1
从上海到世界：WAICA正以“AI原生”范式重写顶会规则
WAICA用“AI原生”范式颠覆传统顶会规则，全PC评审与公平投稿机制引关注
2
AUTOGATE: Automated Clock Gating via Toggling-Aware LLM-based RTL Rewriting
用LLM自动重写RTL代码实现时钟门控，AI+硬件设计前沿研究。
arXiv:2606.17461v1 Announce Type: cross Abstract: Fine-grain clock gating (FGCG) is among the most effective techniques for reducing dynamic power, ye…
3
谷歌用 4000 行 Rust 代码重写：Android 17 引入 ADB Wi-Fi 2.0，彻底重写无线调试堆栈解决断连痛点
IT之家 6 月 17 日消息，谷歌在 Android 17 中对无线 ADB 功能进行了大幅重写，并推出了全新的 ADB Wi-Fi 2.0，旨在解决自 Android 11 引入无线调试功能以来长期困扰开发者的稳定性和易用性问题。 ADB 即 Android 调试桥，是让用户从 PC 端控制 A…
4
We put the Bun Rust rewrite in production
Prisma在生产环境中采用Bun的Rust重写，并揭示了内存泄漏的实战教训
At Prisma we've been working on a Compute offering to complement our hosted Postgres. We settled on Bun early in the process as we liked the experienc…
5
Answer Presence Drives RAG Rewriting Gains
打破刻板印象：RAG重写提升效果并非来自证据质量改善，而是答案存在性起主导作用
arXiv:2606.05633v1 Announce Type: new Abstract: Retrieval-augmented QA pipelines often route retrieved passages through an LLM \emph{rewriter} before …
6
Show HN: Uruky (EU-based Kagi alternative) now has Image Search and URL Rewrites
欧盟隐私搜索引擎Uruky新增图片搜索与URL重写功能，月费5欧，12个月后可得源代码。
You can get a 2h free trial by solving a proof-of-work captcha when topping up your account for the first time. If you'd like to learn more, an indepe…
7
Need to Know: Contextual-Integrity-Grounded Query Rewriting for Privacy-Conscious LLM Delegation
基于语境完整性理论，提出隐私保护查询重写方法，让大模型在委托场景中只获取“需要知道”的信息。
arXiv:2606.04067v1 Announce Type: cross Abstract: As LLMs become increasingly woven into everyday workflows, user queries sent to cloud hosted LLMs ro…
8
D-Judge: Disrupting Multi-Turn Jailbreaks using Semantics-Preserving Output Rewriting
用输出重写破坏多轮越狱攻击，语义保持下高效防御，AI安全新方法。
arXiv:2606.02640v1 Announce Type: cross Abstract: Multi-turn jailbreak attacks pose a growing threat to large language model (LLM) safety because they…
9
Cross-Lingual Token Arbitrage: Optimizing Code Agent Context Windows via Local LLM Preprocessing
提出跨语言令牌套利新方法，用本地LLM预处理重写提示词，低成本优化代码代理上下文窗口。
arXiv:2606.03618v1 Announce Type: new Abstract: AI-assisted coding agents are bottlenecked by input-token cost. Two pathologies of raw human input dri…
10
How to protect your AI endpoints with Vercel BotID
Vercel BotID 教你三步防护 AI 端点，轻松应对 3000% 流量暴增
Article URL: https://vercel.com/kb/guide/protect-ai-endpoints-with-vercel-botid Comments URL: https://news.ycombinator.com/item?id=48342146 Points: 2 …
11
Rewriting stale OSS projects using LLM
用LLM打破传统耗时重写的魔咒，让废弃开源项目焕发新生。
Article URL: https://loopholelabs.io/blog/rewriting-oss-in-the-ai-era Comments URL: https://news.ycombinator.com/item?id=48334593 Points: 3 # Comments…
12
CoHyDE: Iterative Co-Training of LLM Rewriter & Dense Encoder for Tool Retrieval
用协同训练改写器和密集编码器，跨越自然语言与API技术词汇的鸿沟，大幅提升LLM工具检索准确率。
arXiv:2605.29271v1 Announce Type: new Abstract: Tool retrieval over large API catalogs is a core bottleneck for LLM agents: user queries arrive in col…
13
14
LLM Watermark Evasion via Bias Inversion
黑盒环境下LLM水印逃避新突破：理论揭示重写型攻击无需查询即可规避检测，且不损语义完整性，为AI内容溯源安全敲响警钟。
arXiv:2509.23019v5 Announce Type: replace-cross Abstract: Watermarking offers a promising solution for detecting LLM-generated content, yet its robust…
15
Humanize – two LLM-agnostic skills to rewrite and detect AI text
基于50+学术源的开源工具，教你两种通用技能重写与检测AI文本，让文字更「人味」
Article URL: https://github.com/harshaneel/humanize Comments URL: https://news.ycombinator.com/item?id=48283802 Points: 1 # Comments: 0
16
Lynote Humanize Text – Open-source AI text humanization toolkit
开源AI文本人性化工具包，提供翻译链+LLM重写等4种方法，让AI生成文字更自然流畅。
Article URL: https://github.com/lynote-ai/humanize-text Comments URL: https://news.ycombinator.com/item?id=48263078 Points: 2 # Comments: 0
17
CR4T: Rewrite-Based Guardrails for Adolescent LLM Safety
面向青少年的大模型安全防护新方法，基于重写机制的护栏系统，聚焦内容安全与风险管控。
arXiv:2605.21609v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly embedded in adolescent digital environments, mediating i…
18
Be Kind, Rewrite: Benign Projections via Rewriting Defend Against LLM Data Poisoning Attacks
顶会论文新发现：用LLM重写对抗数据投毒，一种温和却有效的后门攻击防御策略。
arXiv:2605.19147v1 Announce Type: cross Abstract: Large language models (LLMs) are highly susceptible to backdoor attacks (BAs), wherein training samp…
19
Systematic Evaluation of the Quality of Synthetic Clinical Notes Rephrased by LLMs at Million-Note Scale
百万级临床笔记重写质量系统性评估，揭示LLM文本生成多维评价短板
arXiv:2605.17775v1 Announce Type: new Abstract: Large language models (LLMs) can generate or synthesize clinical text for a wide range of applications…
20
Not so locked in any more
编程语言不再锁定：编码代理降低迁移成本，React Native重写可轻松回退
This Mitchell Hashimoto quote about Bun migrating from Zig to Rust reminded me of a similar conversation I had at a conference last week. I was talkin…