|
| ▲ | tokyobreakfast 8 hours ago | parent | next [-] |
| In the mid-2000s there was a bit of drama when Linux wireless driver code ended up in BSD (or maybe the other way around). The Internet was angry that day my friend; a bunch of nerds sperging out over licenses and which license is more "free". Ultimately the code was removed. It sure seems like AI agents can sidestep all that by claiming ignorance on license matters. |
|
| ▲ | stanac 8 hours ago | parent | prev | next [-] |
| AI written driver could be a rip off Linux driver. |
|
| ▲ | IshKebab 8 hours ago | parent | prev [-] |
| If the Linux driver is GPL and he made the new driver using AI to essentially copy it then claim that the result wasn't covered by the GPL... It's an area not settled by law yet. Still not as bad as the guy who paid for a commercial license for some Linux driver, fed it into Claude to get it to update it to the latest Linux, and then released it as GPL! That's definitely not a grey area. https://youtu.be/xRvi3k8XV8E Absolutely mental behaviour for a business. What were they thinking? |
| |
| ▲ | heffer 5 hours ago | parent [-] | | It's clickbait. The "driver" is actually a rather comprehensive kernel patch that modifies existing GPLv2 kernel code, so by its very nature it is at least GPLv2 (original parts may be dual licensed by the vendor if they want to, but they can't not make it GPLv2). What this person paid $40,000 for is access to development kits for certain hardware, which with chip vendors like that usually also comes with support. The vendor cannot prevent you from exercising your GPLv2 rights after they hand you the code.
In fact, if you manufacture and distribute a device that uses these kernel patches it becomes your obligation to enable your customers to exercise their GPLv2 rights. Chip manufacturers know this and (if they are somewhat reputable) usually license their code appropriately. |
|
