I also wonder how small a LLM trained on catching only subject (e.g. living room) and action (light on) from text input could be compared to needle - the json wrapping could be done afterwards using templates.
I also wonder how small a LLM trained on catching only subject (e.g. living room) and action (light on) from text input could be compared to needle - the json wrapping could be done afterwards using templates.
The problem is the target device, an LLM can't run on an average TV well.