On the machine learning side of AI, they have CoreML. You can drag-and-drop images into Xcode to train an image classifier. And run the models on device, so if solar flares destroy the cell phone network and terrorists bomb all the data centers, your phone could still tell you if it's a hot dog or not. https://developer.apple.com/machine-learning/ https://developer.apple.com/machine-learning/core-ml/... - Source: Hacker News / 3 months ago

Apple has actually created ML chipsets, so AI can be executed natively, on-device. https://developer.apple.com/machine-learning/. - Source: Hacker News / 5 months ago

For your reference, Apple's pages for Machine Learning for Developers and for their research. The Apple Neural Engine was custom designed to work better with their proprietary machine learning programs -- and they've been opening up access to developers by extending support / compatibility for TensorFlow and PyTorch. They've also got CoreML, CreateML, and various APIs they are making to allow more use of their... Source: about 1 year ago

> It’d be one thing if Apple actually worked on AI softwares a bit and made it readily available to developers. * Apple Silicon CPUs have a Neural Engine specifically made for fast ML-inference * Apple supports PyTorch (https://developer.apple.com/metal/pytorch/) * Apple has its own easily accessible machine-learning framework called Core-ML (https://developer.apple.com/machine-learning/) So it would be inaccurate... - Source: Hacker News / about 1 year ago

This is the developer documentation where they advertise the APIs - https://developer.apple.com/machine-learning/. Source: over 2 years ago

This is a good place to mention https://nuitka.net/ which aims to compile python programs into standalone binaries. - Source: Hacker News / about 1 month ago

For Python, you could make a proper deployment binary using Nuitka (in standalone mode – avoid onefile mode for this). I'm not pretending it's as easy as building a Go executable: you may have to do some manual hacking for more unusual unusual packages, and I don't think you can cross compile. I think a key element you're getting at is that Go executables have very few dependencies on OS packages, but with Python... - Source: Hacker News / about 2 months ago

There is already an AOT compiler for Python: Nuitka[0]. But I don't think it's much faster. And then there is mypyc[1] which uses mypy's static type annotations but is only slightly faster. And various other compilers like Numba and Cython that work with specialized dialects of Python to achieve better results, but then it's not quite Python anymore. [0] https://nuitka.net/ [1] - Source: Hacker News / 5 months ago

Nuitka deals pretty well with those in general: https://nuitka.net/. - Source: Hacker News / 10 months ago

Have a look at Nuitka, which is a "real" Python compiler into C. It uses CPython in its backend and should be completely compatible to "regular" Python. The compiled code can, but does not have to improve performance. It's probably worth looking into. Source: about 1 year ago