Devon @ForagerForLife

x.com/i/article/2059…

Wild what's possible now: I can ship a 3D experience prototype to a museum in a single afternoon. Everything coded and generated with Omma, leveraging AI to iterate fast. 3D models generated in Omma. Scene built on top of Three.js. Prompted for dissolving shaders + particle systems?

This feels illegal… You can now use Claude to clean up your digital footprint in just hours, it can: • completely erase your history • clean up old accounts • remove broker listings • reduce personal data exposure Step-by-step powerful mega prompts below:

Ask Claude to document and describe the main flows in your app and output in a single page html + json data file. Incredibly useful for humans and the JSON file is very useful for explaining the flow to the LLM when working on new features/bugfixes.

x.com/i/article/2052…

Bored of boring flat heatmaps? Introducing Topographical Explorer that turns any country into a real-time tactile landscape Search any country → watch real elevation data come alive as thousands of satisfying 3D blocks. Built entirely client-side with: - React Three Fiber + Three.js - AWS Terrain Tiles + OpenStreetMap - Real-time boundary @threejs @reactthreefiber #DataVisualization #Geospatial #CreativeCoding #BuildInPublic

THE CREATOR OF OBSIDIAN JUST TURNED YOUR NOTE VAULT INTO AN AI AGENT. Not a plugin. Not an integration. A full agent skills system that teaches Claude Code, Codex, and OpenCode to READ, WRITE, and REASON inside your Obsidian vault like a power user. 27,000 GitHub stars in days. Here is what shipped at launch: obsidian-markdown — wikilinks, embeds, callouts, properties, the full Obsidian flavor Claude now understands natively. obsidian-bases — Claude can create .base files with views, filters, formulas, and summaries. json-canvas — Claude builds .canvas files with nodes, edges, groups, and connections. obsidian-cli — Claude controls your vault, develops plugins and themes directly from the terminal. defuddle — strips web pages into clean Markdown so you stop burning tokens on clutter. Install the whole thing in one line: npx skills add github.com/kepano/obsidia… Then connect it to Claude Code, Codex, or OpenCode. That is it. Your second brain now has an agent inside it that understands how Obsidian actually works. Not a generic AI that pastes text into files. An agent that knows what a wikilink is. What a callout is. What a canvas is. Built on the open Agent Skills spec. MIT license. Free forever. The gap between people using Obsidian as a note app and people using it as an AI operating system just got wider. Bookmark this before you open your vault today. Follow @cyrilXBT for every build that changes how Obsidian and Claude work together.

ANDREJ KARPATHY DESCRIBED THE PERFECT AI KNOWLEDGE SYSTEM. Someone built it inside Obsidian. Claude Code x Obsidian. Under 10 minutes to set up. YOUR VAULT WRITES AND ORGANIZES ITSELF while you sleep. Based on Karpathy's own LLM Wiki pattern. FREE. Here is what is going on. Everyone who uses Obsidian knows the problem. Notes go in. Connections never get made. Six months later you have hundreds of orphaned files, zero cross-references, and a second brain that feels more like a digital junk drawer. The system only works if you maintain it. Nobody maintains it. This solves that entirely. It is called claude-obsidian. You clone it, run one setup script, open it in Obsidian, type /wiki in Claude Code, and from that point forward Claude does all the organizing, filing, cross-referencing, and maintenance. You just drop things in and ask questions. What makes it different from every other Obsidian AI plugin is this. Other plugins answer questions about your existing notes. This one creates, organizes, evolves, and maintains the notes autonomously. There is a difference between a chat interface and a knowledge engine. ↳ drop any source and Claude creates 8 to 15 structured wiki pages automatically ↳ every new page gets cross-referenced against everything already in the vault ↳ contradictions get flagged with callouts so you always know when sources disagree ↳ /autoresearch runs a 3 round web research loop, finds gaps, fills them, files everything ↳ /save turns any Claude conversation directly into a permanent wiki note ↳ hot cache updates every session so Claude never needs you to re-explain context again ↳ lint command finds orphans, dead links, and stale claims without you touching anything The hot cache is the part most people miss. At the end of every session Claude writes a compact summary of recent context. Next session it reads that first. You never waste 10 minutes rebuilding context again. 10 skills. Multi-agent support. MIT license. Free forever.

use at your own risk: madera.app (can’t wait to see what yall build)

xavier (jack) @KMkota0

2 months ago

i just wanted custom cabinets this escalated quickly...

121 244 5K 813K 3K

SOMEONE VIBE CODED A LIVE TOOL TO TRY AND GUESS SATOSHI’S PRIVATE KEYS THIS IS WILD

AI BASKETBALL ANALYSIS. A FULL COMPUTER VISION SYSTEM. BUILT ON YOLO, OPENCV, AND PYTHON. Take any NBA broadcast. Any camera angle. Any resolution. Feed it into the system. YOLO finds every player and the ball. Frame by frame. No manual annotation. No pre-labeled data.The model just sees the court and understands it. Zero-shot classification looks at jersey pixels and decides who plays for whom. Two teams separated in milliseconds. Without ever being told the team names. But here's where it gets wild. Court keypoint detection identifies the geometry of the playing surface. Homography transforms the broadcast camera into a top-down tactical map. Real meters. Real coordinates. From a flat 2D video. Now every player has a position on a real court. Every movement becomes a data point. Every pass becomes a vector. Speed. Distance. Possession time. Pass networks. All extracted from nothing but pixels. No GPS. No chips in the ball. No million-dollar Second Spectrum setup. A Python script and a GPU. The full pipeline is open source. The tutorial walks through every line of code. From detection to transformation to analytics output. Teams used to pay six figures for this data. Now you build it in an afternoon. Computer vision didn't just enter basketball. It democratized it.

zostaff @zostaff

3 months ago

x.com/i/article/2046…

27 49 568 1.1M 2K

Lovable has a mass data breach affecting every project created before november 2025. I made a lovable account today and was able to access another users source code, database credentials, AI chat histories, and customer data are all readable by any free account. nvidia, microsoft, uber, and spotify employees all have accounts. the bug was reported 48 days ago. its not fixed. They marked it as duplicate and left it open.

keyboard_arrow_left Previous keyboard_arrow_right Next

A CEO ASKED CHATGPT HOW TO STEAL $250M FROM GAME DEVS. BIG MISTAKE → Krafton buys Subnautica studio for $500M → Promises $250M bonus if the sequel sells well → Sequel is about to sell really well → CEO panics, asks ChatGPT how to get out of it → GPT writes him a takeover plan called "Project X" → CEO ignores his lawyers and executes the plan → Delaware court reads his ChatGPT logs at trial → Judge calls it out by name in the ruling → CEO loses. Devs get reinstated. $250M still owed. Conversations with AI are not privileged. Executives haven't figured this out yet.

Nathan Calvin @_NathanCalvin

3 months ago

The CEO of Krafton (creator of PUBG) asked ChatGPT to create a "corporate takeover strategy" to prevent a company they acquired from hitting a revenue target within a certain time window (which would trigger an additional payout). ChatGPT (against his lawyer's advice) suggested

133 2K 18K 2.1M 4K

Liquid mask on hover. Move your cursor — watch the image melt away. Built this in @framer + @hiunicornstudio this weekend. More satisfying than I expected 😶 Live demo in the replies 👇

Introducing Triggered Agents AI agents that take action when things happen. Shopify stock low → Adaptive finds the supplier and drafts the PO. Stripe payment fails → Adaptive reads the history and starts recovery. GitHub PR opened → agent reviews the diff and flags the risk. We want you to try it for free. Share a use case in the comments to get $50 of Adaptive credits.

⟨0⁺| Φ* |0⁻⟩

Do you even understand what this means? An open source model just released that is: • Outperforms models 20x its size • Can run on a base model Mac Mini • Is AMERICAN 🇺🇸 If you have a base model Mac Mini you can have unlimited super intelligence on your desk. For free. Sonnet 4.5 was released 5 months ago In 5 months that level of intelligence went from frontier to free on your desk And not only that, can run on any basically any computer out there If you have even a remotely modern computer, do the following immediately: 1. Download LM Studio 2. Go to your OpenClaw and ask which of these new Gemma 4 models is best for your hardware 3. Have it walk you through downloading and loading it 4. Build apps with it knowing you are using your own personal, private super intelligence on your desk The people denying this is the future are so beyond lost.

Google DeepMind @GoogleDeepMind

3 months ago

Meet Gemma 4: our new family of open models you can run on your own hardware. Built for advanced reasoning and agentic workflows, we’re releasing them under an Apache 2.0 license. Here’s what’s new 🧵

368 1K 9K 4.0M 6K

Introducing render-json The Generative JSON framework. 1. Point it at anything 2. It generates JSON 3. That's it Apps, games, and more. If it exists, it can be converted into a JSON spec. 𝚗𝚙𝚖 𝚒 @𝚓𝚜𝚘𝚗-𝚛𝚎𝚗𝚍𝚎𝚛/𝚛𝚎𝚗𝚍𝚎𝚛-𝚓𝚜𝚘𝚗

Claude Code 用户每天被吃掉的 token 里，有多少是废话？ 有人做了个实验：往项目根目录放一个 9 行的 CLAUDE.md，输出 token 直降 63%。仓库叫 claude-token-efficient，两天 1900 star。 原理极其简单——Claude 默认回复充斥着 "Sure! Great question!" 开头、"I hope this helps!" 结尾、复述你的问题、给你没要求的建议、对明显错误的观点先说一句 "You're absolutely right"。这些「礼貌」全部消耗 token，信息量为零。 这 9 行就是完整的 CLAUDE.md： ``` - Think before acting. Read existing files before writing code. - Be concise in output but thorough in reasoning. - Prefer editing over rewriting whole files. - Do not re-read files you have already read. - Test your code before declaring done. - No sycophantic openers or closing fluff. - Keep solutions simple and direct. - User instructions always override this file. ``` 实测对比： → 代码 review：120 词 → 30 词（-75%） → 概念解释：180 词 → 65 词（-64%） → 纠正错误事实：55 词 → 20 词（-64%） → 信息零损失 第三方独立基准测试验证：编码任务总成本省 17.4%。最极端的 v8 配置只有 7 行规则 + 20 次工具调用预算，逼 Claude 提前规划而不是边试边改。 但作者很坦诚地指出了适用边界：这个文件本身每轮对话都会作为输入 token 加载。只有高频场景——Agent 循环、自动化流水线、日均 100+ prompt——才有净收益。偶尔聊两句反而更贵。 本质上是一个「用输入 token 换输出 token」的游戏。在配额日益紧张的 2026，这个权衡值得认真算一笔账。 github.com/drona23/claude…