If we assume GPT is system 1, can we get it to "develop" a system 2 by asking it the right questions?
- I and others have had success asking it to work step-by-step and talk out loud.
- I've also had success asking it to provide a better answer after it answers.
- I've tried doing a de Bono's Thinking Hats scenario to answer questions.
I think there's some interesting work there to be done, especially regarding "frameworks". Like ask it to use a framework to answer the question. Ask it to use several different frameworks then synthesize a single answer.
The cool thing is, it tends to already know the framework. You don't have to program it in, you just have to ask it to use the framework.
I also don't know if there is any advantage to using multiple chats (that don't share history) to collaborate on an answer vs using a single chat with a single history.
Have you got a mac machine? I can send ya a link to my toy app that lets you edit responses and prompts, save conversations. I’m experimenting with a “strongly typed” conversation where each message is a call/response to itself that we can push along by requesting a new message from the conversation tip each time. Works particularly well when requesting implementations of snippets given a built up conversational context, and then saving each context line to edit and request variants repeatedly z
I’ve enjoyed my time using mindsera.com which has some similar functionality as this. I think it’s remarkable how Mindsera will guide your thinking with pre-programmed frameworks and prompts for the human to follow.