I'm saying, either you have a problem with the copyright issues related to AI training or you don't. If you do, neither Qwen nor Claude are acceptable, if not then both are. They have similar moral standing to me.
Btw, ethically sourced, open source LLMs exist! Check out eg Olmo by Allen AI: https://allenai.org/olmo
in this case yes. stealing from a thief is right if you give all of it back to the victims. with ai the "stealing" is from everyone on the internet, so the only ethical option is making the results open source and available to all. thats exactly what chinese labs are doing.
(in general i think piracy or breaking ip laws in general is not morally wrong unless you make money from it, but thats a whole other conversation.)
Btw, ethically sourced, open source LLMs exist! Check out eg Olmo by Allen AI: https://allenai.org/olmo