Re:AI's Jurassic Park Moment, a real and imminent threat to ...
by Molomby on Wednesday December 21, 2022 @02:11AM
(#34077585)
Keep in mind that...
> The model is able to reference up to approximately 3000 words (or 4000 tokens) from the current conversation - any information beyond that is not stored. (https://help.openai.com/en/articles/6787051-does-chatgpt-rem...)
So if you overflow that it'll loose context.
When I talk about coaching I meant that I told ChatGPT to answer only with questions. In a way, ChatGPT is good at having socratic conversations. Sometimes it gets out of character but it depends mostly on your answers or questions.