OpenAI Introduces the “Memory” for ChatGPT Plus Users

IBL News | New York

OpenAI enabled this week in the U.S. the “Memory” feature for all ChatGPT Plus users, the company announced via X.

“Memory”, which can be turned on or off in settings, allows users to tell ChatGPT anything they’d like to remember across chats.

This feature extends ChatGPT capabilities by allowing the model to retain the context of previous conversations. It’s part of OpenAI’s strategy to evolve ChatGPT into a personal assistant.

Until now, each new chat started a new conversation without any prior knowledge.

Plans for wider availability will be announced at a later date.

OpenAI is reportedly working on two agents for different use cases, as well as on networked GPTs.

According to OpenAI, the memory feature allows ChatGPT to learn the user’s preferences and style, which should further increase efficiency at work.

For example, ChatGPT can now remember users’ preferred general tone, language, or format for blog posts; the preferred programming language and frameworks for coding; or the preferred charts for monthly business meetings.

OpenAI didn’t specify how ChatGPT’s memory works. According to experts, it might use text mining to create a database of facts from previous conversations, which are automatically extracted and incorporated into new responses that match the user’s prompts. This would make it like an extended, automated form of the already available “Custom Instructions”.