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

G
Google Developers Blog
WordPress大学
WordPress大学
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
小众软件
小众软件
人人都是产品经理
人人都是产品经理
美团技术团队
Blog — PlanetScale
Blog — PlanetScale
S
SegmentFault 最新的问题
博客园 - 【当耐特】
V
V2EX
Microsoft Azure Blog
Microsoft Azure Blog
博客园 - 叶小钗
Google DeepMind News
Google DeepMind News
量子位
罗磊的独立博客
月光博客
月光博客
N
Netflix TechBlog - Medium
大猫的无限游戏
大猫的无限游戏
博客园_首页
P
Proofpoint News Feed
Jina AI
Jina AI
云风的 BLOG
云风的 BLOG
博客园 - 司徒正美
腾讯CDC

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]
Detecting AI obfuscated porting [LWN.net]
jorgegv · 2026-06-02 · via LWN.net comments

Detecting AI obfuscated porting

Posted Jun 2, 2026 9:47 UTC (Tue) by jorgegv (subscriber, #60484)
In reply to: Detecting AI obfuscated porting by khim
Parent article: Ombredanne: An AI agent ported our codebase from Python to Rust
to post comments

Detecting AI obfuscated porting

Posted Jun 2, 2026 11:08 UTC (Tue) by khim (subscriber, #9252) [Link] (2 responses)

> I have to disagree here. LLMs are definitely already designing architectures. Perhaps not complicated ones, not humongous projects, but they are definitely there.

They are very nice at stealing existing code and translating it to work in new place.

But the limitation is still the same: 200-300 lines code should give you something working and testable. That's not “designing an architecture”, that's “finding a place where someone's else architecture may fit”.

And yes, it's really impressive, they like to graft massive amount of code to repeat the same architecture that they found somewhere again and again.

But that's an attempt to build a skyscraper by piling twigs into a large pile. You may build a hut that way or maybe evem, evetually something similar to the ant's nest… but that's not an architecture, that's still pile of pieces not connected in any sensible order.

> I'm using them currently for work and personal projects, and Claude was able to design from scratch (and is currently implementing) a retro computing emulator. My emulator is fully working at this point, and I'm fixing bugs.

So Claude have duplicated something that was done thousands of times and was able to amalgamate that into something kinda-sorta-working… what's the big deal? It's very easy to see when it does that: try to ask it to add something that needs a component that is not there yet, and it would start with calling it, then trying to compile — and only then finding out it needs to be writtem. But try to do something differently from how other projects do thing, on average — and you'll discover that it would ignore your requests and would return “design” back to the average between other projects of similar nature.

Detecting AI obfuscated porting

Posted Jun 2, 2026 22:29 UTC (Tue) by Cyberax (✭ supporter ✭, #52523) [Link] (1 responses)

Detecting AI obfuscated porting

Posted Jun 7, 2026 4:47 UTC (Sun) by fwyzard (subscriber, #90840) [Link]

Curious, what model?