And what about a website I want to make public? I'm just concerned about my IP being visible, like for my personal website or my searxng instance

Personally I'd just proxy it through a vm running on hertzer, linode, rackspace, etc

Tailscale Funnel, but might need a paid account

Tailscale's control plane uses Cloudflare.

Thanks, I did not know this. My Tailscale was unaffected by the outage.

I read their point as why have passwords at all when the security is you having access to your email account.

> The backup roll thrusters in use are now at risk due to residue buildup in their fuel lines

Such a human experience this probe is having

In relation to the client (AI Agent), the MCP server is serving resources like tools, but in relation to your platform that hosts the API those tools call, it is a client.

exactly, a proxy has tools but no content.

I had good results with pyannote and the following model for that use case in the past https://huggingface.co/pyannote/speaker-diarization-3.1

I believe their comment was about safety, not usability

Curiously, Scipio is also arguably one of the most famous family names from Roman Antiquity.

https://en.wikipedia.org/wiki/Scipio_Africanus

I share your frustration on services that won’t let you automate them, but to me that’s precisely what generative AI will let you do. You don’t need an API at the family doctors to have AI automate it for you. It just rings them up and sorts it out at your command. AI is like obtaining an API to anything

Walking, cycling, running, driving, relaxing on the couch

This is a large numbers problem that is not yet visible. You can't have everybody walking and talking. There would be too much noise (think crickets, cicadas, toads, etc.)

I'm not going into cycling/running and talking .. that's just not how things work when you need to breathe.

Driving and talking to a phone to then have it recite back to you 10 minutes of details you can just glance at but would be dangerous to?

If I'm relaxing on a couch .. i'm using a device. And please don't come back with "play me a chill song" as a fancy use case.

What I'm trying to say is that voice is not it and the only other kind of interaction I'm looking forward to see evolve is neuralink-style. In the sense that it needs to be wireless / non-invasive for mass adoption. That's it.