Mashimo

Why are they absurd and meaningless?

Can be art and creative, just like the music.

claude.ai does not run on your local machine though. Evil.com needs to be accessible from the internet.

It's not a questions about if it's possible or not, but if TypeScript makes it easier to do so.

Blog, youtube channel and landing page is kinda sparse when it comes to examples.

And I'm not going to sign up just to test it.

I agree with the other ones, have 20 cached examples or at least some videos that show the process from start to finish.

Nah, I would not do it.

With works for me on Android with Pixel phone, after I added Immich to the list of apps that can work in the background.

But as you can see in the linked release note, they made a lot of change to background sync on Android and iOS. It should (TM) work out of the box now.

> You missed the biggest one: continuity. Start listening to music at home, take it to the car. Start a podcast in the car, finish it in the gym.

That would still work, as you can use Bluetooth.

> Also, anyone know if I can get immich to upload the photos without... Running immich once in a while? Would be great if it just automatically sent them to "my cloud".

See the release note that this HN thread links to ;-)

>>> Background backup improvements Background backup on Android is now significantly more reliable. Previously, the background backup on Android was limited to newly taken photos. Now, the app uses a new periodic task scheduler, which allows you to upload your entire library in the background, and it plays nicer with Android's background execution limits, properly cleans up tasks, and warns you when battery optimization and notification settings might interfere with backups.

On iOS, the background refresh task now runs its sync and upload work in parallel, so uploads actually start within the short time window iOS allows.

The release notes says:

> On iOS, the background refresh task now runs its sync and upload work in parallel, so uploads actually start within the short time window iOS allows.

But I don't know if that fixes your issue.

I don't think that has changed, but AFAIK is on the Roadmap. Or at least they talked about it.

The open source codec opus https://opus-codec.org/comparison/

> Their big money maker is their app store

That said, their AirPods division could be a Fortune 500 on its own.

Further down someone said the support is great and they respond within the day.

> Why would you have to give up vision?

Because you would have to switch model.

You can't just say "Oh, button X looks weird see [screenshot]" while coding with GLM. You would need to switch to another model and then maybe back.

OpenRouter, Z.ai coding plan, OpenCode Go, OpenCode Zen .. and probably more.

Yeah, me neither. Fast enough for me on CPU.

Not for faces, but the CLIP model for the context search https://docs.immich.app/features/searching/

That needs to be in (v)ram for searches.

Who is "The government"?

China or your local one?

Maybe he wants really fast or large AI models inside immich?

(I just run the defaults on my CPU, works for me)

Well we are on HACKER news ;-) To mess around and learn something would be one reason. Maybe you already have the hardware. Why selfhost anything if cloud does the thing?

An other reason would be because your company does not allow any source code leaks and thus every developer either has local models or none.

6 T/second local model while your colleagues have 200 EUR/month claude does not make much sense. At least I can't see a use case.

Finally hacker news on .. Hacker News. No need for it to be economical cheap.

I'm also a heavy SwiftKey user, but donated some money to futo last year in hopes they improve the keyboard.

SwiftKey got annoying with pushing Ai image Gen and sometimes pop-ups.

Why would you use this when your company has access to actual SOTA? I don't get it.

Run one task, while you do another? Or while you sleep / eat / rave?

I used GLM (4.7, 5 and 5.1) both through their coding plan and now through OpenCode zen. Both where painless to get.

Inhouse talent

I have used GLM since version 4.8 I think and do enjoy using them. More then other models like Kimi or Deepseek. Though only tested them on smaller private projects.

Immich can do part of this. For photos it does lm object detection and ocr for text. I think for video is currently only the first frame. It also has face / people detection.

And once set up it's easy to use even for non technical people.

Could be, but AFAIK it was similar with other glm releases. Just a Twitter post with blog post coming later.

In most EU countries you have to take a break after 4.5 hours for about 45 minutes. And you can only drive 9h per day.

Sounds feasible to me.