Clement

Much better than One UI

M1 chip indeed the Biggest leap in tech industry The chip that changed the whole laptop industry …… Hands Down

Ok in practice, M5 Max NPU is 2x faster than Panther Lake NPU in Parakeet v3

Samsung has copied a video editing feature from iPhone. The background blur/bokeh effect can be adjusted after shooting a Portrait video. It works better on the iPhones, Hopefully samsung catches up. Full video : youtu.be/NVOL2XFqxXA

Apple accidentally built the world's largest hearing aid company. AirPods Pro 2 got FDA clearance as a clinical-grade over-the-counter hearing aid in September 2024. The average American pays $4,700 for a pair of prescription hearing aids. AirPods Pro cost $249. That's a 95% price reduction for mild to moderate hearing loss, which covers roughly 30 million American adults. But the price gap isn't even the real story. The real story is the stigma math. Nearly 1 in 5 adults over 40 believe society judges people who wear hearing aids. The average person waits 4 years after noticing hearing loss before doing anything about it. A 78-year-old man threw away his hearing aids, popped in AirPods, and his niece didn't even register it as a medical device. That's the product working exactly as designed. The hearing aid industry spent decades engineering smaller, more invisible devices to reduce stigma. Apple solved the problem from the opposite direction: make everyone wear something in their ears first, then add the medical function later. By the time the FDA cleared the software update, a billion people were already wearing the hardware. The clinical study that earned the clearance enrolled 118 people. Self-fitted AirPods matched professionally fitted devices on perceived benefit, amplification, and speech comprehension scores. The audiologist appointment, the $200 fitting fee, the three follow-up visits bundled into that $4,700 price tag: optional. Every hearing aid company spent the last century trying to make their product disappear. Apple made theirs a status symbol and added hearing restoration as a software update.

Wow! CUDA IS NOW WORKING IN MAC! Got 127 Tokens per second running Qwen3.5 35B. Magic!

MLX + TurboQuant + Apple's M5 Max = 🔥 Some more details for you on the @Prince_Canuma MLX port of TurboQuant running on Apple's M5 Max. Rather than convert a PDF to text and then process it, I loaded the PDF (arxiv.org/pdf/2603.06728) as 150 dpi images. 20 pages at bf16 uses 1.33 GB; however, using TurboQuant at 2.5-bit, it's only 229 MB. The document in this form is 42k tokens. Building the cache (normally the pre-load) takes 18.2 seconds, this is a one-off if we're processing the same document. However, we can save the cache and re-load it next time. For 230 MB, it takes 23 ms to load the entire quantised cache of the entire document. Working with a quantised cache is slower than "raw" (bf16). TTFT with the 160 MB TurboQuantised cache is 250 ms against around 130 ms for the 1.3 GB bf16 cache. Similarly, and more significantly, the generation speed is down to 29 tok/sec from 80 tok/sec with an un-quantised cache (using an 8-bit quantised model). What's amazing about processing the document visually is that you can query the images AND the text. You can ask questions about images and graphs and get a response in a few seconds across the entire document. You can pre-process your documents and save them as KV-caches and load them in a fraction of a second. Pick the document and query it. Load from disk, and first token in less than half a second. The video represents queries on the PDF above, on the left, demo query UI on the right. When mlx-vlm is updated for the TurboQuant I will push the code for the demo. Remember, this is the worst this is ever going to be.

Gemma 4 by @GoogleDeepMind is here! Day-0 Apple Silicon support 🍎 Specs: 👀 All are VLMs 🧠 31B / 26B A4B for complex tasks 📱 E2B / E4B for edge (with audio support) 🔧 Base + IT checkpoints mlx-vlm & mlx-lm releases incoming... 🚀

There is not a single fucking reason to buy anything other than a Mac Mini after this

@4k_isn Wow

@Michael_Urwin @app_settings Am just ahed

@app_settings This is where I’m at.

it’s been over 6 months and 200 cycles since i got my iPhone 17 Pro and it’s still at 100% battery health lol this is pretty wild, especially when you consider the fact that i’ve only ever used MagSafe to charge it 👀

Show your battery cycle count Mine iphone 15 1116 cycles almost 3 years 82% battery 🔋 health Not bad in my opinion considering i plugged in night fully with Samsung mac and one-plus chargers almost all days to 100 %

@app_settings 1116 cycles 82 health not bad at all

Galaxy S26 Ultra vs iphone 17pro camera comparison 📸

In a actual 4K video streaming test, the iPhone 17 Pro Max beat the S26 Ultra by a huge margin. iPhone 17PM: 20h 10m Galaxy S26U: 14h 39m

This was the moment I knew that iOS 26.4 was going to beat every Android OS version out there 😍 Just look at the incredible detail used with Depth and Parallax Effecton on the lockscreen!

@Dratuna_ @billiongjgly Tsunami

@billiongjgly One is a light flush. The other is a heavy flush.

What's the difference between these two buttons?

Here’s why even M1 is a beast Macbook neo A18 pro vs MacBook Air M1 4k 422 10 bit footage shot on Sony FX3 edited in 4k time line both playback timeline smoothly What shocking is the rendering times 1 hr 10 m for A18 pro vs 6 m 20 sec for M1 Crazy

@vibeonX69 Windows

What’s the first thing you change after installing Windows?

Why non one talking about this beast *Huawei Pura 80 Ultra The zoom of this thing is just impressive even better than vivo or Xiaomi