Date: Tue, 10 Mar 2026 20:33:32 +0100 From: Vladimir Varankin <vladimir@varank.in> To: freebsd-wireless@freebsd.org Subject: Rebuilding brcmfmac Wi-Fi driver with the help of AI Message-ID: <CAGLqCM=55k2j%2B_-pH7Sdh2SevXyrr6GF3yMaSD_RJMXSfxaz3Q@mail.gmail.com>
index | next in thread | raw e-mail
[-- Attachment #1 --] I recently wrote a blog post [1] sharing my experience of rebuilding a Wi-Fi driver for BCM4350 for FreeBSD with the help of agenting AI tooling. I'm aware that different groups of people have different opinions about the topic of using AI in software development. Still I think this was a fairly interesting experiment, and I'm curious to hear the opinion on the approach and the results, from people close to in-tree drivers development. The GitHub repository [2] includes documentation about the testing approach, recorded decisions and know issues (which I'm — still with the help of AI agents — addressing in my spare time). P.S. Just to be absolute clear: I'm not proposing or suggesting to upstream the code of this driver. Neither do I think that in the current state the AIs can vibe-code something reliable in one go. But I do think, the tooling can be a huge multiplier for building, testing, explaining, reviewing, etc large bodies of complex code. Cheers, V. [1]: https://vladimir.varank.in/notes/2026/02/freebsd-brcmfmac/ [2]: https://github.com/narqo/freebsd-brcmfmac -- Vladimir Varankin vladimir@varank.in [-- Attachment #2 --] <div dir="ltr"><div></div><div>I recently wrote a blog post [1] sharing my experience of rebuilding<br>a Wi-Fi driver for BCM4350 for FreeBSD with the help of agenting AI<br>tooling.<br><br>I'm aware that different groups of people have different opinions about<br>the topic of using AI in software development. Still I think this was<br>a fairly interesting experiment, and I'm curious to hear the opinion<br>on the approach and the results, from people close to in-tree drivers<br>development.<br><br>The GitHub repository [2] includes documentation about the testing<br>approach, recorded decisions and know issues (which I'm — still with<br>the help of AI agents — addressing in my spare time).<br><br>P.S. Just to be absolute clear: I'm not proposing or suggesting to<br>upstream the code of this driver. Neither do I think that in the current</div><div>state the AIs can vibe-code something reliable in one go. But I do think,<br>the tooling can be a huge multiplier for building, testing, explaining,<br>reviewing, etc large bodies of complex code.<br><br>Cheers,</div><div>V.<br><br>[1]: <a href="https://vladimir.varank.in/notes/2026/02/freebsd-brcmfmac/">https://vladimir.varank.in/notes/2026/02/freebsd-brcmfmac/</a><br>[2]: <a href="https://github.com/narqo/freebsd-brcmfmac">https://github.com/narqo/freebsd-brcmfmac</a><br><br clear="all"></div><span class="gmail_signature_prefix">-- </span><br><div dir="ltr" class="gmail_signature" data-smartmail="gmail_signature"><div dir="ltr"><div style="font-size:12.8px">Vladimir Varankin</div><div style="font-size:12.8px"><a href="mailto:vladimir@varank.in" target="_blank">vladimir@varank.in</a></div></div></div></div>home | help
Want to link to this message? Use this
URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?CAGLqCM=55k2j%2B_-pH7Sdh2SevXyrr6GF3yMaSD_RJMXSfxaz3Q>