1. The Raw Idea (Written in 2 minutes, Zero LLM Assistance) "I think that using LLMs is a way of clarifying what you think and getting some facts (real or hallucinated) but I make the hypothesis that LLMs are not good to enhance your creativity when (your creativity) is working at full power. So I think that you should/could get some time apart (far from) from LLMs to enhace deep thinking and allow your creativity to flourish. This is my initial post and idea (composed in two minutes) and now here is the 'enhanced by LLM' (grammar, spelling and others). So LLM put this post in good shape."
2. The Maturation of the IdeaAfter feeding this raw spark into a chat with an LLM, the idea evolved. We moved from a simple suggestion about "deep work" to a more aggressive, value-based observation: Creativity is a game where the only prizes worth winning are high-potential outliers. The "trap" (la trampa) is that LLMs are built on statistical probability. They don’t just "polish" your thoughts; they regress them to the mean. If you have the capacity for high-level creative output, using an LLM while at "full power" is a strategic error. You are trading your unique "Alpha"—the treasure of your creativity—for a polished, low-value "Beta." To win the creativity game, you must protect your "outlier" thoughts from being averaged out. 3. The Final "Enhanced" Version: Escaping the LLM Trap The Hypothesis: Average is a Failure State
Creativity is the pursuit of high-potential ideas. If you want to take full advantage of your creative power (in case you have any), you must recognize the LLM for what it is: a statistical anchor. It is excellent for clarifying muddled thoughts or retrieving data, but it is a value-killer for breakthroughs. The Strategy: Cognitive Isolation By smoothing over the "jagged edges" of your initial thoughts, LLMs eliminate the very friction where innovation happens. To allow your "Alpha" to flourish, you need intentional, "analog" isolation. You must develop the spark before the model has a chance to turn it into a high-quality mediocrity. The Vision I am considering exploring this further—perhaps through a group or a space dedicated to "escaping the trap" and protecting human "Alpha" from the generative average. I’m curious if there is room for a project or community that prioritizes this kind of unassisted "Proof of Human Thought." |
https://en.wikipedia.org/wiki/Kitsunetsuki
and last December got serious about it in terms of character acting and found Copilot was initially very helpful. So that’s an example of using an LLM for something really unusual and creative.
The really important developments happened as a result of interacting with people though and “foxwork” turned into “foxography”.
It’s gotten to be less fun to talk about it with Copilot as it fits everything into a schema and doesn’t seem to mirror my emotional highs and lows. It is still thrilling to talk to another LLM about it because most of them seem to think it is a good idea.