Daily AI brief
Daily AI brief: November 14, 2026
The AI brief for November 14, 2026: 10 new repos, 8 stories people are discussing, 8 new papers, led by alexeyw/lot-map. Each item links to its source.
What moved in AI over the last day, pulled from GitHub, Hacker News and arXiv at 12:39 PM GMT+2. Every item links to its source. Repo descriptions are the projects' own words; star and point counts are as of that time.
Repos to watch
New open-source projects created since November 7, tagged llm or ai-agents on GitHub, ranked by stars.
- alexeyw/lot-map · 769 stars · TypeScript. A live map beside the chat that shows what Claude Code is doing: tool calls, model steps, hooks, skills and subagents light up as they happen. Local only, in...
- Dodaios/ste80-humanizer · 498 stars · Python. STE80 Humanizer: agent skill that removes AI tells and rewrites text 80% of the way to ASD-STE100 (Simplified Technical English), the method Andrej Karpathy...
- op7418/guizang-game-skill · 334 stars · JavaScript. 歸藏 Game Skill:让 AI 从零做出能在浏览器里玩的 3D 动作游戏,附可玩演示《雾锁山门》。Agent skill for Claude Code / Codex that builds a playable browser 3D action game with AI-generated assets...
- berkantay/gpucanvas · 270 stars · TypeScript. Put thousands of live DOM nodes on an infinite canvas: the GPU draws them, an editor selects, moves and resizes them, shaders and transitions run on them, and...
- AdmiralEmporium/ai--manus · 266 stars. AI Manus is a general-purpose AI Agent system that supports running various tools and operations in a sandbox environment.
- TorusBarbarianMap9/ai--manus · 266 stars. AI Manus is a general-purpose AI Agent system that supports running various tools and operations in a sandbox environment.
- BarrierCenter/ai--manus · 266 stars. AI Manus is a general-purpose AI Agent system that supports running various tools and operations in a sandbox environment.
- TealAgentRevive/ai--manus · 266 stars. AI Manus is a general-purpose AI Agent system that supports running various tools and operations in a sandbox environment.
- Aspectnisafeguard/ai--manus · 266 stars. AI Manus is a general-purpose AI Agent system that supports running various tools and operations in a sandbox environment.
- SortGuardian/ai--manus · 266 stars. AI Manus is a general-purpose AI Agent system that supports running various tools and operations in a sandbox environment.
What people are talking about
The most upvoted AI stories on Hacker News in the past 24 hours.
- Nvidia allegedly engineered scarcity by funding AI startups to buy its GPUs (techpowerup.com) · 592 points · 343 comments
- AI is destroying the trust between writers and readers (theatlantic.com) · 341 points · 206 comments
- Jonathan Blow, If AI solved coding, why is my software still the same? video (youtube.com) · 302 points · 366 comments
- No AI Slop: A Manifesto (slopmanifesto.com) · 199 points · 115 comments
- Why is Google cutting off Search from AI-free schools? Here are some theories (text.npr.org) · 185 points · 174 comments
- Anthropic upgrades Claude Code Projects to run parallel AI workers (claude.com) · 88 points · 82 comments
- The avalanche that hit math is coming for AI development (dwarkesh.com) · 63 points · 104 comments
- Are we just going to ignore that books are destroyed for AI? (forbes.com) · 56 points · 62 comments
New research
The latest papers submitted to arXiv's artificial intelligence category. Preprints are not peer reviewed.
- AgentSSL: Can MLE Agents Leverage Unlabeled Data? · Ethan Lin, Akanksha Sarkar, Ziang Liu and others. From the abstract: "Applying machine learning systems to new domains introduces bottlenecks in both labeled data acquisition..."
- CoReMem: Cost-Internalizing Memory for Successive Coding Tasks with Prospective Valuation · Peiwen Li, Harshit Verma, Sophia Zhou and others
- Sketching Language Models for Context Attribution · Christopher Liaw, Aranyak Mehta, Grigoris Velegkas and others
- Classical Energies Learn to Reason 1,000x Faster than Looped Models · Benjamin Hoover, Hugh Blayney, James C. R. Whittington
- Consistent Video-to-Video Translation via Explicit Correspondences · Gaurav Parmar, Zhengqi Li, Richard Zhang and others
- Goal Encoding in LLMs · Arnab Sen Sharma, Eric Todd, Sheridan Feucht and others
- Metal Sandbox: Isolated Execution and Command Scheduling for GPU Coding Agents on Apple Silicon · Haozhe Wang, Lina Chen, Fanqi Wan and others
- Synthesis Smuggling: Maliciously Hiding Inferred Personal Attributes in LLM Outputs · Gautam Galada, Supreeth Shastri, Sagnik Ray Choudhury
