What about spinning up a thousand agent and let them run wild ? Like many projects are doin

For CRUD, that can work. For something like that, it's almost impossible.

It's niche, performance and code-quality sensitive, needs deep and wide knowledge, and hardware dependent.

Hi, thanks for sharing.

Have you considered using usb-hdmi capture dongle instead of using hdmi-csi. That is my idea, you bring your own capture dongle, plug it in and good to go. The esp32-s3 (and P4 i guess) support usb host, and there is uvc example from esp-idf.

a 1280*720 frame, 16 bit, ping-pong buffer uses only 3.6MB of ram, still plenty of ram left for compression. The Keyboard/mouse component use like 512KB ram at most(even less, HID is cheap).

porting librespot to C using Zephyr RTOS. Mostly vibecode, to see how far LLM can go.

As long as it's not intended for user to plug in, it's fine. Many other vendors also do that.

i thought idevice can receive call/sms as long as they are login with same account? I tested it on my ip13mini, ip7+ and macbook.

The SMS forwarding is handled entirely within iMessage.

Phone call forwarding works when all the devices are nearby, and they can handoff the audio streams between themselves; but you can't pick up a phone call on your Mac if your phone is on the other side of the world/at the office/etc; the feature we're talking about here would not have this limitation.

I think for phone calls this only works on Facetime and for calls maybe only on Wifi.

SMS syncing is true. But if you have a phone and you're out and about you also need mobile data, so would otherwise need a second mobile plan. Or to swap the SIM over, which was easier with a physical SIM, more difficult with eSIMs.

quite a few: Qin has some models. Sometime there are some startup on kickstarter that do small phone. Ikko mind one

Different thing. The claw machine is basically gambling for kids. There is no skill involved.

Here there's no skill involved either. It's not that you have some time to catch as many ducks as possible and if you're good at it you catch more. It's that the 10 € give you the right to catch e.g. 3 ducks, so you spend the time that you need to catch 3 ducks (typically for a 7-year-old like 20 seconds, smaller kids take some more but still not long) and then you look at the score below the ducks, which is totally random. So yeah, quite similar to the claw machine although at least they don't have the farce that you could win an iPhone (Actually you can buy more ducks to get higher scores, so the prizes need to be linear. I have seen parents spend like €50 for their kid to get a toy that could be at most €10).

So instead of talking directly, you talk indirectly through ticket ?

I’m of the feeling that talking directly to these things all day is a path to madness.

They talk to each other, come to consensus, and give me a structured thing to look at that has already been vetted and tested and screenshot evidence and a verification plan. It’s not conversational for me.

Ok, but my problem is that what it builds is not right. It's never right on the first try, or the second or third tries. There's always a ton of incremental corrective feedback needed.

Do you run into this problem? If not, then I need to figure out how to stop running into it myself.

If so, then how do you give it all the incremental corrective feedback without a conversation?

>very disorganized codebases where small changes require major refactoring.

In the vibecode era, this is more common than you thought.

I don't think it's more or less common, pretty much any code base I inherited prior to AI had serious problems.