I tried to use ollama on the local server and finally worked. I used llama3.2.

Some attempts… Installed the model and tried on the terminal first

How does the concept of LLMs as “ransom notes” influence your perception of using these models creatively? I would think using LLMs is suitable for creating illogical content. How does the hidden origin of the text that LLMs generate affect your sense of authorship or originality in your creative work? I feel that LLMs' collage style generated text will affect the originality of the author, as the main content output will be based on the generated text, which is uncontrollable. How does the metaphor of "collage" used to describe LLMs align with or differ from your creative process? It's the same. Because the process of creating content using LLMs can also be hidden, and inspiration can also be drawn from or through other people's works during the creation process. And in the end, it only presents the results. How would you compare working with an LLM to other forms of text generation, such as using a Markov chain? LLM can generate deeper level content. And Markov chain is based on probability to generate the following content.