New in Reader: Ghostreader v3 on web! Chat with... any document, now: * Much faster * Links to the exact sources in your document * Preset prompts (eg summarize, lookup) built inshow more

New on Deepvue · Prompt Library with pre-built prompts... for market analysis, themes, stock analysis and earnings · @ mentions to reference any watchlist or screener preset as context · / slash commands to search and run prompts instantly Entire research workflow in one place.show more

Upload PDFs Now ✨ 📄 Upload whitepapers, reports, or... any document and ask June to summarize or analyze it 🔐 Your files stay private and they are never stored on our side. Try it now and get deep insights in seconds.show more

Perplexity Email Assistant can now process image and file... attachments. Starting today, you can send your Assistant any document and have it: - understand the document - summarize its contents - add relevant dates to your calendar Here’s how I use it to add dates from a syllabus to my calendar:show more

we built a new way to index and chat... with any PDF. introducing tree-guided hybrid agentic search. Nozomio Labs indexes PDFs into document trees, reasons over structure, and uses agents to retrieve precise answers in minutes. we’re seeing strong performance on financebench and other benchmarks. curious what you think!show more

You can now embed your connectors directly inside web... apps built by Perplexity Computer. To demonstrate, we built a document editor that uses the Google Docs and Notion connectors to fetch, edit, and save docs across both.show more

3. Summarize and explain web pages Copilot can summarize... a long web page in just a few words. It's also the best way to explain certain terms or concepts you don't understand. - Go to the web page you want - Click on the Copilot icon - Enter your prompt, specifying that you're talking about the page you're currently on Prompt: "Summarize this web page in 5 short bullet points, then explain the technical terms in simple words". Note: You can also generate new content from the web page. For example, ask Copilot to "Write a new blog post introduction that summarizes this information".show more

In a 1984 CIA remote viewing session document, the... viewer attempted to see Mars approximately 1 million years B.C. Based on the document, I had Grok feed itself imagery prompts to re-create it. If nothing else, it's awesome to see what AI thinks it describes. More below...show more

NEW in Dia: Inline Browsing Starting today, when you... click links in a chat with Dia, the webpages will automatically render inline. No more context switching. No more tab mess. Now you can browse the web without breaking the flow of your conversation:show more

I was nerd sniped into integrating this with ProseMirror... to enable the "holy grail" of rich text editing on the web. Document layout with page breaks! More to come... but back to my birthday weekend. Online demo in threadshow more

DOM3 is made from HTML, CSS and Javascript, closer... to a document than a canvas. It's a strange contemporary material that shapes much of our digital lives. The rhythm of endless creation and deletion in DOM3 is a self-driving version of what happens when you browse the web. "The Document Object Model (DOM) connects web pages to scripts or programming languages by representing the structure of a document—such as the HTML representing a web page—in memory." A html element, and a rectangle on a canvas, are not the same thing. It's a different material. Even if it all ends up controlling the same pixels, the process is different. The html element kind of actually exists, in this abstract context of a document object model. And in memory, in the moment. If it was possible to measure its weight, it would be heavier than a pixel on a canvas.show more

📈 Copilot in Word gives you more control to... fine-tune your document. Easily edit text, lists, and tables like a pro. It's like an assistant making your job easier. Available on the web and desktop: #AIshow more

You’re busy. We get it. You don’t have time... to open every random file shared with you in Google Chat. That’s why Gemini will summarize any Doc, Sheet or Slides asset shared in Chat, with a single click. Now that’s helpful! 👉show more

8. Write an updated essay Now ChatGPT can give... you links and references for your essay. Prompt → Write an essay on the Napoleonic Wars citing your sources with links. Add titles in markdown.show more

You can now open your Figma files in Sketch... 📂 Head to File > Open Local Document, choose your .fig file and we’ll handle the rest 💪show more

A New Era with V3🪄 V3's new engine introduces... significant advancements in output generation. Unlike V2, where the multi-model system processed prompts to produce a single output, V3 is designed to generate multiple outputs and logically link them together. This enhancement effectively removes limitations on output size, enabling more complex and expansive results. Key Features Seamless Multi-Output Generation: V3 has been trained to generate separate outputs and connect them logically. This advancement ensures that there are no longer any limitations on output size. Intelligent Image Creation: V3 improves image generation with better tools, allowing the AI to create as many images as needed and place them within the project’s context. It supports various formats like PNG, JPEG, SVG, and GLB. Web-Integrated Intelligence: V3 can now search the web for documentation and data, providing real-time context and up-to-date references. For example, if you run a restaurant and want to update your website, simply ask Alchemist AI to “generate this website in a more modern style,” and it will update all content accordingly. Improved Creativity and Output Quality: V3's creative capacity has significantly increased. Simple prompts now generate more complete and refined results, with the system efficiently combining multiple elements into cohesive outputs.show more

Proud to say that I made the new document... UI for Forsaken in the jane doe update :) Forsaken #roblox #robloxdev #forsakenshow more

Do you want me to document everything that happens... in my house with the security camera? 📽️🙈show more

We're launching 5x faster document parsing in the Firecrawl... MCP. Use /parse to turn PDFs, spreadsheets, and docs into LLM-ready data for your agents. Supports running locally or with our hosted MCP server. Try it out today with no API key required on our free tier!show more

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.show more