Monday, May 8, 2023

Issue and capability superprompt

I have not been writing in this blog for a while. I have been collecting thoughts.

I thought I'd start small and get to the point with less prosaics. Saves us both time.

I believe this prompt will too, a little now and much more in the future.

Here I'm asking the large language model to relax it's propensity to answer correctly and engage in a game.

It named this conversation: Issue-Capability Brainstorm Game and the chat starts like this.

User:
Let's play a game of academic paper. I have a piece of paper. It says issue on top and capability at the bottom. What am I missing in between. Assuming I could be all knowing and have methods.

ChatGPT:
Based on the information provided, it seems like you have a game prompt that requires you to fill in the missing content between the "issue" and "capability" labels.

To play this game, you may need to define the specific context or topic you want to explore. For example, if you're interested in exploring a problem within a certain industry or field, you could write the issue as a statement that describes the problem or challenge that needs to be addressed.

Next, you could brainstorm potential capabilities or solutions that could help solve the issue. These capabilities could include methods, tools, technologies, or approaches that could be used to address the problem.

To fill in the missing content, you could then write down a list of possible strategies or solutions that could be used to bridge the gap between the issue and capability. These could include steps or actions that could be taken to implement the identified capabilities and solve the issue at hand.

Overall, this game could be a fun and interactive way to explore different problems and potential solutions within a given context or field.

Here's another:

ChatGPT: Based on the information you have provided, it seems like you are missing a research question or topic for your academic paper. The issue and capability statements provide some context but do not provide a clear direction for your research.

To develop a research question, you could consider the following steps:

1. Identify a broad topic area that you are interested in researching.
2. Conduct a literature review to identify gaps in the existing research on this topic.
3. Refine your topic area based on the literature review and identify a specific research question that you want to answer.
4. Develop a hypothesis or set of hypotheses that you will test through your research.
5. Choose appropriate research methods to collect and analyze data that will help you answer your research question and test your hypotheses.

Once you have a clear research question and methodology, you can begin drafting your academic paper. Your paper should include an introduction that outlines the research question, a literature review that provides context for your study, a methods section that describes how you conducted your research, a results section that presents your findings, and a conclusion that summarizes your research and discusses its implications.

It could be interesting to use prompts like these to load context for problem solving tasks. Just like it works in the data that is used to train the large language model.

Remember, I said no prose. No idea if I kept that promise. Let me know.

No comments:

Tip me if you like what you're reading