Original article excerpt
Server-side extracted preview paragraphs from the original source.
OpenAI says ChatGPT's memory is getting better. But my tests show outdated assumptions, personal profiling, and wrong details that could quietly distort future answers.
According to a blog post released last week, OpenAI seems quite proud of the "improvements" it's made to managing user memories in the chatbot. I'm not sure I like them. In fact, I know I don't. I'm just not sure whether turning the improvements off will make things better or worse.