arcrwlock·4 miesiące temu·discussWhy not use a struct of arrays?https://en.wikipedia.org/wiki/Data-oriented_design
arcrwlock·w zeszłym roku·discussBecause then you'd be running a full speech to text model all the time, and an LLM any time any speech is detected.
arcrwlock·2 lata temu·discussHow does this interact with DRM? Does ACR still work if HDCP is being used?
https://en.wikipedia.org/wiki/Data-oriented_design