Would be curious about legal statement with EU AI Act that kills Bing API (Microsoft switch to Grounding Bing that rephrase the content)
Yes, Ephemeral queries must not retain any data, but there is also other rules, for instance it is forbidden for commercial services (where Ollama have a pricing model ?).
In a nutshell you ask an LLM to summarize the transcript and input some notes to help frame the results that's all ? It could be done with ChatGPT + Notepad ?
Yes it could be fully local, but to do that you need a serious computer and a way to distribute Whisper (on Windows)
FYI I tried something close, but comparing Plaud and Whisper (on Windows) Plaud wins far ahead.
I like the setup, have it in mind for XReal Pro but not convinced.
1. The FoV is limited, it's cool on the go but won't replace my Odyssey Ark 55
2. The CPU/GPU is limited, so why not simply using your Phone + XReal ?
3. All your meeting with Team/Zoom/Meet won't works
So yes if your task are surfing the web, using office app it should works until an AI do your job ;-) But if you are working ... Photoshop, Davinci Resolve, Advanced Coding, 3D Building, ...
I build a 3D TableTop SpaceHulk with W40K 10th minis. Combine with electronics (ESP32 LED and Hologram, Induction, SmartTable...). StoryTell with GenAI.
Each game is recorded into a French Podcast.
I made a kinf of SpaceHulk with the rules of KillTeam and Minis of W40K. The board is 3D Print + Laser cutting + Painting. I add some electronics ESP-32, Holograms, Induction, ... and GenerativeAI for story telling. Then I record with Mevo and DJI Pocket into a Podcast (in French) :-)
Here is a conf I did for GlobalAI where I summarize my work on a side project of SmartMirror using Speech, Computer Vision, IoT, SmartHome, NLP, GPT3 Avatar, Matterport, ...
Yes, Ephemeral queries must not retain any data, but there is also other rules, for instance it is forbidden for commercial services (where Ollama have a pricing model ?).