It could be used to fuel an offline assistant that would be able to easily add an appointment to your calendar, open an app, etc. without #privacy issues.
This has come to reality with this proof of concept using the Phi-2 2.8B transformer model running on /e/OS.
It is slow, so not very usable until we have dedicated chips on SoCs, but works (and #opensource !)
@gael I'd say before that happens, running an LLM on your local network is your best bet. Projects like https://ollama.com/ make that incredibly easy. #llm#ollama
All these actions are so so soooo difficult to do manualy! That's a perfectly reasonable motive to add yet another chip, burn some more ressources, use more energy 🙄 @gael
@gael lots of potential :ablobcatheart: Especially if it can access third party apps so I can say stuff like 'send [filename] to [contact] via [messenger]'
Add comment