Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k
(systima.ai)
142 points by systima 1h ago | 82 comments
The Internet Right Now — Live Technology Dashboard
Track what people are reading, building, and publishing right now across Hacker News, GitHub, and arXiv. The dashboard refreshes throughout the day so you can scan top stories, trending repositories, and fresh AI papers without bouncing between tabs.
🔥Hacker News
Top stories, links, and active comment threads from the Hacker News front page.
I love LLMs, I hate hype
(geohot.github.io)
115 points by therepanic 1h ago | 46 comments
The shingles vaccine may reduce the risk of dementia
(economist.com)
148 points by saikatsg 4h ago | 108 comments
Old and new apps, via modern coding agents
(terrytao.wordpress.com)
361 points by subset 8h ago | 103 comments
Automation Without Understanding
(arxiv.org)
52 points by root-parent 3h ago | 26 comments
The One-Step Trap (In AI Research)
(incompleteideas.net)
12 points by jxmorris12 1h ago | 2 comments
Don't you mean extinct?
(fabiensanglard.net)
142 points by zdw 4h ago | 70 comments
Can We Understand How Large Language Models Reason?
(cacm.acm.org)
22 points by adunk 2h ago | 11 comments
Why write code in 2026
(softwaredoug.com)
29 points by softwaredoug 2d ago | 79 comments
Against Usefulness
(motivenotes.ai)
31 points by supo 2h ago | 5 comments
⭐GitHub Trending
Recently created repositories climbing fastest by stars, language, and momentum.
withmarbleapp/os-taxonomy
(github.com)
⭐ 2657 | JavaScript | 4d ago | 12 issues
Shpigford/knockoff
(github.com)
Chrome extension that filters pseudo-brand junk out of Amazon. Buy from real, established brands.
⭐ 1814 | JavaScript | 6d ago | 9 issues
oso95/scroll-world
(github.com)
A skill that turn any brand into a scrollable 3D world
⭐ 1161 | JavaScript | 5d ago | 1 issues
Robbyant/lingbot-world-v2
(github.com)
Infinite Worlds with Versatile Interactions
⭐ 911 | Python | 4d ago | 2 issues
x4gKing/3x-ui-Upgrade
(github.com)
⭐ 874 | HTML | 4d ago | 1 issues
Robbyant/lingbot-video
(github.com)
Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence
⭐ 709 | Python | 4d ago | 7 issues
Robbyant/lingbot-vision
(github.com)
Self-supervised learning for spatial perception
⭐ 669 | Python | 6d ago | 2 issues
mereyabdenbekuly-ctrl/clodex-ide
(github.com)
Local-first, zero-trust agentic IDE for verifiable autonomous software development.
⭐ 636 | TypeScript | 9h ago
op7418/guizang-material-illustration
(github.com)
归藏的材质插画 skill：生成带字解释图、图表美化和参考辅助配图。
⭐ 584 | 5d ago | 1 issues
vinhhien112/Three.js-Object-Sculptor-Codex-Plugin
(github.com)
Codex plugin that turns attached object images into code-only, animation-ready procedural Three.js models.
⭐ 541 | Python | 3d ago
📚arXiv Papers
New papers from cs.AI, cs.LG, cs.CL, and stat.ML with quick access to abstracts and PDFs.
UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks
(arxiv.org)
Zhekai Chen et al. | 3d ago
OpenCoF: Learning to Reason Through Video Generation
(arxiv.org)
Xinyan Chen et al. | 3d ago
Ideas Have Genomes: Benchmarking Scientific Lineage Reasoning and Lineage-Grounded Idea Generation
(arxiv.org)
Yifan Zhou et al. | 3d ago
Score Accuracy Along the Forward Diffusion Does Not Certify Numerical Stability in Diffusion Sampling
(arxiv.org)
Yiwei Zhou | 3d ago
MulTTiPop: A Multitrack Transcription Dataset for Pop Music
(arxiv.org)
Nathan Pruyne et al. | 3d ago
SLORR: Simple and Efficient In-Training Low-Rank Regularization
(arxiv.org)
David González-Martínez et al. | 3d ago
Using AI-based Learning Assistants in Higher Education: A Large-Scale Descriptive Analysis
(arxiv.org)
Kristina Schaaff et al. | 3d ago
Dimensionality Reduction Meets Network Science: Sensemaking on UMAP's kNN Graph
(arxiv.org)
Duen Horng Chau et al. | 3d ago
AUTOPILOT VQA: Benchmarking Vision-Language Models for Incident-Centric Dashcam Understanding
(arxiv.org)
Siddharth Damodharan et al. | 3d ago
ARDY: Autoregressive Diffusion with Hybrid Representation for Interactive Human Motion Generation
(arxiv.org)
Kaifeng Zhao et al. | 3d ago