Sometimes it's good to remind yourself what a staggering achievement the new M6 Mac mini is. Not only is it affordable, but it packs an enormous amount of power into a tiny package, especially with Apple Silicon's ability to run AI models locally. If there's a wrinkle, it's that the Mac mini now starts at 899, pushing its price much higher than what we're used to. It got me thinking that Apple could really do with making a new, low-cost desktop Mac that could fill the space vacated by the mini's ever-increasing price. It should make a Mac Neo.

When you purchase through links in our articles, we may earn a small commission. Windows malware numbers look awful next to macOS. A recent numbers dump from Surfshark suggests a massive danger to PCs--but I'm not sweating it after digging into the numbers. And a recent blog post just made arguing with them more annoying. Back in mid-August, security software maker Surfshark released its look at its threat detection numbers from January through July 2026.

Breakthroughs, discoveries, and DIY tips sent every weekday. Sinking feelings don't come much worse than when you think you delete something you really need. Many of us now have files synced to the cloud from our phones and laptops, but sometimes data can disappear from there too--maybe through a click of the wrong button or a swipe across the wrong menu option. If this happens to you, don't lose hope-most cloud storage services come with a deleted file restore function that's similar to the Recycle Bin on Windows and the Trash folder on macOS. It means that any files that you delete, deliberately or not, can be recovered without too much fuss.

On-device inference offers privacy, offline use, and instant response, but consumer hardware restricts large language models (LLMs) to low throughput and capability. To overcome this challenge, we present prima.cpp, a distributed on-device inference system that runs 30-70B LLMs on consumer home clusters with mixed CPUs/GPUs, insufficient RAM/VRAM, slow disks, Wi-Fi links, and heterogeneous OSs. We introduce pipelined-ring parallelism (PRP) to overlap disk I/O with compute and communication, and address the prefetch-release conflict in mmap-based offloading. We further propose Halda, a heterogeneity-aware scheduler that co-optimizes per-device CPU/GPU workloads and device selection under RAM/VRAM constraints. On four consumer home devices, a 70B model reaches 674 ms/token TPOT with <6% memory pressure, and a 32B model with speculative decoding achieves 26 tokens/s. Compared with llama.cpp, exo, and dllama, our proposed prima.cpp achieves 5-17x lower TPOT, supports fine-grained model sizes from 8B to 70B, ensures broader cross-OS and quantization compatibility, and remains OOM-free, while also being Wi-Fi tolerant, privacy-preserving, and hardware-independent. The code is available at https://gitee.com/zonghang-li/prima.cpp.

Earlier this week, OpenAI announced that ChatGPT can now be connected to more apps and services, allowing you to pull your data from those sources in real time. Newly connectable sources that were explicitly mentioned include Outlook, Teams, Google Drive, Gmail, and Linear. ChatGPT can now connect to more internal sources & pull in real-time context--keeping existing user-level permissions. These new connections are only available for paid ChatGPT Plus, Pro, Team, Enterprise, and Edu users. Furthermore, the feature is excluded for users in the European Economic Area (EEA), Switzerland, and UK.

Breakthroughs, discoveries, and DIY tips sent every weekday. You've unwrapped your new Mac desktop or laptop and you're ready to dive in: Where should you start? Modern-day macOS is designed to be intuitive and straightforward, but it's also stuffed with options and features you can tweak to fit your needs. Here we'll look at some of the fundamental settings that you should change first, to ensure you're getting the best possible experience. All of these options can be found by opening the Apple menu in the top left corner of the macOS interface, then choosing System Settings.