Prompting Styles


LLM-based AIs, or large language models, are becoming increasingly prevalent in our daily lives. They are used in a wide range of applications, from chatbots to automated writing and even to the generation of computer code. One of the most interesting aspects of working with these systems is the wide variety of ways in which people choose to interact with them.

There are those who approach LLM-based AIs as if they were colleagues, speaking politely and in full sentences. This approach can be seen as a form of politeness and respect, similar to how we interact with human colleagues. It is based on the assumption that the AI is a sophisticated system that deserves the same level of respect as a human.

On the other hand, there are those who use a different approach, chaining a bunch of keywords together and intuitively ordering them by relevance and desired weights. This approach is based on the assumption that the AI is a machine, and that it can be trained to understand and respond to specific keywords or phrases. This approach is often used by experts in the field, as it allows them to control the behavior of the AI to a greater degree.

Another approach is starting with a hasty random input and refining it after checking the first result. This approach is based on the assumption that the AI is a tool that can be used to generate new ideas and insights. By starting with a random input and refining it based on the AI's responses, one can explore new possibilities and discover new connections.

In conclusion, the way people interact with LLM-based AIs can vary widely, from treating them as colleagues, to controlling them with specific keywords, to using them as tools for generating new ideas. Each approach has its own advantages and disadvantages, and it's up to the individual to decide which approach is best for their particular situation. But one thing is for sure, LLM-based AIs are powerful tools that can be used in a wide range of applications, and the way we interact with them will continue to evolve as our understanding of these systems grows.