Hacker News new | past | comments | ask | show | jobs | submit

Inside the M4 Apple Neural Engine, Part 1: Reverse Engineering

https://maderix.substack.com/p/inside-the-m4-apple-neural-engine
196zdw | | 53 | HN
LatencyKills | parent | next
I worked on the Xcode team for years and know the lengths Apple goes to make this stuff difficult to figure out.

I just wanted to say that you’ve done an excellent job and am looking forward to the 3rd installment.

loading story #47221548
Octoth0rpe | parent | next
Part 2 has benchmarks: https://maderix.substack.com/p/inside-the-m4-apple-neural-en...

6.6 FLOPS/W, plus the ability to completely turn off when not in use, so 0W at idle.

behnamoh | parent | next
It's insane that the source code of ANE is not available even to the MLX team, possibly one of the reasons Awni (MLX project head) left Apple.
mathisfun123 | parent
Tell me you've never worked at a hardware company without telling me lololol
loading story #47220186
loading story #47223093
loading story #47223102
mattlangston | parent | next
The future is bright for software engineers.

The big takeaway isn't reverse engineering the ANE per se, but what Manjeet could do with his software engineering skills when accelerated by AI.

This is a good example of the present state of software engineering. Not future state - present state.

loading story #47222323
GeekyBear | parent | next
The recent news is that Apple is supposedly replacing the Core ML framework with an updated version that will make it easier to integrate third party LLMs into your apps.

> the company is also planning a few other software-based AI upgrades, including a new framework called Core AI. The idea is to replace the long-existing Core ML with something a bit more modern.

https://www.bloomberg.com/news/newsletters/2026-03-01/apple-...

eleventyseven | parent | next
> Throughout this series, “we” refers to maderix (human) and Claude Opus 4.6 (by Anthropic) working as a pair. The reverse engineering, benchmarking, and training code were developed collaboratively

Sure, "collaboratively." Why would I ever trust a vibe coded analysis? How do I, a non expert in this niche, know that Opus isn't pulling a fast one on both of us? LLMs write convincing bullshit that even fools experts. Have you manually verified each fact in this piece? I doubt it. Thanks for the disclaimer, it saved me from having to read it.

Anonbrit | parent | next
Humans also write endless amounts of convincing bullshit, and have done since time immemorial. False papers and faked results have been a growing scourge in academia before LLMs were a thing, and that's just counting the intentional fraud - the reproducibility crisis in science, especially medical and psychological science, affects even the best designed and well intentioned of studies.

Humans also make mistakes and assumptions while reverse engineering, so it will always need more engineers to go through the results, test things

withinboredom | parent
Claude likes to hide bad benchmarks from you, so it will show you where you are clearly winning. You even see some weird benchmarks in the article.
giancarlostoro | parent | next
Reverse Engineering with AI is only going to get better. I have seen some crazy things friends of mine have done with Claude alone. Let's just says SaaS isn't the only industry that could one day suffer.
love2read | parent | next
This article was clearly written by a human (and AI) but still has a few "LLMisms" such as:

- The key insight - [CoreML] doesn't XXX. It YYY.

With that being said, this is a highly informative article that I enjoyed thoroughly! :)

The article links to their own Github repo: https://github.com/maderix/ANE

walthamstow | parent | next
We've got about a year before so many people are interacting with LLMs on a daily basis that its style starts to reverse infect human speech and writing
loading story #47221007
loading story #47219162
loading story #47218998
rafram | parent
Also the Prior Art section, which has telltale repetition of useless verbs like "documenting," "providing insight into," and "confirming" on each line. This was definitely AI-written, at least in part.
mayhemducks | parent | next
I never realized just how much hardware engineering Apple dedicated to enabling people to type faster with their thumbs!
kamranjon | parent | next
I have always wondered if the neural engine could be used for training - pretty excited for part 3 of this to see if the juice is actually worth the squeeze
loading story #47220955
daoistmonk | parent | next
Tangential: Is anyone doing something similar to accelerate the support matrix of Linux on anything higher than M2?
msie | parent | next
I remember the good old days when Apple was desperate for developers and produced great documentation and there were a lot of great 3rd-party books too. You can't just give out awards in hopes that someone will make that great app.
loading story #47221326
loading story #47222235
poszlem | parent | next
Genuine question, not trying to throw a shade or anything, but are those cores actually useful with the state of apple intelligence being what it is?
rahkiin | parent | next
They are also used by ML models that are deeply integrated in macos and ios without you knowing. Like object and text detection in images.
loading story #47219032
loading story #47219542
dagmx | parent | next
If you strip away the branding, Apple has and continues to ship a ton of algorithms that likely use the ANE and end users can use CoreML to do the same.

Just some things that people will likely take for granted that IIRC Apple have said use the ANE or at least would likely benefit from it: object recognition, subject extraction from images and video, content analysis, ARKit, spam detection, audio transcription.

loading story #47220066
stetrain | parent | next
Apple's OSes run a lot of local ML models for many tasks that aren't branded as Apple Intelligence, and they have done so for many years now.
esafak | parent
You can convert your own ML models to MLX to use them; Apple Intelligence is not the only application.
loading story #47218525
FL33TW00D | parent | next
Unreadable Claude slop