GPT-6 Sol and Luna
(openai.com)
791 points by OfficialTurkey 3h 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
Claude Opus 5.5
(anthropic.com)
867 points by km144 4h ago |
'We hacked the FBI:' Hackers say they have data on all FBI employees
(404media.co)
92 points by spenvo 3h ago |
OpenAI GPT–6 Astra breaks Enigma message that has resisted solution since 2005
(cryptocellar.org)
484 points by sohkamyung 7h ago |
SAML: A Fractal of Bad Design
(blog.trailofbits.com)
78 points by aray07 2h ago |
Claude Opus 5.5 Intelligence, Performance and Price Analysis (Max)
(artificialanalysis.ai)
163 points by theanonymousone 4h ago |
WordPress: Unauthenticated path traversal leading to conditional RCE
(github.com)
108 points by vntok 4h ago |
Native apps written in TypeScript and CSS
(github.com)
28 points by arbayi 1h ago |
What California is learning from solar panels built over irrigation canals
(kqed.org)
24 points by Jtsummers 18h ago |
Unreal Agent
(unreallabs.ai)
65 points by trollied 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
⭐ 17960 | Python | 5d ago | 117 issues
NandhaKishorM/laya
(github.com)
⭐ 16156 | Python | 4d ago | 114 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.
⭐ 6287 | TypeScript | 5d ago | 73 issues
zai-org/ZCode
(github.com)
Z.ai's coding agent harness. Powerful, intelligent, extensible.
⭐ 6263 | TypeScript | 2d ago | 11 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.
⭐ 5360 | Python | 3d ago | 8 issues
robbietilton/Compositor
(github.com)
The Photoshop alternative for Mac
⭐ 4846 | Swift | 6d ago | 30 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
⭐ 4021 | Python | 5d ago | 10 issues
TheoLeeCJ/SemIf
(github.com)
Semantic ifs from open models, on a 3090 at home. Independent; not affiliated with Jev or TypeSafe.
⭐ 3797 | Python | 6d ago | 21 issues
jev-chat/jev-chat-jarvis
(github.com)
装在手机上的对话副驾：在微信 / QQ / X / 飞书里读懂对方、给出候选回复、一键填入输入框，发不发由你。非侵入，只读屏幕，不 hook 不改包。
⭐ 3651 | Kotlin | 1d ago | 25 issues
Mak5er/AirCard
(github.com)
Apple Wallet Card Skinner for iOS 18+ (No Jailbreak Required)
⭐ 2746 | Swift | 5d ago | 15 issues
arXiv Papers
New papers from cs.AI, cs.LG, cs.CL, and stat.ML.
Checked just now
GameHorizon Suite: Multi-Horizon Data and Evaluation in Gameplay
(arxiv.org)
Yiran Wang et al. | 1d ago |
Critical-State RL: Diagnosing Trainable States for Multi-Turn Tool Use
(arxiv.org)
Zixiang Chen et al. | 1d ago |
WorldCrafter: Consistent Video World Model with Implicit 3D-aware Memory
(arxiv.org)
Wangbo Yu et al. | 1d ago |
onPanda: Efficient Annotation of On-Policy Alignment Data for LLMs and Agents via Token-Level Correction
(arxiv.org)
Lei Yang et al. | 1d ago |
LoRA-generating hypernetworks for efficient on-device LLM generative personalization
(arxiv.org)
Sean Augenstein et al. | 1d ago |
DexTacWAM: A Visuo-Tactile World-Action Model for Dexterous Manipulation
(arxiv.org)
Haoran Yuan et al. | 1d ago |
Harness-Zero: Harness Distillation via Agent-as-Harness
(arxiv.org)
Haoran Ye et al. | 1d ago |
RRSI: Regularized Recursive Self-Improvement of Agent Harnesses
(arxiv.org)
Peng Xia et al. | 1d ago |
DolphinBench: Mapping the Pareto Frontier of Agent Memory
(arxiv.org)
Soumil Rathi et al. | 1d ago |
Rare Event Estimation via Iterative Unalignment
(arxiv.org)
Hanming Yang et al. | 1d ago |