tommat32

That’s a very fair concern. I completely understand why you’d want to avoid exposing yourself or your clients to that risk.

I also agree that diarization and speaker identification are probably one of the hardest parts to get right if the speakers aren’t separated correctly, even a great summary won’t fix it.

We’re looking into more privacy preserving approaches for MindNote (a multimodal AI Notetaker), including local/on-device processing, so this is really useful feedback. Thanks for sharing your experience!

Thank you so much for the feedback. I am curious to know how you are currently solving it.

Thanks! Still, for an MVP, it’s pretty practical and cheaper than a GPT sub right now. Could’ve been a Ghigli generator or maybe just a wrapper around an image generator, or music (which are quite popular). Still, the idea at a later stage is to use brain-to-text to input information with the mind.

Hey to all, I have an opening for a Lead iOS Engineer - AI notetaking team. If interesting please apply directly through the link or distribute among your network. Looking for someone with previous experience shipping Productivity apps (e.g.Notion, Miro). Salary USD$100,000 - USD$120,000 Remote Worldwide - Hong Kong timezone, UK timezone