blutfink·12 か月前·議論Of 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 か月前·議論The 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.