Artificial intelligence: Chatbot ChatGPT gets a memory

Artificial intelligence
Chatbot ChatGPT gets a memory

ChatGPT should have a memory function. photo

© Frank Rumpenhorst/dpa

ChatGPT users should be able to recognize each other in the future. The memory function is intended to make the chatbot more useful.

The chatbot ChatGPT should be able to remember information about its users in the future. The function will initially be tested in a small group. This allows software to remember, for example, that you have a daughter who likes jellyfish – or in which format you prefer to receive summaries of meetings at work, explained the developer company OpenAI. For example, if you ask ChatGPT to design a birthday card for your child, a jellyfish with a party hat could be in the picture.

In order for ChatGPT to remember information about users in the future, they must ask the chatbot to do so in the first execution of the function. You can also query what the software knows about you – and delete all or individual information. The memory function is intended to make the chatbot more useful. There are temporary chats for conversations without personalization. The information from this will not be used for further training of the software.

ChatGPT is the AI ​​chatbot that triggered the hype about artificial intelligence a year ago with expectations ranging from a digital land of milk and honey for everyone to the fear of humanity being wiped out. AI chatbots like ChatGPT are trained with huge amounts of information and can formulate texts at the linguistic level of a human. The principle behind this is that they estimate, word by word, how a sentence should continue. A disadvantage of this is that the software can give completely wrong answers, even if it was only based on correct information.

dpa

source site-5