AquiGorka

Hi Hacker News!

I found myself asking my AI assistant to help me with some non-trivial tasks (describing visual changes to an app, filling in forms, setting up a server instance in a new provider, changing some dns settings in another one, mostly things I know how to do but that would take me extra time to figure out on an unknown UI). I was solving this by taking screenshots all the time and pasting them, when I got tired of that I just copy&pasted the whole text.

With DesktopVisionMCP, I just ask my AI to "look" and it takes a screenshot on-demand of all my monitors, passes it directly to the AI (no file), so it gets the context instead of me figuring out the best way to describe it and my intent.

I'd like to hear your thoughts and feedback.

It is live on Product Hunt today.

PS, this whole thing was written by me, by hand but proofread using DesktopVisionMCP ;)

A few things I expect to come up:

- Privacy: nothing leaves your device.

- Other options (like Otter or Granola): AudioTap is not cloud-based, recordings are yours as local files (instead of a limited access to the transcripts), no extra non-identifiable data analysis to train anything else, offline first (although use case is online calls) and one-time payment vs subscription.

- It uses stereo channels to identify you (as [Me]) and analyzes voice embeddings to cluster other speakers in the system-audio channel (letting it know how many speakers were in the call significantly improves diarization).

Happy to go deep on any of these.

(edit formatting)

Thank you for letting me know, I’ll update both links asap.

nsa.tech is a domain name I acquired some years ago for fun and I’ve been meaning to use for some time now. I understand that most people know of an agency that uses the acronym but hey! We’ve been thinking “network secure access” around the office ;)

The infra intended here exposes TCP and/or UDP connections, it is protocol agnostic; so end-user apps can use smtp, http, activity pub, at protocol, etc. I am going for an infra that can scale by leveraging the DHT as DNS and p2p for end user apps/apis.

(Edit typo)

I want to build an open protocol for building p2p apps that don't rely on any central servers. For this I'm looking into BitTorrent's DHT for discovery, libp2p for connection and encryption. The idea is that you own your identity, you pick who you trust, and nothing gets stored on servers you don't control. It will work for things like messaging, photo sharing, and private networks where you want real decentralization/federation, not just a blockchain slapped on top of the same old client server model.

I've been enjoying working with LLMs for some weeks now, and realized that as faulty as these can get, asking them to put material in place to learn some resource may be worth my time.

I am looking to learn more about Clojure, I read through it all and was happy that it ends up with examples for an actual api app. I may ask for more in depth lessons as I find more suitable apps to be built.

Sadly no, the feedback loop with users lacked consistency and we never got around finding use cases. One of the visions for it was to help people clean up inboxes, because as you put it, some sources can get pretty spammy. I'll keep an eye out for Cozy Watch, I hope you are successful!

Interesting... the way I workaround'd non-macos-native-sshfs is by using docker and mounting a local folder, do you plan on publishing your tool?

This looks fun! But the fact that the self hosted version lacks support for some core apps is sad, I'd love to be able to build puter apps! Any plans for an app store-like ecosystem?

Some time ago I was building a mitm proxy myself, then I found out about: https://www.mitmproxy.org/ Maybe you already had it in your radar

If you are open to suggestions, libp2p has a good amount of sdks for several languages and you can integrate kademlia for peer discovery

Some years ago, I co-founded a startup that would run workflows when email messages arrived, any email from any source was parsed and it would trigger "actions" that could include notifications - this sounds like a good use case for it! You don't need the service to expose an api to listen in, since most services end up sending email as last fallback.

Mailgun has a free tier for low volume that you can setup on any email client via smtp.

> Some password hashing algorithms have a maximum input size. For example, bcrypt is limited to 72 characters.

Ahh, I was not aware of this limitation, thank you for clarifying. If I sign up for a service that does not allow up to 72 chars does it mean their hashing algorithm is of lower quality?

> Why not train the AI on machine language and have it generate binaries directly?

Maybe that's the answer I was looking for, AI can "interpret" sentences referring to the problems/needs to be solved and it may lack the way to solve for those with the existing programming languages and it could come up with it's own "abstraction" on top of processes - or maybe not, and will plainly speak low-level 0-1s directly.

Sure, but do consider this may be an aside the main question: I (maybe naively) make the distinction that Software Engineering involves a wider range of problem solving that is not limited to programming, and programming is a specific subset of problems in that bigger collection.

That's my hypothesis: _that we have yet to create the "best" programing languages_ we can and I'd expect AI to be able to do so faster than we do.

This is awesome, I am building a visual tool to build frontend workflows, I'd love to talk to you to see where we can match.

A bit late to the game, but this tool allows me to script anything locally: https://www.scriptkit.com/

Oh wow. My hat is off for you. Don't bother with the why's! Doing this for fun should be a good enough reason!

Thank you very much for the rundown of features and your description of the service, I was interested but after reading your comment I'm definitely gonna try it out.

No, I just learned about it today while reading a guide on putting together my own git server and wondered what the opinion was about it - they offer testimonials that make it sound wonderful but what landing page wouldn't do so.

Thank you for sharing this "Extended Mind" concept, it is mind-blowing -> on an arbitrarily contained mind inside a skull to keep collateral damage to a minimum. In the mind experiment of Inga and Otto they use a notebook to extends Otto's mind and claim it is so because "it is constantly and immediately accessible to Otto", can we say the same of the Internet? Does it extend our own minds?

Thank you for sharing. Metastream is very nice! I thought I was following Paul Frazee's blog but I wasn't (updated my feeds now) so, thanks for the link to the `hyperswarm` post too.

Oh wow, I am shocked to see the patent was granted and I'm very interested in understanding the repercussions. These might be big.

> everybody can build up their own decentralized telephone network

Nice. I'm very interested in being able to connect devices in areas where there is no Internet and using a mobile router, like in the mountains or in a bus trip through deserted areas.

Both options work in Mobile Safari.

I'm sorry to hear you could not get it to work, this means I have to improve the flow. I tested this using Chrome and both Android and iOS devices (chrome and safari). The catch is that you gotta point the series of qr codes towards the center of the camera.

I saw you use IPFS in there, are you sure it did not use one of their signalling servers to find the peers?

Hey there, I wasn't aware you had worked on the same thing (and 4 years ago!). Amazing, my hat is off for you.

Did you continue to experiment with it? Improve the experience? Try out different approaches?