I think that's true about Bach's instrumental music, but his big sacred works like his Passions and the Mass in B minor are as "romantic" as the Baroque period gets. Like OP, I think of these works as basically the pinnacle of human artistic achievement. They somehow have all the nuance and complexity you're referring to -- while also telling a deeply emotional story, and just being heart-wrenchingly beautiful even if you don't know the story.
Nvidia's Linux software is first rate -- actually a large amount of the software that would merit buying an Nvidia graphics card is Linux-only anyway. I actually briefly had an AMD card but ended up giving it away since it didn't support ~any of the projects I needed to work on. But YMMV, my anecdata is from a ML engineering perspective.
I can confirm your anecdote, based on messing with ML on a linux system in my personal time over the last few years. I don't do any work in ML, but I have never heard of anyone doing anything with ML on Windows other than maybe running some models locally.
Though I will say I have encountered issues in the past with a Linux gaming computer which experienced issues with the Nvidia drivers anytime I decided to update the distro (I was using Kubuntu at the time).
Not only has Nvidia Linux support been first rate for decades now, but their FreeBSD support is also great. The secret has been that they run the same driver on all platforms with just a shim to interface with the different kernels.
As a happy customer, I picked nanit because it actually worked. We didn’t even use the “smart” features, but “you can turn on the app from anywhere you happen to be and expect the video feed to work” is unfortunately a bar that no competitor I tried could meet. The others were mostly made by non-software companies with outsourced apps that worked maybe 50% of the time.
I wish we could have local-first and e2ee consumer software for this sort of thing, but given the choice of that or actually usable software, I am going to pick the latter.
I self host my "baby monitor" with UniFi Protect on UCG-Max and a G6 Instant wireless camera. It's more work to setup, but pretty easy for a techie. It has the "turn on the app anywhere and it works" feature, and with a 2TB SSD I get a month+ of video storage. Because storage is local, it doesn't need to compress the video and I get a super clear 4K image. And I use Homebridge to expose the camera over Apple HomeKit which is a convenient and a more user friendly way to access it. And HomeKit also gives you out-of-home access with a hub. I love my setup, but I couldn't in good conscience recommend it to a non-techie friend, especially if they're sleep deprived from their infant.
But I do miss the lack of any baby-specific features like sleep tracking. It has support for crying detection, but that's it.
Hah never thought I'd be compared to that legendary comment! It hits home for me because I worked at Dropbox for years. I did at least qualify that I couldn't in good conscience recommend my setup to non-techies :)
If you don't want a baby camera system that's also a part-time hobby...Nanit does seem like the best option. I just lament that the best option requires giving up so much.
Don't worry, I also use Ubiquiti, and self-host Home Assistant on my TrueNAS :)
I have a little server rack cobbled together out of wood under my basement stairs, with a UDM Pro, 24 port POE switch, and an ancient Dell 2U poweredge for TrueNAS.
You joke but wireguard and, very easily, tailscale, solves most crap you normally need to fix. Close everything with ufw and put tailscale, and then you trivially have access from any device / desktop.
I just rely on UniFi and HomeKit for out of home access! But you're so right I could also access remotely via my Wireguard server or Tailscale running on my ubiquiti console... Wish I could hook up baby events like "poop diaper" to Grafana.
Regarding out-of-home access, I'll drop a note about connecting your phone to your home network with a VPN. Now you're always connecting the same way for this and everything else.
It's not perfect because wifi networks might block the VPN, but for the one wifi network I use the most, Wireguard on port 53 works splendidly, for now.
It's pretty cool! But homebridge is another service to run in a Docker container.. so even less user friendly. But it's definitely the primary way everyone that's not me accesses the baby camera. The out-of-home access requires a "HomeKit Hub" which can just be an Apple TV that's always plugged in. And HomeKit also has "HomeKit Secure Video" feature which is cloud based video storage, but with E2EE. But don't recommend their video storage really.
I have a bunch of cameras from various vendors, some with open FW, some with their original FW, all cut off from the internet. They used to be connected to Frigate but due to performance issues I offloaded the work to Scrypted on a RPi and an AppleTV and the setup works great. It was easy to set up and it's easier to use than any other app, assuming you are into the Apple Home ecosystem.
It's not really self hosted since it relies on Apple but it's the least evil at this point. Giving unencrypted video and audio to some company (if what OP says is right) would be way beyond my risk tolerance point.
I have a smarthome setup I built myself using Lua and a Raspberry Pi. Anything it can do locally can be securely exposed on the internet via a service like netbird , which I use for free and is literally a command to get running, or tail-scale which I believe is harder to use. I don’t have video but I think that would work in that scenario as well.
I used to use the docker + homebridge route but it became tedious to maintain.
Instead, I connected it via the Google Home integration (requires an Insights plan) and then use my existing Starling Home hub to access it via HomeKit. This seems to be more reliable and less work than before.
Alternatively you can setup a vpn with rules that automatically enable vpn when you try to connect to specific addresses. Works with Tailscale and on-demand VPN for me. This will work with any IP webcam.
I unfortunately did spring for a Nanit, but am keen to stop paying the subscription... any pointers of a resource you'd encourage me to look at to try to the same thing you did?
and the camera has a standard 1/4" female thread mount, so also a stand to hold the camera. And in the UniFi protect setting enable "Hallway Mode" to rotate it 90 degrees to get the length of baby.
- For a Unifi Protect console (basically an NVR), there's lots of other options too. The one I linked I also use as my Network controller and wifi gateway. I assume it's possible to just use it as a Protect server/NVR (but I also recommend Unifi Wifi)
- The G6 camera, since its meant for normal security uses, is wide by default. But I like it flipped 90 degrees for baby monitoring. Just find the advanced setting that lets you enabled "Hallway Mode" and it flips it 90 degrees so you a tall skinny screen
- Also, to save money, you can get an UCG-Max (linked above) without an SSD, then just install your own nvme SSD. Can get a semi-cheap one since you don't really need super high write and read speeds. But decent endurance would be good.
- I also use the 'privacy area' feature to black out areas in my camera that aren't baby. That way I make sure I'm not recording anything else, and it makes the video storage more efficient.
- You can run Tailscale on the UCG-Max which is another way to enable out-of-home access if you don't want to enable Ubiquiti's cloud services: https://github.com/SierraSoftworks/tailscale-udm
I've been exploring this! Have tried Frigate and SCrypted. With their API it's easy to connect the camera to anything. Haven't got any useful AI models running. What I'd love is sleep tracking.
What competitor have you actually tried? My girlfriend’s parents have a few cheap TPlink solar powered CCTV and they work flawlessly since setup. I used to jerryrig an Android phone for Alfred and that too worked well.
I tried a high end Philips one and a Nest camera. Both were way less reliable than the Nanit. Possibly because they didn’t play nicely with my mesh WiFi at home. But regardless I just wanted to vouch for Nanit’s software, whatever they are doing with their networking and UX is really good.
Their networking is awful in my experience. The WiFi chip is cheap crap, extremely sensitive, cuts out a lot, and doesn’t support WPA3.
I had to set up a dedicated Nanit-only AP in my house in order to stabilize the connection. It would not work any other way, tried many different configurations, even other APs.
They've mostly sold off bits of themselves, and/or licensed their name to other producers. It's highly unlikely that Philips actually made that camera.
My £15 TP-Link camera that we use as a baby monitor works 100% of the time. I can use it completely locally too with nothing sent to their servers at all, or use it through the internet if I want to. Got 4+ years of continuous use and counting, with zero issues.
I have 2 free-roaming rabbits in one room of the house, we've been using Eufy camera to access live feed and found no issues with it, definitely would buy again. And the SD card recording allows us to seek a couple days into the past - it is pretty fun to watch the rabbits scramble to the automatic feeder at the set time.
> you can turn on the app from anywhere you happen to be and expect the video feed to work
if i'm understanding "anywhere you happen to be" right: Real question -- I'm not a parent. What is your use case for wanting to monitor your baby remotely from a different location than your baby? Obviously someone is with them at the house or location with the baby! You don't trust em? Or just like seeing/hearing your baby when you are out?
I see why a baby monitor in general is helpful so you can be in another room in the house and still keep an eye/ear on baby, but obv someone has to actually be in the location with the baby! (and the monitor at least needs to be on the wifi, right? So the monitor is in a place you have network access to, yes?)
It's a reasonable question! I'm past the baby monitor stage now, but when we used our Nanit from a different network it was for things like:
* Doing garage or yard work where Wifi coverage was spotty. May seem like an edge case but remember that when baby is sleeping is exactly when you want to be doing things like yard work.
* Hanging out across the street cooking out with the neighbors while baby sleeps
* Having a couple drinks at the hotel bar on vacation after baby goes to sleep. You're only ~30 seconds from your room if baby wakes up, but it's nice to not have to sit in a dark room for the whole evening after 7pm.
- I'm at a small party 1 block away. Baby is sleeping in the bedroom with mama but I'm trying to protect her sleep. I listen to baby with an airpod in my ear at the party. If baby shows signs of waking I come back and either bottle him or help mama feed him.
Also just because I'm out of the house and miss my baby and want to stare at him...
The vtech camera is working well enough for me for what it’s worth. But any such app solution generally implies transfer through the company’s servers.
Yeah that’s fair, we had one of those too which absolutely did everything it advertised. The nanit is a different product that doubles as a home camera that lets you monitor your home while you’re away. Its software/networking is impressively reliable.
I don't think it's just safeguards; they really don't seem to understand pitch at all. I tried asking ChatGPT's advanced voice mode to recognize a tune I was humming, and it insisted it was Beethoven's 5th -- multiple times. I think it must have basically tokenized my humming to "dun dun dun duuun".
advanced voice mode operates on audio tokens directly, it doesn't transcribe them into "text tokens" as an intermediate step like the original version of voice mode did.
we don't know if that's due to inherent limitations of the tokenisation of audio, or a byproduct of reinforcement learning. In my own usage, I noticed a significant degradation in capabilities over time from when they initially released advanced voice mode. The model used to be able to sing, whisper, imitate sounds and tone just fine, but I imagine this was not intended and has subsequently been stunted via reinforcement learning.
I don't find the articles argument that this is due to tokenisation convincing.
> This is likely because they’re trained on a lot of data generated synthetically with text-to-speech and/or because understanding the tone of the voice (apparently) doesn’t help the models make more accurate predictions.
right, but either whatever audio tokenization it's doing doesn't seem to encode pitch, or there's ~nothing where pitch is relevant in the training set.
That sounds great. How well does the base OS + "pet" containers work with all the crazy dependencies you need to do modern ML work, e.g. some exact combination of nvidia drivers + CUDA + torch + other random stuff? That's the pain point I'd be motivated enough to solve that I'd switch distros.
Your "pet" containers basically become your traditional OS, in a way. They use filesystem overlays, so your container can see all of the files on your system, plus it's own layered files, ie. each container has it's own "view" of the filesystem.
You can install anything inside your "pet" containers that you would normally install on your actual system. The container keeps everything tidy and self-contained. I have a container for development, another for music/DAW, another for certain games that needed weird deps.
Fedora Kinoite/Silverblue come with `Toolbx`[1] preinstalled, but I found `distrobox`[2] to be more flexible for my needs. I layered distrobox onto my base image, and it just works.
Many GUI apps are available via Flatpaks, and can be installed directly or via the Software Center. You can enable Flathub[3] as a source, so there's a ton of available software, including Steam, Chrome, Firefox, Discord, Spotify and more. Flatpaks are also sandboxed and self-contained, so they can't pollute/break your system either.
Some forms of kernel anticheat make dual booting harder, too. I can’t play valorant since that version of Vanguard requires secure boot, which doesn’t seem to work with my dual boot setup unless I invest more time fiddling than I care to. Easier just not to play that game.
