I know this is me coming from my spoiled perspective of Linux and macOS, but the advice of running a VM that manages the WiFi hardware and passing it back to the OS seems insane to me
> Instead of continuing with the code, I spawned a fresh Pi session, and asked the agent to write a detailed specification of how the brcmfmac driver works
Planning markdown files are critical for any large LLM task.
Had an experience like this recently. QEMU stopped compiling for old versions of MacOS (pre-13) w/M1 arch, due to it requiring newer SDKs which don't support older MacOS versions. I put Sonnet 4.6 on the case, and it wrote a small patch, compiled and installed it in a matter of minutes, without giving it any instructions other than to look at errors and apply a fix. I definitely would have just given up without the AI.
The future is that people stop buying software and just build it themselves. The spam filter in thunderbird was broken for me, I built my own in hours and it works way better. Oh that CRM doesn’t have the features you want? Build one that does. It will become very easy to built and deploy solutions to many of your own bespoke problems.
a kernel module written entirely by AI, loading into ring 0, that the author admits has known issues and shouldnt be used in production. Were speedrunning the "insecure by default" era.
I feel like ubiquitous hardware support in every OS is going to be a solved problem soon. We're very close to just being able to set an AI coding agent to brute-force a driver for anything. The hardware designer would have to go well out of their way to obfuscate the interface if they really wanted to forbid it, instead of just not bothering to support an OS like BSD or Linux.
Software is still eating the world, now even faster. I wonder how soon we will adapt to this new situation where software is vibe coded for anything and make use of this software without caution as expressed in the article.
For most people the main difference will be: Will it run and solve my problem? Soon we will see malware being put into vibe coded software - who will wants to check every commit for write-only software?
It used an existing implementation, in theory this was mostly a porting task.
GPL-wise, I don't know how much is inspiration vs "based on" would this be, it'd be interesting to compare.
This looks like my Company peers, as long as there is any existing implementation they are pretty confident they can deliver, poor suckers that do the "no one has done it before" first pass don't get any recognition.
To be honest, I find this more impressive, than Claude writing a browser from scratch.
It'd be nice to have drivers for newer Mac's for a better Asahi Linux experience. Good use of AI imo.
> I didn’t write any piece of code there. There are several known issues, which I will task the agent to resolve, eventually. Meanwhile, I strongly advise against using it for anything beyond a studying exercise.
Months of effort and three separate tries to get something kind of working but which is buggy and untested and not recommended for anyone to use, but unfortunately some folks will just read the headline and proclaim that AI has solved programming. "Ubiquitous hardware support in every OS is going to be a solved problem"! Or my favourite: instead of software we will just have the LLM output bespoke code for every single computer interaction.
Actually a great article and well worth reading, just ignore the comments because it's clear a lot of people have just read the headline and are reading their own opinions into it.
Even bigger accomplishment is ai finally figured out how to configure my samba share for guest access! Lol
Your LICENSE file reminds me that the copyright status of LLM-generated code remains absolutely uncharted waters and it's not clear that you can in fact legally license this under ISC
We'll reverse engineer our way out of planned obsolescence
very neat, setting codex on the task of building a mac-compatible app for my Pharos Microsoft GPS-360 Receiver... we'll see how it goes!
Omg!!. Similarly, Do you know a way to interface with BIOS so that it can change the parameters?
> The person intentionally didn't put in much effort.
And it's incredible that they got a somewhat working wifi driver given just how little effort they put in.
I have no doubt that a motivated person with domain knowledge trying to make a robust community driver for unsupported hardware could absolutely accomplish this in a fraction of the time and would be good quality.
This used to be more common right? Back in the winmodem days?
This is exciting! This sounds like a great application because it’s mostly tedious work to adjust an existing driver to another device.
AI didn't write a driver for him. He ported the Linux driver to FreeBSD with some assistance from an LLM.
What's more interesting to me is the licensing situation when this is done. Does the use of an LLM complicate it? Or is it just a derivative work which can be published under the ISC license [1] as well?
*built
Dude is at Grafana, this port is an advertisement stunt:
https://grafana.com/blog/generative-ai-at-grafana-labs-whats...
Don't use it and don't use Grafana.
Now we can have operating systems that write the drivers they need at boot.
An impressively softwarey alternative to simply pulling out the wifi module and replacing it with an AliExpress Apple wifi module adapter board and a compact M.2 WiFi module with a supported chipset :)
That AI was trained on the GPLv2 Linux source code, which does have a driver for your Wi-Fi.
How is this not copyright laundering?
This is really neat, I'm glad it worked.
This is atrocious C code.
The DNS name has both Russian and Indian in it, and its about vibe coding and AI to make system level software which can access the plaintext of my app comms: nope, nope, nope, nope and oh hell no.
[dead]
[dead]
[dead]
[dead]
[flagged]
The Linux community has been doing this since forever. Old hardware is fully supported on Linux, unless of course, you are a macOS fanboy because Apple will do everything to preventing you from owning your hardware, including locking hardware ID via firmware.
This isn't a news to be in here.
The interesting part is not that it built a driver, it is that it built one for a specific chip on a specific OS with no existing example to copy. That is not autocomplete. That is reasoning about hardware registers, kernel interfaces, and driver architecture from documentation and first principles. A year ago this would have been a strong counterexample to AI coding claims. Now it is a blog post.