blutfink·12 bulan yang lalu·discussOf course an LLM uses more space internally for a token. But so do humans.My point was that you compared how the LLM represents a token internally versus how “English” transmits a word. That’s a category error.
blutfink·12 bulan yang lalu·discussThe LLM can also “say” “cat” with few bits. Note that the meaning of the word as stored in your brain takes more than 24 bits.
My point was that you compared how the LLM represents a token internally versus how “English” transmits a word. That’s a category error.