This is a first-person record of how I took Karpathy's LLM-Wiki intuition and turned it, step by step, into the
llm-skillproject. I'll walk through: where I started, why I chose this particular layering, what each layer solves.
Karpathy's LLM-Wiki throws out one core intuition:
Humans don't get smarter by memorizing "every conversation" — they distill conversations into entries, and next time a similar problem shows up, they look up the entry first.
This is a first-person record of how I took Karpathy's LLM-Wiki intuition and turned it, step by step, into the
llm-skillproject. I'll walk through: where I started, why I chose this particular layering, what each layer solves.
Karpathy's LLM-Wiki throws out one core intuition:
Humans don't get smarter by memorizing "every conversation" — they distill conversations into entries, and next time a similar problem shows up, they look up the entry first.