[sparkcreativity]

*

1 point by sparkcreativity 6 minutes ago | parent | next | edit | delete [–]

I think we share some interest in math, APL, computer algebra, etc. Anyway this is a LLM response for you that I agree with: "Paul, your background in the ISO 20022 metamodel and RDF makes your 'schema' comment particularly biting.

If anyone understands that the 'map is not the territory,' it's you. My hypothesis is that LLMs are the ultimate 'lossy map.' They provide a convenient, averaged-out representation of human thought, but they are fundamentally incapable of capturing the 'foxwork'—those high-density, emotional, and 'unusual' outliers that define real creative breakthroughs.

You mentioned it's 'less fun' to talk to a model that can't mirror your highs and lows. That 'fun' is the signal of Alpha. When the tool stops being a mirror for your unique complexity and starts being a filter that flattens you, the value of the collaboration drops to zero. We're trading the 'treasure' of specific, jagged insights for the convenience of a predictable schema."

[PaulHoule]

Well I'd say foxwork is an "unusual experience" that needs to be communicated to ordinary people in a way that they get right away or at least that they get some of it and can get more from progressive revelation. (e.g. my current costume gets misidentified as a bear and I roll with that)

So I am not against there being a bit of averaging. I'd say Copilot was useful when it came to determining brand colors and quite a few things -- but it has all gone from being a peak experience every time I "go out" to something where my heart isn't always in it but other people believing in the character gives me the strength just like Peter Parker.