I made the fingerprint sensor on my Lenovo 14s Yoga work thanks to Claude. It took 30 minutes.
I have been wanting my fingerprint device working too. Did it require a Claude subscription or would the free plan suffice?
Yes, this is what I got excited about upon hearing about the recent Adobe “open sourcing.”
It would be amazing if this could bootstrap RISCV drivers
Or just drivers for existing abandoned but perfectly functional Qualcomm SoCs.
Damn straight, an absolute shitton of Linux phones just waiting to happen…
For all the very real bad things AI is/can be used for. I really would love to see more uses like this. So long as the code generated is made to be easily auditable (clear comments and traceable code) by folks that know how to do it for other projects that have been trying to free as many left to rot devices. Obviously a lot of slop stuff will make things hard for finding the gems, and will be important to treat all things as “too good to be true” until verified.
With the way that companies lock the shit out of modern devices with planned obsolescence. It would be great to repurpose those devices with as much of the hardware being accessible, unlike the current issues with major parts not working (not from lack of trying/caring to be clear). The breakthroughs that humans are able to figure out will still be more impressive, but there is a difference between folks like them clearly stating what parts they used tools to help with (if used at all) vs the no effort vibe-coder crowd. Will be also great if they are able to get results with small focused locally hosted AI instead of everything being on those “bubble” data centers.
If I wanted a virus on my device, I’ll just go to a malware repository rather than trust low quality slopware.
I am not going to defend the unacceptable external costs of LLMs here, namely the environmental destruction and the large-scale rug pull on social contracts for creative people.
But adressing your argument, it is totally possible to rewrite the Claude slop to clean, easy to review software. I guess this would be far less work than to reverse-engineer a driver just from captured USB communication.
(That is just my $0.05, but I think the main problem with AI slop in smaller software is not that the code they generate is completely unreadable, but that the LLM systems tend to break down after a few thousand lines, and that they produce architecturally unsound and often subtly wrong software, which leads to an exponentially increasing amount of technical debt if not continously corrrected by experienced people.)
Good luck finding a malware repository for undocumented proprietary hardware
Reverse engineering is actually a very good use case for LLMs. Its like using a black box to get a different black box to do a trick. It might not be epistemologically sound, but if it can boot the kernel, who cares?
This is the repo that people are using, 270k stars
Yea but you will also install other software like maybe gidhra.
Yep, all in the readme
I would love if someone reverse engineered Logitech drivers and made them better as actual drivers instead of an annoying app
Logitech and Razer have great open-source driver support on Linux.
I had very good results with OpenLogi https://github.com/AprilNEA/OpenLogi/
Could this one day get us a second life for our echo flex units? They are phenomenal pieces of hardware.
Meta portal TV are also excellent hardware units discarded by its mothership and ripe for reuse. They were so mired by controversy but the TV unit hardware was really great.
You’ll be playing doom on your toothbrush in no time.
But yah maybe. There are mountains of “smart” hardware that demanded cloud, cloud went away, suddenly a brick. I’d love to wire some of that up and give Claude a shot at jail breaking and flashing that kinda thing.
