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

V
Vulnerabilities – Threatpost
Google DeepMind News
Google DeepMind News
Scott Helme
Scott Helme
NISL@THU
NISL@THU
T
Tor Project blog
T
Tenable Blog
D
Darknet – Hacking Tools, Hacker News & Cyber Security
P
Privacy International News Feed
Cyberwarzone
Cyberwarzone
Project Zero
Project Zero
S
Schneier on Security
C
Cybersecurity and Infrastructure Security Agency CISA
P
Proofpoint News Feed
Exploit-DB.com RSS Feed
Exploit-DB.com RSS Feed
O
OpenAI News
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
美团技术团队
Hugging Face - Blog
Hugging Face - Blog
V2EX - 技术
V2EX - 技术
H
Help Net Security
C
Check Point Blog
T
The Exploit Database - CXSecurity.com
Forbes - Security
Forbes - Security
人人都是产品经理
人人都是产品经理
U
Unit 42
cs.CL updates on arXiv.org
cs.CL updates on arXiv.org
Microsoft Azure Blog
Microsoft Azure Blog
D
Docker
I
InfoQ
Schneier on Security
Schneier on Security
K
Kaspersky official blog
罗磊的独立博客
Cisco Talos Blog
Cisco Talos Blog
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
S
Security Affairs
Microsoft Security Blog
Microsoft Security Blog
GbyAI
GbyAI
雷峰网
雷峰网
G
GRAHAM CLULEY
Cloudbric
Cloudbric
IT之家
IT之家
Stack Overflow Blog
Stack Overflow Blog
AI
AI
L
LINUX DO - 热门话题
云风的 BLOG
云风的 BLOG
博客园_首页
T
Threat Research - Cisco Blogs
S
Secure Thoughts
有赞技术团队
有赞技术团队

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] Maintaining old code Varieties of filesystems and schedulers, so why not for IPC mechanisms too? [LWN.net] AI and documentation [LWN.net] Delegating the work to a subsidiary [LWN.net] Maybe they should provide their reviews to the world [LWN.net] Something can be a bug but not a vulnerability [LWN.net] History is a little backwards ... [LWN.net] A reasonably extreme point of view [LWN.net] Let’s stop here [LWN.net] authd [LWN.net] Suggestion for bug report [LWN.net] Software pain points for long-term equipment [LWN.net] Wrong direction [LWN.net] mjg59 has lost the plot there [LWN.net] Role of German law in this? [LWN.net] Without beer? [LWN.net] Feels soul destroying [LWN.net] No zswap in Debian cloud kernel [LWN.net] No Beer?!? [LWN.net] The other fam [LWN.net] Thank you Andrew [LWN.net] Brave! [LWN.net] I second the cost factor [LWN.net] cassandra [LWN.net] Proprietary tools [LWN.net] familiar [LWN.net] ... is also staging. [LWN.net] Python package managers [LWN.net] Pour one out for AX.25... [LWN.net] tun/tap? [LWN.net] Another article at gnulinux.ch [LWN.net] Transitive checks [LWN.net] Just execute from stdin [LWN.net] Cross-compile Vacation [LWN.net] Concrete steps toward RFC 3550 (new Range types) You can rip with Windows apps too! Have the tempfile issues raised in the release notes been fixed? onlyoffice tried to add stuff in the fine print, and failed Work w/o publication is not science Removing art like offensive fortunes is a mistake. [LWN.net] De-googling (was Wtf) [LWN.net] I liked pdfmark [LWN.net] Juice then tag [LWN.net] why did PREEMPT_LAZY caused more preemptions than PREEMPT_NONE with THP disabled? [LWN.net] x86-64 was first introduced in 2003 [LWN.net] no memory safety? [LWN.net] False positive identification rate [LWN.net] "Defensive" AI use [LWN.net] LTS release? [LWN.net] ironic (ugly, good) [LWN.net] Moving away from LLVM [LWN.net] ironic (ugly, good) [LWN.net] Abandoning vim(1) ASAP [LWN.net] "Picard" naming [LWN.net] circular reasoning is a potential source of unsoundness [LWN.net] Nice to see an update [LWN.net] Writable THPs [LWN.net] Whole network messages [LWN.net] I'll fix my code ... [LWN.net] Can also recommend beets [LWN.net] Jack the CD ripper [LWN.net] How about the bad CDs? [LWN.net] systemd-boot [LWN.net] Significant raise of reports [LWN.net] IMO, it's appropriate [LWN.net] How about the bad CDs? [LWN.net] Update to include Part 4? [LWN.net] Pandoc also is invauable for a cheap-and-dirty retrieval augmented generation. [LWN.net] Whole network messages [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?