👁 146 次阅读
HackerNews 今日热榜
GitHub 热门AI项目
| rank | repo | stars | description |
|---|---|---|---|
| 1 | i3T4AN/KADATH | 173 | Evolutionary multi-agent runtime that breeds, evaluates, and |
| 2 | oliverb-io1902e8/agent-skills-collection | 134 | Curated collection of modular agent skills for LLM-based age |
| 3 | jundizhou/easy-stock | 103 | A 股AI行情分析与智能投研工作台-基于大模型 |
| 4 | wanmol/goal-flow | 72 | 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 | 36 | AI Security Monitor — Real-time threat detection, prompt inj |
| 7 | TonicAI/distillery | 29 | Distillery: open-source LLM traffic proxy – Route and manage |
| 8 | Badtheorylabs/Macaw | 28 | Macaw — on-device AI agent for macOS. 2.7B LFM2.5 fine-tune, |
| 9 | reiver-ai/reiver | 18 | Production AI control plane — OpenTelemetry-native APM, LLM |
| 10 | danielbergholz/phoenix-ai-setup | 15 | Six steps to make a new Phoenix app work well with AI coding |
Arxiv 最新AI论文
| rank | title | authors |
|---|---|---|
| 1 | Beyond Naturalness: Probing Automated Text-To-Speech Evaluat | Oluwanifemi Bam, Simon Rosen, Jash Shah |
| 2 | Multimodal Model Diffing for Feature Discovery and Control | Hunar Batra, Lachin Naghashy, Ashkan Khakzar |
| 3 | From Values to Benchmarks: Evaluating Large Language Models | Laurens Samson, Iva Gornishka, Gossa Lô |
| 4 | Fusion Training for Mathematical Generalization in Large Lan | Congfeng Cao, Pengyu Zhang, Jelke Bloem |
| 5 | Towards Expert-level Medical AI for Real-time Video Consulta | Mahvish Nagda, Jihyeon Lee, Matthew Thompso |
| 6 | Agentic Auto-Research is Fuzz Testing | Yifeng He, Jicheng Wang, Yinzhe Zhao |
| 7 | Mismatch Matters: On-Policy Distillation Beyond Token Agreem | Zichao Yu, Chengzhi Yu, Shengze Xu |
| 8 | Parameter Exploration for RLVR via Variational Learning | Vatsal Venkatkr, Nico Daheim, Iryna Gurevych |
| 9 | KGCaRe: Explainable Complex Conditional Question Answering u | Ghanshyam Verma, Simanta Sarkar, Devishree Pilla |
| 10 | Cultivar: A Contrastive and Locale-Oriented Translation Benc | Pinzhen Chen, Koel Dutta Chow, Xiaoya Xu |
自动采集于 2026-08-11
🔗 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