pull down to refresh
101 sats \ 3 replies \ @klk OP 13h \ parent \ on: Gemma 3n models: designed for efficient execution on everyday devices AI
Large Language Models are not suited for ASCII art. They tokenize the input and only generate tokens as output. They lose a lot of spatial information and are not really trained for aligning the characters of the output.
It's similar to painting with a hammer. A very skilled person might do something that resembles art, but a hammer is not really meant for that😂