News updates

By Ruth Maclean and Saikou Jammeh from NYT World https://ift.tt/vPUsymF via IFTTT

By Lydia DePillis from NYT En español https://ift.tt/afb2YEi via IFTTT

By William B. Davis, Madison Dong, Judson Jones, John Keefe, Joey K. Lee and Bea Malsky from NYT Weather https://ift.tt/ZbhF9nr via IFTTT

By Brooks Barnes from NYT Business https://ift.tt/c5hbQka via IFTTT

Show HN: A Firefox extension to avoid distractions https://ift.tt/kTauHbB September 28, 2025 at 11:10PM

By Natan Odenheimer from NYT World https://ift.tt/2INHTmd via IFTTT

By Ashley Ahn from NYT En español https://ift.tt/RieCKJ1 via IFTTT

By Colin Moynihan from NYT Arts https://ift.tt/7HvGWBT via IFTTT

By Unknown Author from NYT New York https://ift.tt/bgKqeoH via IFTTT

By Text by Katrina Miller from NYT Science https://ift.tt/Hg9JqDM via IFTTT

By Jazmine Ulloa from NYT U.S. https://ift.tt/mBIsD9G via IFTTT

Show HN: Dayflow – A git log for your day Hi HN! I've been building Dayflow, a macOS app that automatically tracks what you're actually working on (not just which apps you have open). Here's what it does: - It creates a semantic timeline of your day; - It does it by understanding the content on your screen (with local or cloud VLMs); - This allows you to see exactly where your time went without any manual logging. Traditional time trackers tell you "3 hours in Chrome" which is not very helpful. Dayflow actually understands if you're reading documentation, debugging code, or scrolling HN. Instead of "Chrome: 3 hours", you get "Reviewed PR comments: 45min", "Read HN thread about Rust: 20min", "Debugged auth flow: 1.5hr". I was an early Rewind user but rarely used the retrieval feature. I built Dayflow because I saw other interesting uses for screen data. I find that it helps me stay on track while working - I check it ever...

By Florence Fabricant from NYT Food https://ift.tt/l1E9YJb via IFTTT

By Chevaz Clarke from NYT U.S. https://ift.tt/eE4C8KJ via IFTTT

Show HN: Chat with Any YouTube Video I built a Chrome extension that lets you chat with the transcript of any YouTube video. Instead of sitting through like a 2 hour video, you can just ask a question and get an instant answer. The Problem: I built it mainly for myself: I often watch long-form videos like lectures or tutorials on YouTube, and I want a fast way to extract the information I need without scrubbing through timestamps or rewatching sections. For example, I recently used it with a 3.5-hour lecture and got the exact answers to my questions in seconds. Another example is that nowadays YouTubers often create videos around one or two key ideas, and I can now figure out whether a video is worth watching by asking what those key ideas are in advance. How it works: 1. The extension gets the video transcript. 2. An AI model summarises it, and makes the content ready for chat 3. You can switch between chat mode and auto-generated summaries depending on how deep you want to go. What’s...

By Bhadra Sharma from NYT World https://ift.tt/V81pNgf via IFTTT

By Hilary Howard from NYT New York https://ift.tt/z7fcg3d via IFTTT

Show HN: Rustchain – Rust toolchain AI agent framework universal transpilation https://rustchain.dev September 20, 2025 at 11:59PM

By Maia Coleman from NYT New York https://ift.tt/3lK0GSq via IFTTT

Show HN: Little Fluffy Clouds: Combine a bunch of small adjacent networks https://ift.tt/r7MXEfV September 20, 2025 at 08:00PM

By Richard Sandomir from NYT Books https://ift.tt/yC6FXiN via IFTTT

Show HN: RustNet, a network monitoring TUI with process identification Hi HN! I built RustNet, a Terminal UI based network monitor written in Rust that shows real-time connections with process identification and protocol detection. What may make it interesting: • Deep packet inspection for HTTP, HTTPS/TLS (with SNI), DNS, and QUIC protocol detection • Process identification using eBPF on Linux (experimental) and PKTAP on macOS which does also catch short-lived processes that polling procfs or lsof would miss • Multi-threaded packet processing with lock-free data structures for the UI • Cross-platform (Linux, macOS, Windows but process identification so far only on Linux/macOS) The eBPF implementation was a bit more tricky to implement than using PKTAP, but it was very interesting to learn about how to hook into tcp_connect, udp_sendmsg, etc. in order to catch process info before connections disappear. I built this as a lightweight Wireshark alternative for quick TUI based network inspe...

By The Learning Network from NYT The Learning Network https://ift.tt/eHYT82h via IFTTT

Show HN: SandBox – AI agents simulating possible futures Hi HN, I’ve been working on SandBox, a project that lets you explore possible futures using autonomous AI agents. You can build scenarios (environmental, social, governance, etc.), make decisions, and see how things might unfold under different paths. Some of the things you can do: Generate speculative news and events under your scenario settings Visualize how small decisions ripple over time Run multiple agent-based simulations in parallel Built with Python, LangGraph + Azure OpenAI, plus a front-end for visualization. Still in active development; feedback, critiques, ideas & contributions are very welcome. Live demo: https://sandboxes.live/ Github: https://ift.tt/DZUq9R6 If you like it, a helps me know this is worth pushing further. Thanks! https://ift.tt/DZUq9R6 September 18, 2025 at 10:37PM

Show HN: One prompt generates an app with its own database Hey HN, manyminiapps is the world first massively multiplayer online mini app builder (MMOMA) *Here’s what it does:* You load the page. You write 1 prompt and you get a mini app back in under 2 minutes. There’s no sign up, and you can see what everyone’s creating in real-time! Each mini app comes with it’s own database and backend, so you can build shareable apps that save data. *What’s different* There are a lot of app builders that promise you’ll build production software for others. But we think true production software can take a long time to get right. Even if you don’t need to program there’s a lot of work involved. What if we turned the promise around? Instead of “you vibe code software companies”, it’s “you build fun software for yourself”. If you cut the problem right, LLMs as they are today can already deliver personal software. manyminiapps is meant to be an experiment to demonstrate this. You may wonder: do you real...

By Luis Ferré-Sadurní from NYT New York https://ift.tt/5BAbZUX via IFTTT

Show HN: Web-based 2D geometry calculator I often find myself trying to solve a geometry problem where the constraints are really simple to understand, but solving it algebraic is really hard and tedious. I built this whole thing from scratch with Claude Code. It's my first time trying it and I literally did not write a single line of code... That said, it still would be hard build this as a novice. I had to guide things along the happy path, but it saved me a ton of time! The code is open source! Let me know if you run into any issues. https://ccorcos.github.io/geocalc/ September 17, 2025 at 10:18PM

By Florence Fabricant, Becky Hughes and Luke Fortney from NYT Food https://ift.tt/m2VWatX via IFTTT

Show HN: AI Code Detector – detect AI-generated code with 95% accuracy Hey HN, I’m Henry, cofounder and CTO at Span ( https://span.app/ ). Today we’re launching AI Code Detector, an AI code detection tool you can try in your browser. The explosion of AI generated code has created some weird problems for engineering orgs. Tools like Cursor and Copilot are used by virtually every org on the planet – but each codegen tool has its own idiosyncratic way of reporting usage. Some don’t report usage at all. Our view is that token spend will start competing with payroll spend as AI becomes more deeply ingrained in how we build software, so understanding how to drive proficiency, improve ROI, and allocate resources relating to AI tools will become at least as important as parallel processes on the talent side. Getting true visibility into AI-generated code is incredibly difficult. And yet it’s the number one thing customers ask us for. So we built a new approach from the ground up. Our AI Code D...

By Unknown Author from NYT Home Page https://ift.tt/2lNU45w via IFTTT

Show HN: AI-powered web service combining FastAPI, Pydantic-AI, and MCP servers Hey all! I recently gave a workshop talk at PyCon Greece 2025 about building production-ready agent systems. To check the workshop, I put together a demo repo: (I will add the slides too soon in my blog: https://ift.tt/vYjQqA6 ) https://ift.tt/CTqtyw2... The idea was to show how multiple AI agents can collaborate using FastAPI + Pydantic-AI, with protocols like MCP (Model Context Protocol) and A2A (Agent-to-Agent) for safe communication and orchestration. Features: - Multiple agents running in containers - MCP servers (Brave search, GitHub, filesystem, etc.) as tools - A2A communication between services - Minimal UI for experimentation for Tech Trend - repo analysis I built this repo because most agent frameworks look great in isolated demos, but fall apart when you try to glue agents together into a real application. My goal was to help people experiment with these patterns and move closer to real-world us...

Show HN: From selling AI to QA teams to building a smooth test-management app Hey HN, Bootstrapped founder here. I've got a bit of a story for you. We started desplega.ai to build a sophisticated AI platform that could automate E2E testing. We spent the last few months talking to dozens of QA leaders, and trying to learn what are their actual challenges. We've got one consistent feedback from large teams: their daily reality is a living hell of slow, clunky tools. We're talking about teams at major companies still managing tests on spreadsheets. Or they're stuck in a Jira instance so customized and slow you can “make a full pot of coffee” while a page loads (and that’s why they acquired arc! t3.gg said it first). On top of that, they're paying 2k/mo+!? for these tools that feel like they were designed in ‘05. Soon, it became obvious that our AI tool was way too advanced for them, and why it was much easier for younger startups to start using us. But we didn't wa...

By Brooks Barnes from NYT Business https://ift.tt/KXsJtNk via IFTTT

Show HN: A store that generates products from anything you type in search https://anycrap.shop/ September 13, 2025 at 05:32PM

By Ang Li from NYT World https://ift.tt/CxySFzd via IFTTT

By Niraj Chokshi from NYT Business https://ift.tt/6TS9Idn via IFTTT

Show HN: ProcASM v1.1 ProcASM is general purpose, visual programming language that I've developed. A few months ago I made a post about ProcASM v1.0 here < https://news.ycombinator.com/item?id=43892442 > and got some feed about the UI. So, I spent that last few months trying to improve the UI. Before, I used a GUI library, that I developed specifically for this app using SDL3, for ProcASM. I used Emscripten to port it to run in web browsers for those who wanted to try the app. Now, the front-end is written in HTML, CSS, and JavaScript to execute in a web browser. The back-end is a server that stores user's projects and handles user's requests. There is also a tutorial with text and video that will walk you through the usage of the app. My hopes are that the UI will be more approachable for those who want to try out the app. The plan going forward is to develop new software using ProcASM and blog about the details and the advantages of using ProcASM. https://procasm.te...

By ‘The Opinions’ from NYT Opinion https://ift.tt/NFTS2C3 via IFTTT

Show HN: Willow – a configurable file watcher and rule‑based file manager https://ift.tt/wCRp6r0 September 11, 2025 at 11:01PM

By Rebecca Schmid from NYT Arts https://ift.tt/FKEfcZ4 via IFTTT

Show HN: Strange Attractors – a maths side-project in Threejs I went down the rabbit hole on a side project and ended up building this: [Strange Attractors]( https://ift.tt/EQu59YK ). It’s built with three.js. Working on it reminded me of the little "maths for fun" exercises I used to do while learning programming in early days. Just trying things out, getting fascinated and geeky, and being surprised by the results. I spent way too much time on this, but it was extreme fun. My favorite part: someone pointed me to the Simone Attractor on Threads. It is a 2D attractor and I asked GPT to extrapolate it to 3D, not sure if it’s mathematically correct, but it’s the coolest by far. I have left all the params configurable, so give it a try. I called it Simone (Maybe). If you like math-art experiments, check it out. Would love feedback, especially from folks who know more about the math side. https://ift.tt/EQu59YK September 10, 2025 at 11:27PM

By Mihir Zaveri from NYT New York https://ift.tt/mYV6Hit via IFTTT

Show HN: Atsphinx-qrcode – Sphinx extension to generate QR code in document Document is here: https://atsphinx.github.io/qrcode/ https://ift.tt/CxaOpbG September 9, 2025 at 11:12PM

By Jessica Silver-Greenberg, Matthew Goldstein and David Enrich from NYT En español https://ift.tt/PyRIfZd via IFTTT

Show HN: I made a simple ASCII-art analog clock in Emacs Just a toy, showing how easy it is to leverage built-in Emacs features (most notably Artist mode, which provides a set of functions for creating ASCII-art vector graphics) and things like trigonometric functions and timers to create something nice. A short blog post mentioning some background (and showing a screenshot): https://ift.tt/VQ1wJjm . https://ift.tt/zIHNG2k September 8, 2025 at 11:48PM

By Samantha Latson from NYT New York https://ift.tt/oTEqRjY via IFTTT

Show HN: A livestream of all image descriptions (alt text) on Bluesky In 2019, an academic paper by Gleason et al. found that only 0.1% of Twitter image posts had any form of image description (alt text) [1]. I wanted to see the analogous number for Bluesky today - my full blog post is here [2], but I found looking at the live stream was illuminating and fun too: * Bluesky image posts are frequent enough to keep moving, but not so frequent that it's an unreadable blur. * There's lots of bot content for things like ADS-B feeds (planes nearby), radio station "Now playing", and good old-fashioned affiliate link spam. * There is a lot of detailed descriptions for sexual content. This was a surprise to me! [1] https://ift.tt/BvLzEdW [2] https://ift.tt/wXi2EbW https://bobbiec.github.io/bluesky-alt-text.html September 7, 2025 at 10:59PM

By Simar Bajaj from NYT En español https://ift.tt/0V5poxZ via IFTTT

Show HN: Dumb Site to Rate Horses I wanted a project to learn the Dioxus framework. It needed to be relatively simple and fun. Here is a site that lets you rate horses. The horse people I know have taken issue with this site because they say all horses are beautiful. What do you think? Images are from an open source AI training dataset of horses, so there are some odd ones in there... https://hhn.bustin.tech September 6, 2025 at 11:02PM

By Stephen Castle from NYT World https://ift.tt/MScXtk7 via IFTTT

Show HN: Swimming in Tech Debt This is the first half of my book, “Swimming in Tech Debt”. It is available at a pre-launch sale price of $0.99 ( https://ift.tt/gioxSsa ). I have been working on it since January 2024. It is based on some posts in my blog, but expands on my ideas quite a bit. In September 2024, excerpts appeared in Gergely Orosz’s Pragmatic Engineer newsletter, which helped me get a lot of feedback that expanded the book from my initial idea. This half is about what I expected to do before that —- the rest of the book goes into team and CTO practices. https://ift.tt/p6V9EZM September 5, 2025 at 11:03AM

By Maia Coleman and Benjamin Weiser from NYT New York https://ift.tt/WL9iay6 via IFTTT

By Patricia Mazzei from NYT U.S. https://ift.tt/Y4ht6p0 via IFTTT

Show HN: Entropy-Guided Loop – How to make small models reason TLDR: A small, vendor-agnostic inference loop that turns token logprobs/perplexity/entropy into an extra pass and reasoning for LLMs. - Captures logprobs/top-k during generation, computes perplexity and token-level entropy. - Triggers at most one refine when simple thresholds fire; passes a compact “uncertainty report” (uncertain tokens + top-k alts + local context) back to the model. - In our tests on technical Q&A / math / code, a small model recovered much of “reasoning” quality at ~⅓ the cost while refining ~⅓ of outputs. I kept seeing “reasoning” models behave like expensive black boxes. Meanwhile, standard inference already computes useful signals both before softmax normalization and after it(logprobs), which we usually throw away. This loop tries the simplest thing that you could think of: use those signals to decide when (and where) to think again. GitHub (notebook + minimal code): https://ift.tt/fCXBzDq Paper ...

By Cade Metz from NYT Technology https://ift.tt/OkNXgLE via IFTTT

By Elda Cantú from NYT En español https://ift.tt/qXVz2oi via IFTTT

Show HN: Open-source AI writing your javadoc https://ift.tt/IFsJkpY September 2, 2025 at 11:25PM

Show HN: qdb.us is back, after extensive downtime http://qdb.us/ September 1, 2025 at 10:56PM