Qwen3.8 Max now ranked as the best overall model by agentic index
(artificialanalysis.ai)
153 points by apitman 1h ago |
The Internet Right Now — Live Technology Dashboard
One live view of what tech is reading, building, and publishing across Hacker News, GitHub, and arXiv.
🔥Hacker News
Top stories, links, and active comment threads from the Hacker News front page.
Mario Meets Pareto
(mayerowitz.io)
741 points by theanonymousone 8h ago |
Launch HN: ProvenMetal (YC S26) delivers circuit boards in days instead of weeks
(provenmetal.com)
135 points by willcarkner 4h ago |
Almost no skill required to cook a steak
(blog.sydorets.com)
179 points by yusyd 4h ago |
xAI Ignores Laws and Profits: Rules for Thee, Not for Me
(illegal.solutions)
69 points by speckx 31m ago |
Taste Is All That's Left
(notashelf.dev)
29 points by tsak 3h ago |
Herdr is joining Y Combinator. The runtime stays open
(herdr.dev)
9 points by collinmanderson 55m ago |
The DISTINCT in Your COUNT
(boringsql.com)
3 points by gmcabrita 29m ago |
Crime Pays but Botany Doesn't
(crimepaysbutbotanydoesnt.com)
593 points by DarkContinent 15h ago |
Learn how chips are made with this Rollercoaster Tycoon-inspired animation
(laurentiugabriel.github.io)
38 points by laurentiurad 6d ago |
⭐GitHub Trending
Recently created repositories climbing fastest by stars, language, and momentum.
firecrawl/anydoc
(github.com)
Convert Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV, and PDF to clean Markdown. Built in Rust, with Node.js and Python bindings.
⭐ 7869 | Rust | 3d ago | 29 issues
trycompai/crm
(github.com)
Comp AI CRM is an open source, CRM designed for AI agents. Agentic-first CRM.
⭐ 7116 | TypeScript | 5d ago | 6 issues
FareedKhan-dev/kimi-k3-in-c
(github.com)
A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.
⭐ 2790 | C | 5d ago | 2 issues
imsai-sh/zhuzhiliao
(github.com)
竹知了 —— 一转就哇哇叫的传统玩具，Web 模拟版。零依赖单文件，真实录音采样，移动端优先。
⭐ 2289 | HTML | 5d ago | 9 issues
genspark-ai/genoffice
(github.com)
An AI-native office suite for macOS and Windows: word processor, spreadsheet, presentations, and PDF.
⭐ 2026 | TypeScript | 6d ago | 18 issues
thebuggeddev/anatomy
(github.com)
An interactive 3D human anatomy explorer built using threejs with GPT 5.6 Sol
⭐ 1838 | TypeScript | 4d ago | 8 issues
DannyMac180/sol-advisor
(github.com)
Codex-native architect orchestration with Luna and Terra implementation lanes and mandatory fresh Sol review.
⭐ 1684 | Shell | 5d ago | 12 issues
KKKKhazix/human-writing
(github.com)
让 AI 写的中文读起来像一个具体的人在说话。通用创作与改稿 Skill，开箱即用。
⭐ 1548 | Python | 1d ago | 3 issues
Binaryify/open-kimi-ppt-skill
(github.com)
非官方 Kimi Slides Skill：让 AI Agent 生成可编辑 PPTD + PPTX，并附带本地浏览器编辑器 Unofficial Kimi Slides skill for AI agents — generate editable PPTD + PPTX with a local browser editor
⭐ 1279 | Python | 1d ago | 2 issues
Accio-org/RealReplicaBench
(github.com)
RealReplicaBench: Benchmarking Long-Horizon Agents in High-Fidelity, Stateful, and Reproducible Replicas of Real Online Services
⭐ 1036 | HTML | 4d ago
📚arXiv Papers
New papers from cs.AI, cs.LG, cs.CL, and stat.ML with quick access to abstracts and PDFs.
Reasoning Core: Designing Broad Procedural Data for Completion-Supervised Reasoning Training
(arxiv.org)
Damien Sileo et al. | 1d ago |
Argus: A General-Purpose Agentic Runtime for Long-Horizon Reasoning
(arxiv.org)
Boxiu Li et al. | 1d ago |
OctoLong: Mid-Training On Cross-Repository Code Contexts Enhances Long-Context Modeling
(arxiv.org)
Indraneil Paul et al. | 1d ago |
Toward Skill-Native LLMs: Skill Entropy for Benchmarking and Training Long-Horizon Reasoning
(arxiv.org)
Yinghui He et al. | 1d ago |
Teaching Nemotron Greek: Mining a Corpus, Adapting Retrieval, and Grounding Generation for Modern Greek across Specialist Domains
(arxiv.org)
Ayoub Kirouane et al. | 1d ago |
The Loss Does Not See the Basis, but Adam Does
(arxiv.org)
Devender Singh | 1d ago |
Predicting Brain Morphometry with MT-GNN: Mesh Evolution in Continuous Time with Graph-Based Metric Tensor Embeddings
(arxiv.org)
Hao Ding et al. | 1d ago |
OPD-V: Visual On-Policy Self-Distillation with Modality Balance
(arxiv.org)
Aniri et al. | 1d ago |
SSTQ:Privacy-Preserving Vector Quantization via Subsampled Stochastic TurboQuant
(arxiv.org)
Adel Javanmard et al. | 1d ago |
Spoken Function Calling: A New Perspective on Spoken Language Understanding for Large Audio Language Models
(arxiv.org)
Yuezhang Peng et al. | 1d ago |