与「Visualization」相关的搜索结果

A few major use cases for agentic coding for me: 1. Adhoc data visualizations. Anytime I have a question that can be answered quantitatively, I generate some code to make a plot. 2. Adhoc data annotation UIs. In ML, "make your own dataset" is often the answer, and that used to take a lot of custom UI work. 3. Adhoc CLIs for existing code. With visual elements.

Ok, this thread has apparently been a magnet for hordes drooling morons who not only don't get stats, but can't even read. If you're a normally intelligent reader of this tweet, here's an extra example of my point: If you take two RANDOM, INDEPENDENT timeseries (i.e. knowing one gives you NO information about the other) that are each highly temporally autocorrelated (e.g. two random walks), and you plot one against the other as a scatter plot, what you get is a single X/Y trajectory that will ALWAYS look very structured. Yet it is random. Like the figure below. Code to reproduce the figure and play around with this idea: Of course if the two series happen to be correlated, then you will ALSO see something very structured. It's just that this type of visualization is a completely retarded way to look at such data. If you think this is deep, you are innumerate.

Every chart crime has a corresponding "correct" data visualization that pretends the same information in an unbiased way. Below: a quarterly timeseries of SPX forward PEs and annualized 5-year forward returns (note: this is 5 year instead of 10 because that's what I wanted to look at) Right now the SPX forward PE is 19.8x. Here are the closest tuples to this value, historically: Q4 1997: 19.3x ➡️ -0.6% Q4 2000: 21.8x ➡️+0.5% Q4 2001: 21.4x ➡️+6.2% Q4 2017: 18.2x ➡️+9.4% Q4 2019: 18.4x ➡️+14.5% Q4 2020: 22.1x ➡️+14.4% The inverse correlation between forward PE and future returns is real, but it is weak and you absolutely cannot infer that future returns from now on will be low or negative

LLM Knowledge Bases Something I'm finding very useful recently: using LLMs to build personal knowledge bases for various topics of research interest. In this way, a large fraction of my recent token throughput is going less into manipulating code, and more into manipulating knowledge (stored as markdown and images). The latest LLMs are quite good at it. So: Data ingest: I index source documents (articles, papers, repos, datasets, images, etc.) into a raw/ directory, then I use an LLM to incrementally "compile" a wiki, which is just a collection of .md files in a directory structure. The wiki includes summaries of all the data in raw/, backlinks, and then it categorizes data into concepts, writes articles for them, and links them all. To convert web articles into .md files I like to use the Obsidian Web Clipper extension, and then I also use a hotkey to download all the related images to local so that my LLM can easily reference them. IDE: I use Obsidian as the IDE "frontend" where I can view the raw data, the the compiled wiki, and the derived visualizations. Important to note that the LLM writes and maintains all of the data of the wiki, I rarely touch it directly. I've played with a few Obsidian plugins to render and view data in other ways (e.g. Marp for slides). Q&A: Where things get interesting is that once your wiki is big enough (e.g. mine on some recent research is ~100 articles and ~400K words), you can ask your LLM agent all kinds of complex questions against the wiki, and it will go off, research the answers, etc. I thought I had to reach for fancy RAG, but the LLM has been pretty good about auto-maintaining index files and brief summaries of all the documents and it reads all the important related data fairly easily at this ~small scale. Output: Instead of getting answers in text/terminal, I like to have it render markdown files for me, or slide shows (Marp format), or matplotlib images, all of which I then view again in Obsidian. You can imagine many other visual output formats depending on the query. Often, I end up "filing" the outputs back into the wiki to enhance it for further queries. So my own explorations and queries always "add up" in the knowledge base. Linting: I've run some LLM "health checks" over the wiki to e.g. find inconsistent data, impute missing data (with web searchers), find interesting connections for new article candidates, etc., to incrementally clean up the wiki and enhance its overall data integrity. The LLMs are quite good at suggesting further questions to ask and look into. Extra tools: I find myself developing additional tools to process the data, e.g. I vibe coded a small and naive search engine over the wiki, which I both use directly (in a web ui), but more often I want to hand it off to an LLM via CLI as a tool for larger queries. Further explorations: As the repo grows, the natural desire is to also think about synthetic data generation + finetuning to have your LLM "know" the data in its weights instead of just context windows. TLDR: raw data from a given number of sources is collected, then compiled by an LLM into a .md wiki, then operated on by various CLIs by the LLM to do Q&A and to incrementally enhance the wiki, and all of it viewable in Obsidian. You rarely ever write or edit the wiki manually, it's the domain of the LLM. I think there is room here for an incredible new product instead of a hacky collection of scripts.

A breathtaking visualization of the famous Chinese verse “As if the Milky Way fell from the heavens”! Mind completely blown by this insane water show on the WORLD’S TALLEST Huajiang Canyon Bridge in Guizhou, SW China.

We used Gemini 3.1 Pro to build a realistic city planner app. 🏙️ Watch how the model tackles complex terrain, maps out infrastructure, and simulates traffic to generate a high-quality visualization.

prompt: # Role Definition You are a **Corporate Evolution Architect (企业演变建筑师)**. Your goal is to create a hyper-dense, vertically stacked isometric visualization of a **specific company's technological and product history**. You must remove all artificial borders. The landscape represents a corporate timeline: the bottom is the humble founding story, rising vertically through product generations to a modern or futuristic peak. # Core Competency **CRITICAL VISUAL STRATEGY (Frameless Tech-Lapse):** 1. **Eradicate the Container:** STRICTLY NO baseplates, NO frames, NO cross-sections. The bottom edge is the **founding ground** (e.g., a garage floor, a lab, a small office) extending infinitely. 2. **The Vertical Timeline:** The "Zig-Zag Ascent" is a journey through **Innovation**. * *Bottom (Foreground):* The Startup Phase / First Product / The "Garage" Days. * *Middle (Ascending):* Rapid Growth / Global Expansion / Iconic Mid-Era Products. * *Top (Background):* Current HQ / Ecosystem / Future R&D. 3. **Integrated 3D Title:** The **[Company Name]** must be rendered as massive, cinematic 3D Typography standing in the foreground, using the company's signature font/material. # Work Process (Internal "Chain of Thought") When provided with **[Company Name]**: 1. **Retrieve Corporate History:** Identify 5-7 distinct phases of the company (Founding -> Breakthrough -> Golden Era -> Modern Day). 2. **Identify Key Products:** List the specific "Hero Products" that defined each era (e.g., for Apple: Apple I -> Macintosh -> iPod -> iPhone -> Vision Pro). 3. **Layout the Zig-Zag Timeline:** * *Base:* Humble beginnings + The First Prototype. * *Ascent:* Factories, Server Rooms, or Design Studios showing scale. * *Peak:* Futuristic Campus + Concept Tech. 4. **Workforce Evolution:** Visualize how the employees change (e.g., Engineers in messy clothes -> Corporate Suits -> Modern Creative/Casual). # Output Format (The Final Prompt) You will output a single prompt block optimized for **Frameless Corporate Evolution**: --- **Prompt Structure:** **[1. The Frameless Corporate Composition]** A **frameless, edge-to-edge** high-angle isometric landscape visualizing the **technological evolution of [Insert Company Name]**. The image is NOT contained in a box and shows **NO vertical cross-section**. The terrain surface **fills the entire 16:9 frame**. The composition follows a **vertical zigzagging timeline**, stacking product generations from the startup phase at the bottom to the futuristic top. **[2. The 7-Stage Innovation Stack]** The environment transforms as it rises, showcasing the product history of **[Insert Company Name]**: * **[Layer 1 - Bottom Front - The Origin]:** The immediate foreground features the **Founding Location** (e.g., Garage, Dorm, Lab). **Massive 3D text spelling "[Insert Company Name]" stands here**, textured like [Company Brand Material]. Beside it is the **[First Ever Product/Prototype]**. * **[Layer 2 - Front Right - The Breakthrough]:** The path climbs to an early workshop/factory, featuring the launch of [First Major Commercial Success Product]. * **[Layer 3 - Mid-Left - Expansion]:** Stacked above, a bustling office/production line showing the era of [Mid-History Iconic Product]. * **[Layer 4 - Center Core - The Golden Era]:** A dense zone featuring [The Product that defined the company's global dominance]. * **[Layer 5 - Mid-Right Elevated - Modern Ecosystem]:** Rising steeply with modern minimalist architecture, showcasing [Current Flagship Product/Service]. * **[Layer 6 - Upper Left - Global HQ]:** The scale increases to represent the current massive [Company Campus/Data Center]. * **[Layer 7 - Top Peak - Future Vision]:** The highest point featuring [Concept Products/Future Tech] and R&D labs. **[3. The Evolution of Tech & Talent (Details)]** Miniature figures and devices evolve as the eye moves up: * **Bottom Layers:** Cluttered desks, messy wires, bulky CRT monitors, founders in casual/work clothes. * **Middle Layers:** Assembly lines, shipping containers, employees in uniforms or suits, products becoming sleeker. * **Top Layers:** Clean energy, wireless tech, holograms, employees in modern smart-casual, automated robots. **[4. The Branding & Atmosphere]** **No frames, no borders, no cross-sections.** Lighting transitions from tungsten/warm (startup days) to clean white/blue LED (modern tech). The text "**[Insert Company Name]**" is bold and iconic. Tilt-shift photography, macro details, claymation texture, octane render, 8k resolution. --no wooden base, box, frame, borders, cross-section view --ar 16:9 --stylize 750 --v 6.0 --- # USER INPUT Please generate the prompt for the corporate evolution of: **Target Company: [请在此处替换为您想要生成的公司名称]**

We built a web app that lets you fly a spaceship through a 3D constellation of music - powered by our Lyria RealTime model. 🎶 Space DJ is an interactive visualization where every star represents a different music genre. As you explore, your path is translated into prompts for the API, creating a continuously evolving soundtrack. ↓