I'm late, but the model can remember 4000 tokens, which according to openai is about 3000 words
Pretty GUI, feels awful to use. Maybe client side reactions with corrections would be better?
pipe yt-dlp into ffmpeg, set encoding setting such that it produces an output file small enough to fit onto storage or external storage
I'm late, but the model can remember 4000 tokens, which according to openai is about 3000 words
Pretty GUI, feels awful to use. Maybe client side reactions with corrections would be better?
pipe yt-dlp into ffmpeg, set encoding setting such that it produces an output file small enough to fit onto storage or external storage