👁 243 次阅读
HackerNews 今日热榜
GitHub 热门AI项目
| rank | repo | stars | description |
|---|---|---|---|
| 1 | alikon-art/DeterminFlow | 250 | A production-oriented AI workflow runtime for building, vali |
| 2 | TOPDEV99999/AI-Knowledge-Management-Platform | 92 | An agentic LLM-powered knowledge assistant that enhances RAG |
| 3 | openwarehq/websiteprompts | 71 | make beautiful 3d websites in one skill, plus 50+ website pr |
| 4 | wanmol/goal-flow | 71 | Graph-Orchestrated Agent Loop — a production-grade framework |
| 5 | Sparkfetch/sparkfetch | 45 | 🔥 Turn any URL into clean, structured, LLM-ready content. Th |
| 6 | Sentry-LLM/SentryLLM | 35 | AI Security Monitor — Real-time threat detection, prompt inj |
| 7 | lifefloating/keyHunter-skill | 26 | Academic research toolkit for AI gateway panel security stud |
| 8 | Badtheorylabs/Macaw | 23 | Macaw — on-device AI agent for macOS. 2.7B LFM2.5 fine-tune, |
| 9 | TonicAI/distillery | 23 | Distillery: open-source LLM traffic proxy – Route and manage |
| 10 | hayescalebmmq5776/asr-linux-ai-dictation | 18 | ASR Linux is an AI-assisted desktop dictation app for Linux |
Arxiv 最新AI论文
| rank | title | authors |
|---|---|---|
| 1 | Tracing the Heart: An Evidence-Linked Pipeline for Heart-Failure Feature Engineering | Soorya Ram Shimgekar, Michelle Hu, Dorisa Shehi |
| 2 | The Low Frequency Trap: Video Language Models Fail at Simple Event Bookkeeping | Sarvesh Baskar, Zikui Cai, Shayan Shabihi |
| 3 | Challenges in Evaluating Explanation Methods for Static and Evolving Data | Jerzy Stefanowski |
| 4 | TRAJDEBUG: Tracing Error Lifecycle to Identify Critical Failures in Long-Horizon Agent Trajectories | Yunjia Qi, Zehua Yin, Xintong Shi |
| 5 | Beyond Top-K: Replacing Black-Box Retrieval with Interpretable Agentic Operations | Sagar Tamang, Ayush Vyas, Tabarakul Hazarika |
| 6 | HarnessOpt-Bench: Evaluating LLMs at Harness Optimization | Varun Ursekar, Apaar Shanker, Yash Maurya |
| 7 | Bias Analysis of L2 Speaking Assessment Systems Using Concept Activation Vectors | Arya Labroo, Mengjie Qian, Kate Knill |
| 8 | QuanTiMedAI: Quantum-Enhanced Time-Series Model guided by Agentic AI for Cardiac Arrest Mortality Prediction | Mutasim Fuad Sarker, Adiba Rahman Namira, Wafa Binte Alam |
| 9 | The Illusion of Visual Tool-Use: A Causal Audit of Thinking with Images | Zhiheng Wang, Bo Peng, Lai Wei |
| 10 | Improving the Realism of Synthetic Clinical Benchmarks Under Utility Constraints | Omid Bazgir, Md Nasir, Jacob Hoffman |
自动采集于 2026-08-08
🔗 相关阅读（你可能还想看）
📄 Gemini Omni 1.2 Flash 发布：视频降价30%、原生15秒，单条成本只贵5分钱
谷歌 11 月 5 日开放 Gemini Omni 1.2 Flash：720p 视频每秒 0.07 美元，比上代降 3
📄 GPT-6 Cyber 发布：121 万美元，948 条通往 root 的路
OpenAI 发布 GPT-6 Cyber：在 Linux 内核上跑出 948 个本地提权利用，整轮 API 成本 12
📄 Anthropic冲刺IPO：170亿营收、8950亿算力承诺、首次在招股书披露递归自我改进风险
📄 Anthropic IPO招股书曝光：单季营收170亿美元背后的8954亿美元算力账单
📄 阿里千问接入 Apple Intelligence：中国版 iPhone 的 AI 时刻来了
📄 苹果AI中国落地靴子落地：千问接入Apple Intelligence，11月4日开测
📄 苹果官宣：Apple Intelligence 国行版落地，阿里千问深度接入 Siri 与系统写作工具
苹果官宣 Apple Intelligence 国行版 11 月 4 日开测、12 月随 iOS 27.3 正式上线。阿
📄 Anthropic 递交 S-1 启动 IPO：Claude 母公司估值剑指 2 万亿美元
📄 Cerebras 公开万亿参数模型部署方案：59 块晶圆跑 3T 参数，推理 2000 tokens/秒