information in future conversations.
If a user mentions a daughter, Lina, who is about to turn 5, likes the color pink and enjoys jellyfish, for example, ChatGPT can store that information and retrieve it as needed. When the same user asks the bot to “create a birthday card for my daughter,” it can create a card with pink jellyfish that says “Happy Birthday, Lina!”
With this new technology, OpenAI continues to turn ChatGPT into an automated digital assistant that can compete with existing services like Apple’s Siri or Amazon’s Alexa. Last year, the company allowed users to add instructions and personal preferences, such as details about their jobs or the size of their families, that the chatbot should take into account during each conversation. Now, ChatGPT can draw on a much wider and more detailed set of information.
“We think the most useful assistants are the ones that evolve with you — and keep up with you,” said Joanne Jang, an OpenAI product lead who helps oversee the memory project.
Although ChatGPT can now remember past conversations, it can make mistakes — just like humans. When a user asks ChatGPT to make Lina a birthday card, the chatbot can create one with a tiny typo, such as “Happy 5th Birthday! Lina!”
The company is first providing the new technology to a limited number of users. It will be available to people using the free version of ChatGPT as well as those who sign up for ChatGPT Plus, a more advanced service that costs $20 a month.
OpenAI is also introducing users on Tuesday to what it calls temporary chats, in which conversations and memories are not saved.
ChatGPT has been offering a limited memory format for some time now. When users chatted with the bot, its responses were based on what they said earlier in the same conversion. Now, the bot can pull information from past conversations.
(The New York Times sued OpenAI and its partner Microsoft in December for copyright infringement on news content related to AI systems.)
The bot creates this memory by automatically locating and storing information that could be useful in the future. “We’re relying on the model to decide what might or might not be,” said OpenAI researcher Liam Fedus, referring to the AI technology behind ChatGPT.
Users can tell the bot to remember something specific from their conversation, ask what is already stored in its memory, tell the chatbot to forget certain information, or turn off memory altogether.
By default, OpenAI records entire ChatGPT conversations and uses them to train future versions of the chatbot. OpenAI said it removed personally identifiable information from conversations used to train its technology. And users can choose to remove their conversations entirely from OpenAI’s training data.
However, creating and storing a separate list of personal memories that can be played back by the chatbot in conversations could raise privacy concerns. The company argued that what it did was not much different from the way search engines and browsers store their users’ Internet history.
