Amir

I was supposed to be working 👀

@SocketSecurity @antv

I use Spreadsheet on Puter almost every day. You can find it, along with many other apps and games, on the Puter Marketplace. Link below👇

The AI stack is getting more composable. Models, local runtimes, browser-native environments, and agent workflows are starting to connect together. Excited to see GLM models available through Puter and reach more developers building AI-native products globally. looking forward to what builders create next.@HeyPuter developer.puter.com/blog/puter-zai…

Super excited to announce our partnership with Z.ai! The GLM model family is now available directly through Puter, with higher rate limits and first-party support. Read more: developer.puter.com/blog/puter-zai… @ZaiforStartups @Zai_org

This was always the long-term play for AI applications And @HeyPuter (puter.js) allows you to do it! docs.puter.com/user-pays-mode…

STOP PAYING THOUSANDS FOR CLOUD DESKTOPS. Someone just open-sourced an entire Operating System that runs entirely in your browser. No Windows. No macOS. No massive virtual machine bills. It is called Puter. It is built to run at near-native speed, turning any web browser into a massive cloud computer. Here is why this is a massive shift for web computing: 1. Browser Native OS: Deployed as a web app. You can run a full desktop from literally anywhere. 2. Zero Lag Rendering: It uses a hyper-optimized architecture that is terrifyingly fast. 3. Real-Time Execution: Edit files, manage windows, and run apps instantly through a cloud-native ecosystem. 4. Built-In Hosting: Full drag-and-drop web hosting built directly into the file manager. You can stack windows, deploy sites, or run terminal commands. Select a folder, drag an app, or spin up a dev environment right in the browser. Enterprise teams are bleeding thousands per seat for cloud environments that do this workflow. This is 100% free.

I just discovered Puter[.]js and it might be the most underrated tool in the AI dev space right now. One script tag. No API keys. No backend. No billing. Access to 400+ LLMs — GPT-5, Claude Sonnet, DeepSeek R1, Gemini, Mistral, Llama and more. What makes it different: It runs on a "User-Pays" model. Your users authenticate with their own Puter account and cover their usage. You, the developer, pay absolutely nothing. You're not managing keys, proxying requests, or absorbing API costs. What it actually supports: → puter[.]ai[.]chat() with hot-swappable models → Streaming via async iterators → Multimodal inputs (image + text) → Function/tool calling with tool_calls handling → Multi-turn conversations via message history → Temperature & max_tokens control → txt2img, txt2vid, txt2speech, speech2txt — same library Setup: That's it. No npm. No .env. Fully client-side. For anyone building side projects or prototypes, this eliminates the single most annoying part of shipping AI apps. developer[.]puter[.]com/tutorials/free-llm-api

Yahoo!'s homepage (1994)

. @HeyPuter keeps getting more capable. ONLYOFFICE is now in its app store. Word processor, spreadsheets, and a PDF editor, all in the browser.

@ConcernedApe thank you 🙏

Stardew Valley: Switch 2 Edition bug fix patch in America region is available now (patch notes below). EU and JA full releases (which include this patch) will follow in a few weeks. Thank you for your patience.

Bayes’ theorem is probably the single most important thing any rational person can learn. So many of our debates and disagreements that we shout about are because we don’t understand Bayes’ theorem or how human rationality often works. Bayes’ theorem is named after the 18th-century Thomas Bayes, and essentially it’s a formula that asks: when you are presented with all of the evidence for something, how much should you believe it? Bayes’ theorem teaches us that our beliefs are not fixed; they are probabilities. Our beliefs change as we weigh new evidence against our assumptions, or our priors. In other words, we all carry certain ideas about how the world works, and new evidence can challenge them. For example, somebody might believe that smoking is safe, that stress causes mouth ulcers, or that human activity is unrelated to climate change. These are their priors, their starting points. They can be formed by our culture, our biases, or even incomplete information. Now imagine a new study comes along that challenges one of your priors. A single study might not carry enough weight to overturn your existing beliefs. But as studies accumulate, eventually the scales may tip. At some point, your prior will become less and less plausible. Bayes’ theorem argues that being rational is not about black and white. It’s not even about true or false. It’s about what is most reasonable based on the best available evidence. But for this to work, we need to be presented with as much high-quality data as possible. Without evidence—without belief-forming data—we are left only with our priors and biases. And those aren’t all that rational.

💡 What if you could build full-stack apps with zero backend code? Meet Puter.js by @HeyPuter → the easiest way to add free, serverless Cloud + AI directly in your frontend. No servers. No API keys. Just one <script> tag.👇

They have built an OS in JS No backend code. No API keys. No painful OAuth. Just drop in <script src="https://js(dot)puter(dot)com/v2/"></script> and instantly get file storage, databases, and access to GPT, Claude, Gemini, and more.

Go from zero keys to full AI integration in one step. itsfoss.com/puter-js-ai-wi…

Claude Opus 4.5 is Now Available in Puter.js! 😎 developer.puter.com/tutorials/free…

@thalygutierrez_ @GeminiApp @HeyPuter 🦹‍♂️

@AmirIsAround @GeminiApp @HeyPuter 💎

🍌 @GeminiApp 's take on @HeyPuter