Often I’ll play dumb and withhold ideas from ChatGPT because I want to know what it thinks. If I give it too many thoughts of mine, it gets stuck in a rut towards my tentative solution. I worry that the memory will bake this problem in.
“I pretend to be dumb when I speak to the robot so it won’t feel like it has to use my ideas, so I can hear the ideas that it comes up with instead” is such a weird, futuristic thing to have to deal with. Neat!
This is actually a common dynamic between humans, especially when there is a status or knowledge imbalance. If you do user interviews, one of the most important skills is not injecting your views into the conversation.
I try to look for one comment like this in every AI post. Because after the applications, the politics, the debates, the stock market —- if you strip all those impacts away, you’re reminded that we have intuitive computers now.
I often run multiple parallel chats and expose it to slightly different amounts of information. Then average the answers in my head to come up with something more reliable.
For coding tasks, I found it helps to feed the GPT-4 answer into another GPT-4 instance and say "review this code step by step, identify any bugs" etc. It can sometimes find its own errors.
In a good RAG system this should be solved by unrelated text not being available in the context. It could actually improve your chats by quickly removing unrelated parts of the conversation.
