[hosh]

Not if you can condense the LLM into being able to run on the embedded hardware.

Article aside, reducing energy use for models is one of the research areas for TinyML.

[calibas]

I'm skeptical that an LLM with billions of parameters can be compressed down into something that runs on embedded hardware and still remain useful.

[bckr]

Skeptical you should be, but I’m optimistic. We have papers showing that knowledge in these models can be edited and deleted. Sam Altman makes the point that too much compute is being spent on using the LLM as a database.

Thinking about how few things any of these CUIs need to know about, I’m optimistic that we can distill them down to a workable size while maintaining the LLM magic.

“Fridge, what is the meaning of life?”

‘Sorry, I don’t know about that. Ask me something about what’s in your fridge.’

“Okay how many eggs do I have.”

“I see 3 eggs.”

When I can have that conversation by proxy through my phone’s onboard CUI while at the store, I’m going to get a lot of value out of that.