Misleading title but this is pretty exciting. Interesting how this is based on llama cpp. Its nice to see some momentum since they released the paper in 2023

Wow I’m a watch guy and this was a fun read. I used a couple of similar apps and they work ok. I wonder how yours stack up. You can get these cheap piezo ones for $150 but unsure how those perform either.

While this article is old, there’s more and more noise that the lay offs is this month. That being said, I can’t help but wonder if the paramount deal accelerated these plans.

A friend was about to start this Monday. Last week Oracle called to rescind their offer

Wow that’s terrible. This is why people don’t give notices anymore. It’s safer to give no notice and start the next job the day of. You burn some bridges but is the safest option.

Awesome guide, shame how a couple of the Qwen leads got kicked out and replaced with more “business” minded leadership. Hopefully this doesn’t mean the end of the open source era from Qwen.

Oh I think on X a few ago: https://x.com/poezhao0605/status/2029151951167078454 - Alibaba's CEO and CTO are having an emergency all hands now! Hope it all goes well!

Interesting how it runs on the A18. I wonder if this means they will try to unify macOS and iOS within this decade.

I think the entirety of the A-series, M-series and even S-series lines are essentially one chip product line, with different balances of chip area, cost, compute and energy use.

Other than that, perhaps some small form factor related device support differences.

Never been an OS (iOS, iPad, watchOS vs. Mac) distinction from the hardware standpoint.

The only thing I read from M-series in iPads and A-series in the Neo, is the A chip is better balanced in price and power draw for a low cost laptop with a smaller battery.

The M-chip with that balance is the A-chip.

I don't think they would; I'm sure they share a lot of the low level code already, the main difference now is in the user interface and software.

Some time ago (...over ten years ago) they made some movements towards unifying the desktop and tablet interfaces with LaunchPad, which looked like it was designed for a touch screen, but they never followed through. Not even touch screens on their laptops, which honestly still surprises me.

Shipping macOS on iPads will near instantly vanish a very large cohort of their macbook users.

I think it's purely a pricing & supply chain thing. Certain iPads have M-series chips in them, now certain MacBooks have A-series chips in them.

Also, the chip used has no impact on the viability of merging macOS and iOS anyway.

Haven't they? I can download iOS apps from the app store, sign them again with my own keys for MacOS, run them natively on my MacBook without any issues. Same binaries, same APIs. It all just works.

From what I've seen people have mostly been asking for Mac OS features on the iPad, not phone apps on the Mac.

The increased compatibility is great and kind of obvious given the switch to ARM, but if it went both ways then the M4 chip in iPads would be a lot less bored.

Seeing as it's the A18, are there any concerns about third-party "desktop" software not running on this new platform?

no? it’s neck and neck with the M1 on benchmarks, plenty of people seem to still love their M1 airs

M1 evolved from the A cpu line.

Why would that mean that, when iPads have had A series and M series chips for ages now?

Hasn’t that been the discussion since the laptops/desktops went arm?

Yeah but macOS has never been ran on a “A” series chip before which makes it all more so interesting.

Technically, the Apple Developer Transition Kit Mac Mini from the Apple Silicon transition (just before the M1 release) ran on an A12Z.

The Developer Transition Kit (DTK) ran on the A12Z chip. I don't think this should be interpreted as a signal of iOS/macOS unification.

It is a given on Windows land, Apple is the one that rather sells two for the price of two.

in a competitive market they would have been unified a long time ago. google has been making slow steps at doing this apple wont until google does

all of apple’s devices with displays down to the watch run OS X with a form factor appropriate UI layer on top. iphone and mac are more unified than google’s android/chromeos

Tahoe made all the touch targets on macOS bigger, we may get a touch macbook pro this year.

I hate how it doesn’t even mention git in the article. That being said, they have a boatload of money. It would be so much h quicker to acquire someone like Gitlab and slap an OpenAI theme on it.

Please don't give them any ideas. The last thing we need is to be pressured to select from 1) GitHub from Microslop, 2) Gitlab with that AI sticker, 3) Self-hosted pain.

Fast.com is from Netflix. They do it so ISP serve Netflix faster since ISP were gaming speed test sites. I’m assuming that’s the same case for cloudflare speed test.

Anyone use the Jolla C2? Seems pretty interesting (not fully European though)

A big part that a lot of local users forget is inference is hard. Maybe you have the wrong temperature. Maybe you have the wrong min P. Maybe you have the wrong template. Maybe the implementation in llama cpp has a bug. Maybe Q4 or even Q8 just won’t compare to BF16. Reality is, there’s so many knobs to LLM inferencing and any can make the experience worse. It’s not always the model’s fault.

I don’t see why people do not use bitwarden. It even supports yubico keys.