1
Show HN: E– – a language you dial between English and Python
一种介于英语和Python的新语言，消除歧义并让LLM可选执行，重构人机交互语法。
Article URL: https://github.com/frmoded/e-- Comments URL: https://news.ycombinator.com/item?id=48863891 Points: 1 # Comments: 2
2
ภาษาโปรแกรมมิ่งที่ syntax ง่าย ทำให้ AI หลอนน้อยลง จริงหรือ?
研究揭示简洁语法真的能让AI减少幻觉？从Token Sugar到MultiPL-E，Java与Python的AI表现差异有新发现。
ภาษาโปรแกรมมิ่งที่ syntax ง่าย ทำให้ AI หลอนน้อยลง จริงหรือ? "เขียน Go แล้ว Copilot แม่นกว่าเขียน Java" — เคยได้ยินไหม? หรือ "Python มันง่าย AI เลยเก่…
3
The Hidden Cost of Structured Generation in LLMs: Draft-Conditioned Constrained Decoding
LLM结构化生成中的约束解码存在隐藏成本：掩码和重新归一化可能扭曲生成模式，论文揭示这一关键代价。
arXiv:2603.03305v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly used to generate executable outputs, JSON obje…
4
Show HN: LLMRender, a 10kb Markdown+LaTeX renderer for React
轻量级React组件，10kb零依赖，支持Markdown、LaTeX和内联数学，测试覆盖率99.9%，开源即用。
I've been using the popular React Markdown renderers with Katex and Prism.js for rendering my Markdown and LaTeX, but was tired of having to bundle 30…
5
Grammar-Constrained Decoding Can Jailbreak LLMs into Generating Malicious Code
研究发现利用语法约束解码可诱导LLM生成恶意代码，揭示新型安全漏洞。
arXiv:2606.11817v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used for code generation, raising concerns that they m…
6
How Far Can Prompting Go for Minimal-Edit Ukrainian Grammatical Error Correction?
探索提示工程在低资源语言乌克兰语上的语法纠错极限，揭示大模型与提示策略的边界。
arXiv:2606.09334v1 Announce Type: new Abstract: Fine-tuned Large Language Models (LLMs) dominate in Ukrainian grammatical error correction (GEC), whil…
7
Noisy memory encoding explains negative polarity illusions
用噪音记忆编码模型揭示“负极性词”语法幻觉的认知根源，颠覆传统语法判断认知
arXiv:2606.04340v1 Announce Type: new Abstract: A sentence like "The authors that no critics recommended have ever received acknowledgment for a best-…
8
A Pre-Training Analogue of Grokking in Language Models: Tracing Delayed Grammatical Generalization
语言模型预训练时竟出现类似“顿悟”的语法泛化延迟现象，揭示学习路径的意外转折。
arXiv:2606.00230v1 Announce Type: new Abstract: Grokking, the phenomenon in which neural networks generalize long after fitting their training data, h…
9
A Grammar of Machine Learning Workflows: Rejecting Data Leakage at Call Time
ML工作流语法登场，用八种基元在调用时直接阻断数据泄露，终结学界十年顽疾。
arXiv:2603.10742v4 Announce Type: replace Abstract: Data leakage has been identified in 648 published papers across 30 scientific fields. The knowledg…
10
How Much Do LLMs Know About Chinese Zero Pronouns?
探究大语言模型在中文零代词理解上的能力边界，一项针对中文语法特殊现象的前沿研究。
arXiv:2605.31056v1 Announce Type: new Abstract: Zero Pronouns (ZPs) are a pervasive linguistic phenomenon in pro-drop languages such as Chinese and ha…
11
Show HN: leaf – one month later: website, releases and lots of improvements
极简Markdown预览工具leaf更新：无需浏览器，命令行快速渲染，40+语言语法高亮，轻量易用。
Hi HN, About a month ago, I shared leaf here while it was still in its early stages. Since then, the project has shipped multiple releases, with UX im…
12
SMolLM: Small Language Models Learn Small Molecular Grammar
小语言模型学会分子语法，高效生成药物分子候选，AI+化学新突破。
arXiv:2605.06322v2 Announce Type: replace Abstract: Language models for molecular design have scaled to hundreds of millions of parameters, yet how th…
13
Accelerating Constrained Decoding with Token Space Compression
通过压缩词空间加速约束解码，让LLM输出精准服从语法规则，显著提升效率。
arXiv:2605.29986v1 Announce Type: new Abstract: To guarantee that an LLM's outputs conform to a specified structure, context-free grammar (CFG) decodi…
14
Various LLM Smells
用亲身数学博客写作经历，教你识别LLM生成文本中那些难以察觉的“气味”特征。
Article URL: https://shvbsle.in/various-llm-smells/ Comments URL: https://news.ycombinator.com/item?id=48313810 Points: 3 # Comments: 0
15
Continuous Diffusion Models Can Obey Formal Syntax
在 arXiv 上轻松获取这篇关于连续扩散模型服从形式语法的最新研究，支持在线预览与 PDF 下载
arXiv:2602.12468v2 Announce Type: replace Abstract: Diffusion language models offer a promising alternative to autoregressive models due to their glob…
16
A Grammar-First Approach to Parser Combinators in Rust
探索Rust中语法优先的解析器组合子新思路，通过实际代码示例教你构建自定义解析库。
Rust already has well-established parser combinator libraries like nom and chumsky , so why build another one? In my experience, using parser combinat…
17
谷歌 AI 摘要频现低级拼写错误，大语言模型固有缺陷难根治
AI写作助手实时检查拼写语法，用智能纠错避免谷歌式低级错误，写作更安心
IT之家 5 月 28 日消息，Google 这个单词里有几个字母 P？谷歌给出的答案是两个。 谷歌的人工智能摘要（AI Overview）还称，单词“poop”里有一个字母 r，而“journalism”一词包含两个字母 d，可它给出的拼写却是：j-o-u-r-n-a-d-i-s-m。谷歌倒是正确…
18
Probing Minimalist Phase Structure in LLMs: What Universal Dependencies Cannot Represent
深入探测13个LLM，发现最小主义短语结构与通用依赖（UD）的表征边界
arXiv:2605.26431v1 Announce Type: new Abstract: Structural probes train on Universal Dependencies (UD), which does not encode formal-syntactic abstrac…
19
Copy-as-Decode: Grammar-Constrained Parallel Prefill for LLM Editing
无需重写整个输出，LLM编辑效率新突破：Copy-as-Decode用语法约束并行预填充，大幅加速文本代码编辑。
arXiv:2604.18170v2 Announce Type: replace-cross Abstract: LLMs edit text and code by autoregressively regenerating the full output, even when most tok…
20
Text Edit Plus 限时免费：老牌轻量级文本编辑器
轻量却强大的Windows文本编辑器，多标签、语法高亮与宏支持恰到好处，限时免费速速替代记事本！
Text Edit Plus 是一款 Windows 下的老派轻量级文本编辑器，可用来替代记事本，提供多标签、拼写检查、宏和语法高亮等功能。常年售价19刀，目前正在限免。@Appinn Text Edit Plus 16 限免 这次限免是 Text Edit Plus 自己发邮件过来的，版本位 Te