1
Show HN: Ty-extended – a Ty fork with plugin support
Ty语言分支，引入WASM插件机制，为语义检查器带来可扩展能力。
Hi HN! I'm a Ty frequent user on all my Python projects, however, lately I've been needing to go back to mypy due to the lack of plugin support on Ty.…
2
Your Docs Are Doing Your Marketing Now (Whether You Like It Or Not)
品牌改名可能让AI搜索“失忆”，旧品牌在AI回答中曝光度反超新品牌10倍，这是文档营销的新暗线。
TL;DR - Nobody has one AI visibility number. You have six (one per model), and they disagree — a cloud infra company we audited scored 33% on ChatGPT/…
3
Extractable Memorization From First Principles
从第一原理出发，揭示LLM可提取记忆研究中两种相反的效度陷阱，平衡过度提取与不可靠证据的争议。
arXiv:2607.12649v1 Announce Type: new Abstract: Recent work on extractable memorization in LLMs suffers from two contrasting validity problems. Some s…
4
小米 MiMo 完成大语言、多模态、语音等全系列模型矩阵闭环，端侧模型通过国家大模型备案
小米MiMo完成大语音、多模态、语音全系列模型矩阵闭环，端侧模型获国家备案，AI投入计划超600亿。
IT之家 7 月 15 日消息，促进生成式人工智能服务创新发展和规范应用，网信部门会同有关部门按照《生成式人工智能服务管理暂行办法》要求，有序开展生成式人工智能服务备案工作， 现将新增的“Apple 智能”等 7 款提供手机端侧生成式人工智能服务备案信息予以公告 。 小米官方刚刚发文，介绍了此次通过…
5
京东 AI 智能体与腾讯元宝打通小程序生态，用户用自然语言即可跳转商品页下单
京东AI智能体联手腾讯元宝，自然语言即可跳转商品页下单，购物体验更智能。
IT之家 7 月 15 日消息，京东与腾讯联合宣布，京东 AI 智能体与腾讯元宝完成小程序生态打通。京东 AI 智能体将为元宝提供覆盖数码电子、家用电器、服饰鞋包、美妆个护、食品生鲜等在内的全品类商品信息，并为用户提供商品推荐、下单，以及履约、售后等服务。 京东表示，如今用户在元宝 App 内询问产…
6
Modeling Story Expectations: A Generative Framework using LLMs
利用LLM建模故事期待，提出生成框架，为叙事理解与文本生成开辟新思路。
arXiv:2412.15239v4 Announce Type: replace Abstract: Consumers' engagement with stories is shaped by their expectations about what will happen next, ye…
7
Comparing Semantic Navigation in Humans and Large Language Models using Natural Language Processing
用NLP对比人类与LLM的语义导航能力，揭秘AI认知机制的新视角。
arXiv:2607.12195v1 Announce Type: new Abstract: Semantic memory retrieval can be conceptualized as navigation through conceptual space. We compared se…
8
A Shared Subcircuit Lets LLMs Count Down Across Tasks
大模型内部发现通用倒数机制，助你在多种任务中精准控制输出长度
arXiv:2607.12279v1 Announce Type: cross Abstract: Writing a sentence of exactly twelve words; ending a DNA sequence at the right codon; formatting an …
9
DeepSeek reportedly in talks to raise $1.5B, then IPO
中国大模型新贵DeepSeek拟融资15亿美元，估值710亿，2027年或提前IPO。
DeepSeek, the Chinese large language model developer, is said to be preparing for a 2027 IPO debut as it also looks to raise around $1.5 billion in ne…
10
Can Induced Emotion Bias LLM Behaviors in Sequential Decision Making?
最新研究揭示情绪诱导如何使大语言模型在序列决策中产生行为偏差，视角独特。
arXiv:2607.12631v1 Announce Type: new Abstract: As Large Language Models (LLMs) are increasingly deployed as autonomous agents in high-stakes domains,…
11
意件（ideaware）诞生与Python/Java正在变成汇编语言
AI正重构软件行业：一人公司模式崛起，Python/Java或沦为“汇编语言”，实时语音AI展现拟人性引发哲学思辨。
https://www.youtube.com/watch?v=5ghhAxcH9R0 由于该视频是一场长达 2.5 小时 的深度直播分享， 这是一份 超详细的视频内容结构化导航指南 。结合视频中的关键时间节点，你可以直接点击对应的进度条，快速收听你最感兴趣的部分： 154分钟对谈完整梳理（分段结构…
12
Show HN: AI-CLI – tiny C terminal assistant powered by local LLM
本地LLM驱动的终端AI助手，C语言编写，轻量小巧又实用
Article URL: https://github.com/vkataev/ai-cli Comments URL: https://news.ycombinator.com/item?id=48918840 Points: 3 # Comments: 1
13
PM-KVQ: Progressive Mixed-precision KV Cache Quantization for Long-CoT LLMs
针对长思维链大语言模型的KV缓存量化新突破，渐进混合精度方案，已被ICLR 2026接收，代码已开源。
arXiv:2505.18610v2 Announce Type: replace Abstract: Recently, significant progress has been made in developing reasoning-capable Large Language Models…
14
FineInstructions: Scaling Synthetic Instructions to Pre-Training Scale
通过合成指令数据扩展预训练规模，突破传统监督训练数据瓶颈的新方法
arXiv:2601.22146v2 Announce Type: replace-cross Abstract: Due to limited supervised training data, large language models (LLMs) are typically pre-trai…
15
Metacognition in LLMs: Foundations, Progress, and Opportunities
探索大语言模型的“自我反思”能力：元认知研究综述，从理论到前沿机遇全梳理。
arXiv:2607.11881v1 Announce Type: cross Abstract: Metacognition is a foundational component of intelligence critical to effective learning, problem so…
16
PRISM Edit: One Vector for All Temporal Answers
单一向量让大模型同时记住新旧答案，攻克时间事实编辑难题
arXiv:2607.11327v1 Announce Type: cross Abstract: Model editing keeps large language models (LLMs) up to date without retraining, but temporal facts e…
17
AeroRAG: Structured Multimodal Retrieval-Augmented LLM for Fine-Grained Aerial Visual Reasoning
新型多模态检索增强框架让大模型精准理解航拍图像细节，解决细粒度视觉推理难题。
arXiv:2604.17889v2 Announce Type: replace Abstract: Despite recent progress in multimodal large language models (MLLMs), reliable visual question answ…
18
MAGIC: Transition-Aware Generation of Navigable Multi-Scene Game Worlds with Large Language Models
用大语言模型实现过渡感知的多场景游戏世界生成，让玩家在不同场景间无缝导航。
arXiv:2607.11594v1 Announce Type: new Abstract: Multi-scene navigation (clearing an objective in one bounded space and then crossing a portal into the…
19
GigaChat Audio: Time-aware Large Audio Language Model
GigaChat Audio 是时间感知音频语言模型，精准理解音频内容与时间关系，提升语音识别与生成质量。
arXiv:2607.10387v1 Announce Type: cross Abstract: Temporal grounding in long recordings remains challenging for audio-conditioned LLMs. We present a t…
20
Dimensionality in Satisfaction Ratings
利用大模型GPT-4.1深度解析近万条客服对话，将满意度分解为多个维度并验证其有效性，揭示AI在客户体验分析中的潜力。
arXiv:2607.11026v1 Announce Type: new Abstract: We used a large language model (GPT-4.1) to annotate the text of about 9,000 support conversations at …