Xiaomi MiMo v2.6
(mimo.xiaomi.com)
180 points by volf_ 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.
Checked just now
The NASA/ESA Mars Sample Return mission has been canceled
(science.org)
167 points by Muhammad523 2h ago |
Transformers Explained Visually
(poloclub.github.io)
39 points by aray07 1h ago |
What Sun got wrong
(bcantrill.dtrace.org)
427 points by chmaynard 7h ago |
Attention is all you have
(alicegg.tech)
462 points by zer0tonin 7h ago |
Why does mathmain need an encrypted loader?
(safedep.io)
80 points by abhisek 3h ago |
The Advisory Group on Mathematics and Artificial Intelligence
(terrytao.wordpress.com)
39 points by digital55 2h ago |
Divide by Depth for Instant 3D
(gabrieloc.com)
20 points by gabrieloc 2d ago |
Apple Copland D11E4 Booting in the Browser
(pagetable.com)
44 points by luu 3h ago |
In Search of a Compositional Theory of Self-Stabilization
(muratbuffalo.blogspot.com)
29 points by matt_d 2h ago |
Popular new repos
Repositories created in the last seven days, ranked by total stars.
Checked just now
browser-use/jev-ultrafast
(github.com)
Fastest and cheapest web agent
⭐ 15480 | Python | 5d ago | 108 issues
NandhaKishorM/laya
(github.com)
⭐ 9717 | Python | 3d ago | 47 issues
tamaratran/fast-jev-compaction
(github.com)
Claude Code plugin that replaces the compaction summary with Jev decisions: every tool call and result is scored in one fast request, stale ones are dropped or truncated, everything kept stays verbatim.
⭐ 5924 | TypeScript | 4d ago | 65 issues
zai-org/ZCode
(github.com)
Z.ai's coding agent harness. Powerful, intelligent, extensible.
⭐ 5517 | TypeScript | 1d ago | 11 issues
robbietilton/Compositor
(github.com)
The Photoshop alternative for Mac
⭐ 4337 | Swift | 5d ago | 14 issues
mizorewww/laya-mlx
(github.com)
Native MLX runtime for Laya typed decision models — 7–14 ms short decisions on M3 Max. No text generation, PyTorch, or cloud API.
⭐ 3620 | Python | 2d ago | 5 issues
TheoLeeCJ/SemIf
(github.com)
Semantic ifs from open models, on a 3090 at home. Independent; not affiliated with Jev or TypeSafe.
⭐ 3150 | Python | 5d ago | 12 issues
mcncarl/jianying-headless
(github.com)
Private source preview: native Jianying drafts, isolated editing/export, and standalone Agent Skill.
⭐ 2354 | Python | 6d ago | 10 issues
jaredpalmer/kev
(github.com)
tiny Jev-like family of decision models built on top of Qwen3.5 you can train and run on your own
⭐ 2329 | Python | 4d ago | 3 issues
jarrodwatts/jev-trader
(github.com)
One AI trade decision every Monad block. Jev on Kuru MON-USDC.
⭐ 1822 | TypeScript | 5d ago | 4 issues
arXiv Papers
New papers from cs.AI, cs.LG, cs.CL, and stat.ML.
Checked just now
Designer-RSI: Evolving Procedural Memory from User Traffic for Agentic Graphic Design
(arxiv.org)
Hongyang Du et al. | 3d ago |
Cross-sector generalization of accident-process role classification in occupational accident narratives
(arxiv.org)
Aho Yapi et al. | 3d ago |
CodeMidas: Scaling Agentic Coding RL Environments from Code Itself
(arxiv.org)
Bowen Ye et al. | 3d ago |
Value-Sensitive Delegation in Everyday AI Agent Use: Evidence from OpenClaw
(arxiv.org)
Renkai Ma et al. | 3d ago |
BrainWideBench: Benchmarking large-scale pretraining and across-animal transfer in multi-region neural recordings
(arxiv.org)
Alexandre Andre et al. | 3d ago |
Predictable Failure in Multi-Hop Retrieval: Score-Distributional Confidence Scoring and Abstention
(arxiv.org)
Andre Bacellar | 3d ago |
Benchmarking World Models for Continual Learning on Compositional Tasks
(arxiv.org)
Haoyu Zhou et al. | 3d ago |
Particle Competition and Cooperation for Robust Graph Convolutional Network Learning Under Label Noise
(arxiv.org)
Fabricio Breve | 3d ago |
Available Guardrails: Certifying Selective Prediction across ML Systems
(arxiv.org)
Parivesh Priye et al. | 3d ago |
An Interpretable Memory Decision Controller for LLM Agents Based on Three-Signal Complementarity: Decoupling Confidence and Consistency
(arxiv.org)
Yiming Zhang et al. | 3d ago |