惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

Vercel News
Vercel News
博客园 - 司徒正美
大猫的无限游戏
大猫的无限游戏
Last Week in AI
Last Week in AI
V
Visual Studio Blog
阮一峰的网络日志
阮一峰的网络日志
小众软件
小众软件
宝玉的分享
宝玉的分享
Apple Machine Learning Research
Apple Machine Learning Research
美团技术团队
WordPress大学
WordPress大学
博客园 - 聂微东
人人都是产品经理
人人都是产品经理
罗磊的独立博客
The Cloudflare Blog
V
V2EX
月光博客
月光博客
有赞技术团队
有赞技术团队
Y
Y Combinator Blog
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
让小产品的独立变现更简单 - ezindie.com
让小产品的独立变现更简单 - ezindie.com
GbyAI
GbyAI
博客园 - 【当耐特】
T
Tailwind CSS Blog

LWN.net comments

tcmalloc's weird hack [LWN.net] Fixed? [LWN.net] mpd [LWN.net] Userspace AX.25 [LWN.net] RIP [LWN.net] My two cents... [LWN.net] pipx [LWN.net] Tragedy [LWN.net] A young man destined for glory [LWN.net] And 'less' won't let you search [LWN.net] A great loss [LWN.net] Sad and shocking news [LWN.net] Easy migration from Clementine [LWN.net] Sad coincidence [LWN.net] GNOME is actually usable thanks to Seth et al [LWN.net] Sad news :( [LWN.net] armhf supports preempt_rt [LWN.net] MusicBrainz accurracy [LWN.net] On open source maintainership [LWN.net] Let's stop here [LWN.net] Not a new thing [LWN.net] uv is indeed great pgmoneta Some comments on this on a Postgres blog feed [LWN.net] uv [LWN.net] going to Debian [LWN.net] Upgrading 64-bit-capable systems to 64-bit kernels? [LWN.net] Free Software foundations Maintainers can wait for code review but not for publish review? A reasonably extreme point of view [LWN.net]
Haha, AI can't do $THING [LWN.net]
marcH · 2026-06-03 · via LWN.net comments

> The distinctions between the inputs and outputs created by an AI on the one hand, and a human art student on the other, are too fine for judges to reliably analyze in the courtroom.

I don't understand why this comparison would be even looked at in the first place, it does not make sense to me.

A printing press can be used to infringe copyright - or not at all. That's why copyright uses a "black box" model: because the same user can sometimes be infringing, other times not at all and yet other times it's borderline and debatable. So copyright never had any other choice than this black box model. It could never care about the technology. It did try to attack some copy technologies sometimes but that never made sense and never worked.

A student can produce a drawing too similar and copyrighted - or not at all. Sometimes they will infringe and others not.

Exact same thing for AI output. There is no simple AI rule and there cannot be. It's still case-by-case.

> Technologies come and go, and the law adapts. But we don't get this flexibility for free. Judges and lawyers have to figure it out on a case-by-case basis, and they need a coherent theory of how that works. That theory is now the problem.
> Broadly and informally speaking, most analysis of infringement uses a black-box model...

That inability to scale has not changed. The only thing that changed is the _volume_ copyright infringement must now face. Copyright enforcement never "scaled". AI made that inability much more obvious but did not fundamentally changed the initial design flaw.

In a recent past, BitTorrent and friends already exposed another, different inability of copyright enforcement to scale. That inability was never "fixed". It was only mitigated through various means: targeting only the biggest offenders, threats, offering better, legal streaming alternatives...

One difference with today's AI challenge is not just the volume of infringements but also the very deep pockets of AI companies who can buy even more congressmen (thank you "Citizens" United vs FEC) than the copyright lobby can. Again: a scaling issue.

So maybe this is finally the end of copyright, dunno. But not because AI affected any of copyright's fundamental logic, but rather because it was never designed to scale in the first place - as you wrote yourself.