News updates

Show HN: Get your coding agent off ~2019 JavaScript, onto modern web primitives Browsers natively handle a lot of what used to take 50 lines of JS (or a dependency): `CSS.highlights` for text range highlighting without s everywhere, ` ` and showModal() give you backdrops and ideal focus management, `field-sizing` to auto-grow textareas as the user types.. (Something yesterday's ftrain post touched on [0]) Models know about some of these by name, but consistently won't default to using the platform-native solution and instead prefer the incumbent +JS based pattern. We started an effort in Chrome to supplement coding agents with this key domain knowledge and we're shipping our 1.0 today, in collaboration with Firefox, MDN, and Edge. 200+ guides (~1.7MB) of curated, hand-crafted implementation best-practices from web experts, updated as the web evolves. (Open source, obv, so.. we'll welcome your bikeshedding ;) Readable versions here: [1] I've spent the last 9 months...

Show HN: Gauge, a 900 KB macOS menu bar app for what's using your RAM and disk https://ift.tt/KjAgI9y November 10, 2026 at 11:19PM

Show HN: WolveKafka – Consume Kafka with a plain HTTP endpoint https://ift.tt/LVBnFMv November 10, 2026 at 11:15PM

Show HN: My daily word puzzle Jointter revisited Hello. This is a follow-up to the post https://ift.tt/3zKG2t7 I've got tons of feedback. Thank you all so much for that! The main issue was an absence of tutorial. I've added it. Hope it helps. Since many people have played, I've noticed that many people start the game, but almost no one finishes it. Is the game hard? What is the main obstacle? Most people, when see opened HA......, try to enter the word that start with HA and give up, forgetting that the first letter can be B as well. It is not necessary to enter specific words. You can submit whatever word you like. So, I'd like to ask for your advice. How to improve the game, so that more people finish it? Maybe I shouldn't make it a daily game with increasing difficulty throughout the week? The same board hides multiple words. I thought that some sort of a challenge would be a good idea, but don't know how to implement it: https://ift.tt/58ziUVY The idea o...

Show HN: Recalc – Spreadsheet where cells can be Claude Code or Codex terminals I built this because it was useful for me when building evals/benchmarks, and I decided to put it up for free for others. The goal was quite simple, make it easy to use a lead claude code / codex session in a panel on the side, while allowing every cell to also be a terminal session running claude/codex, and make it possible to continue a session in an actual terminal window if I needed to. They can all talk to each other using cells on the grid, named cells, or the MCP server that effectively glues the app together. I also found it useful for managing context within related but disparate sessions. My real benchmark runs with recalc are internal to my startup, so to demonstrate some of the functionality I built a small FDA Bench with the tool (obtain and put together dossier's of FDA submissions, and see if a harnessed Claude could have accurately predicted pass/fail): https://ift.tt/kpTfEqn It is s...

Show HN: Write GitHub Actions in any language: Loopt Loopt generates the equivalent code for your workflows in any language, then compiles it down to your workflow files. First-party support for Rust, Python, Typescript, and Go, but it's trivial to add a new language. Check it out if you are tired of mangling YAML. https://ift.tt/X8xrNAf November 9, 2026 at 11:29PM

Show HN: Vegetable Gardening for Engineers https://ift.tt/4GijE0C November 4, 2026 at 02:24PM

Show HN: AirFlick Drop – AirDrop for Windows with zero mobile app installs https://ift.tt/vCO0DUz November 2, 2026 at 02:08AM

Show HN: Jik – a self-hosted language using region-based memory management https://ift.tt/r2yk3b8 November 2, 2026 at 01:21AM

Show HN: 2D world SIM where each creature runs a text classifier in the browser Each creature in this data lab is a real text classifier. You put together a workflow, and the creatures execute it. Just set a stream of incoming messages and watch them work: one filters out the spam, another tags each message's mood, finally a router sends each message to the right bin, and anything it isn't sure about goes to review The classifiers run entirely in your browser. It uses a 22.7M parameter model, int8 ONNX, about 10 ms a message, no API calls Outside the lab, the creatures also evolve, chat, gossip, build huts, plot charts, count numbers, process and eat words, code and dream when asleep. You can also see their stream of consciousness, which they turn into thoughts that they tag. And when they are asleep, you can watch their dreams There are a lot of ways of modifying or evolving the environment and the creatures, including adding elements from other websites, playing music and cha...

Show HN: InterviewLint – Practice explaining code, not just writing it https://ift.tt/MivNWKc October 31, 2026 at 11:36PM

Show HN: A language model that lives in a boot sector All the ideas came from the boot sector demo scene where people had been writing chess and BASIC games in 512 bytes, even a C compiler. I wondered what one can do using a neural network instead of a program and generating boot logs for non-existent hardware was something fun to try. Entire inference engine is 510 bytes of MBR, weights, vocab, and strings reside in the sectors following MBR. Small char-level neural network was trained on dmesg generated by machine, so machine produces Linux boot messages infinitely. train.py performs precisely the same integer arithmetic operations as the asm code does and thus produces an output identical character-by-character to the one produced by QEMU. The difference analysis revealed my favorite bug. The characters at the beginning matched those generated by the simulator, but then the output diverged. I retrieved the hidden layer via QEMU’s debug port and compared the neurons' values with ...

Show HN: I rebuilt Kubernetes for ESP32 microcontrollers https://ift.tt/K1XONGR October 29, 2026 at 10:05PM

Show HN: Pho – TUI for GitHub PRs https://ift.tt/IBRlDMS October 30, 2026 at 12:32AM

Show HN: SLCR – An open standard for agent-native software requirements https://slcr.dev/ October 29, 2026 at 10:13PM

Show HN: I built a map of billboards and banners in Poland (gpy.pl) https://gpy.pl/ October 29, 2026 at 01:24AM

Show HN: Measuring how much of an AI-assisted design is yours https://ift.tt/ilbXgNS October 29, 2026 at 12:11AM

Show HN: OpenTaxRate – open-source US sales tax rates by street address I built this because I tried many sales tax APIs and the problems were: a) the rates were a black box with no source attached b) lookups resolved by ZIP code. ZIP codes are postal routes, not tax jurisdictions. Stripe's Tax team wrote a good post on this [1]: two houses in Drexel, MO share a city, a ZIP, and nearly a house number, but sit in different counties with different rates. If your lookup key is the ZIP, you are wrong on those addresses, even when the rate table is accurate. OpenTaxRate resolves the street address instead: - SST member states (24): the quarterly rate + boundary files, street ranges and ZIP+4, not just the rate tables - Non-SST states: a custom adapter for each state, using its DOR's own published tables and boundary files (TX Comptroller, FL DR-15DSS, ALDOR, IDOR, NY Pub 718, California via CDTFA's lookup, etc) - Census TIGER for geometry I tried with multiple open source geocod...

Show HN: Jog – GitHub runners for 80% less https://usejog.com/ October 28, 2026 at 12:21AM

Show HN: AgenticBench, 9 security tests run on 25 AI coding agents https://ift.tt/Pa6YzBn October 27, 2026 at 10:38PM