youtilitics.com
Show HN: Youtilitics, energy usage analytics from utility data, no hardwarehttps://youtilitics.com/I posted an early version of this 2 years ago. Rebuilt most of it since then, so posting again with what's actually different.Youtilitics still pulls interval data your utility already collects (Green Button/ESPI — 15-60 min whole-house kWh) and turns it into usage analytics. The analytics stack is different: baseline anomaly detection (median/MAD by time-of-day bucket, not a flat threshold), overnight step-change alerts, usage heatmaps, cycle-over-cycle comparisons, etc. It is still based on a model trained on human-labelled data: used to differentiate baseline (eg vampire load) vs EV vs HVAC vs the rest. Inference runs with a python script when new data is received from the utility.I also changed the mobile app. It is still mainly used to store the user credentials without us having them (they never leave the device), for security/privacy reasons. This is used to scrape usage data from the utility dashboard, when they don't support Green Button. However now it also runs an embedded PAug 20, 2026 10:13 PM
news.ycombinator.com
Ask HN: How did you write code on restricted hardware?https://news.ycombinator.com/item?id=49380490I remember trying to write code for a project in college from those library computers when I did not have a laptop of my own at the time.I often used sites like Codepen and copy-pasted the progress into a github repo so I didnt lose my work.What are some workarounds you’ve used (or tried) for writing or running code from restricted hardware, like a school computer or a mobile device? What kind of project was it for, and what hurdles did you encounter?Aug 20, 2026 9:25 PM
praxos.ai
Show HN: Praxos – team messaging with built-in memoryhttps://www.praxos.ai/Hey HN! What does a regular workflow at a startup look like?Probably like this:> One founder talks to customers> Another founder builds> A customer asks for something. The first founder explains it to the second. The second founder explains it to Claude> Two weeks any one of the founders asks one of the following questions: \* Why are we building it this way? \* What happened here? \* What did we promise ACME we’d do? \* How far along are we on X? > Then you scream on the inside because you have to figure out what happened...Before agents, the person who did one part of the work usually held a mental map. They could share the context with other people. Increasingly, they can’t.Small teams can run far more work in parallel than ever before thanks to AI, but someone now has to connect all that context manually. The reasoning behind one product change might now be scattered across a customer call, two emails, a Slack thread, and four Claude conversations.Praxos is a team messaging app.It Aug 20, 2026 8:55 PM
pingchange.com
Show HN: PingChange – monitor web pages and OpenAPI specs for meaningful changeshttps://pingchange.comI built PingChange after watching the same thing happen over and over: a competitor prices change, a company policy is updated or important web content changes but there is often no reliable way to track it and know when it happens.The tool monitors web pages and API on a schedule and alerts your team when something meaningful changes. The keyword here is meaningful. Most monitoring tools trigger alerts for everything (ads, timestamps, cookie banners etc) and could be noisy or spam in your inbox. With PingChange, you can give it an instruction e.g "alert me when pricing changes" and it analyzes the page content and only notifies you when the changes matches what you're looking for on the page.Here are the main features:- Visual region selection / HTML element selector for tracking specific location on the page. - Changed diff viewer and screenshot of the pages. - Geolocation support - Monitor URL's from specific location to detect content from different geographies. - Anti-bot resolutiAug 20, 2026 8:51 PM
danielvaughn.dev
Show HN: Huzzah – a novel approach to coding with AIhttps://www.danielvaughn.dev/posts/huzzah/Hello everyone. I've been working on this experimental editor called Huzzah.I've been working almost exclusively with coding agents since January of this year, and over the past few months I began to feel utterly exhausted by them. They're great, but I'm finding it more and more tedious to write full sentences for every change I want. Not only that, but it seems there's a complexity limit for codebases - beyond a certain point the agent begins confusing itself.I'd like to go back to writing code, but I don't want to go all the way back to fully manual coding. So I've come up with this interaction paradigm where you: 1. write pseudocode in whatever way makes the most sense to you 2. on save, the editor synchronizes your work to real source code 3. the pseudocode is persisted alongside the generated code, making your prompt effectively a stored record of intent. It may not work for every use case, but in my initial playthroughs I've found it very enjoyable.Right now it's just a proof of Aug 20, 2026 7:05 PM
playling.netlify.app
Show HN: Language Audio Trainer – Learn languages without looking at the screenhttps://playling.netlify.app/I recently built a language learning app with a slightly different approach. I deliberately didn't want it to be another Duolingo-like app.I think users should be able to choose what they want to learn and when.The main idea behind Language Audio Trainer is that you can simply press Play and listen to useful phrases in the background with the screen off — while walking, driving, cooking, etc. You can skip or repeat phrases, change the speech speed and number of repetitions, and choose the translation direction.There is also a flashcard mode for when you want to study more actively.I'd be interested to hear what you think about this approach to language learning.iOS: https://apps.apple.com/app/playling-language-trainer/id67619... Android: https://play.google.com/store/apps/details?id=com.playling.a...Aug 20, 2026 6:17 PM
news.ycombinator.com
Are you good at AI, or just using it?https://news.ycombinator.com/item?id=49378057We’re working on a ladder for individual AI proficiency and would love feedback on both the levels and the definitions.L0 New: brand new to AI, or has not yet used it.L1 Chat: simple prompt-and-response use. Work is serial: ask, wait for an answer, then ask again.L2 Contextual Work: gives AI relevant documents, data, or workspace context so it can work within the actual artifact and produce a more useful result.L3 Orchestrate: coordinates multiple agents or AI roles across independent workstreams, with work that may review, challenge, compare, or build on other work. This is not just for engineering.L4 Automate: creates workflows that are triggered by business events and run without someone sitting at a laptop directing each step.L5 Loop: feeds the output of those workflows back into shared knowledge or a company brain, so future workflows improve over time.A few things I’d love your perspective on:Are these the right levels? Are any of the names unclear or overlapping? What observableAug 20, 2026 6:04 PM
skilldocs.dev
Show HN: Skilldocs – Figma for Markdownhttps://skilldocs.dev/tourI got fed up with Notion, so I built my dream document editor. It's all markdowned so it's easy to view skills or other agent-related documents. It's got the collaboration features I love from Figma (shared cursory and the ability to follow) and Google Docs (comments, realtime editing). Then you can export the diff and comments to an agent. I've been really liking it for talking over skill documents live on a call. I'm curious if this resonates with other people. More generally, I feel like notion is less and less relevant in an age where documents have a very different purpose and Markdown is king. Curious what people think!Aug 20, 2026 5:56 PM
news.ycombinator.com
Show HN: JavaScript library that makes any list a smooth picker of any shapehttps://news.ycombinator.com/item?id=49377550Hey HN! I built this solo.You can check it out here: https://loopem.tahazsh.com/This idea had been lingering in my head for a long time. I kept thinking about the best way to turn the idea of a picker into a math problem, where I could describe the layout I want and it would just work.By pickers, I mean something like what `` does in HTML, but with more visual items, whether they are images, icons, colors, or anything that would enhance the user experience.For example, say you have an e-commerce app that shows different color options for a product. Instead of listing blue, red, and so on, you can show the actual colors, and users can drag or flick through them.To prove it works, and to give you usable options out of the box, I added built-in layouts: line, arc, wheel, cover flow, fan, and stack.I also made sure it stays smooth with any number of items. It's still fast because I virtualized the list, so it only renders what's on screen.Accessibility is on by default too. Arrow keys, HomAug 20, 2026 5:24 PM
news.ycombinator.com
Ask HN: One SSH key or many SSH keys?https://news.ycombinator.com/item?id=49377427Is there any benefit to using multiple, separate keys to authenticate to different resources versus only using a single SSH key?On one hand, I've heard that an SSH key is supposed to represent an identity, so using your "identity" everywhere makes sense.On the other hand, I've heard that keeping SSH keys separate is important in the same way using separate passwords for different resources is important.What do you all think?Aug 20, 2026 5:15 PM
news.ycombinator.com
Ask HN: Do you automate your prospection or doing hand made?https://news.ycombinator.com/item?id=49375869When your technical founder, prospection and talking to clients is pain.With AI we have tentation of automating everything.Linkedin or other social medias and letting AI do everything.Problem is that it is also painfull to automate because of anti-bot protections, and services that do it are not enough good (i think).But also that you go a little bit far from discovering your potential clients.What do you think about it?Aug 20, 2026 3:18 PM
news.ycombinator.com
Show HN: LilScript makes JavaScript libraries smallerhttps://news.ycombinator.com/item?id=49374554https://yeargun.github.io/lilscript/LilScript is a typed, compression-first language that compiles into js and sometimes into exec(will be more stable in future). The compiler mangles, reshapes the program into optimized js that happens to be 5-15% smaller (after gzip/br compression or raw) compared to the best performing JS toolchains like oxc/esbuild/terser/..## What has been proven to work with LilScript?- makes VSCode's core js modules 20% smaller on average- makes the world's most performant & small markdown rendering npm library, marked, 5-7% smaller and 10% faster- and many more demos.. works with pretty much any js/ts library## How it is compressing js finer than vite/oxc/terser/esbuild/..### 1. By changing the app.``` class Vector { float x; float y; init(float x, float y) { this.x = x; this.y = y; } float lengthSquared() { return this.x * this.x + this.y * this.y; } }int[] values = [1, 2, 3, 4]; auto doubled = values.map((int value) => value * 2); int sum = 0; for (int i = 0;Aug 20, 2026 1:50 PM
news.ycombinator.com
Is this AWS RI/SP simulation engine interesting / valuable?https://news.ycombinator.com/item?id=49374412TLDR; This AWS RI/SP tool we built might have unique features that are important especially for companies running large, high-variability workloads with high coverage targets. We want feedback on how true that is and whether we should open this up to others, possibly even for free or as OSS.Setup: We're a small cloud cost consultancy, but not a tools vendor. We do build a lot of internal tooling for our own use. We serve companies spending 7- to 9-figures (USD) annually.One of the internal tools we built over the past several years is a simulation engine for RIs/SPs that can do a number of things, some of which we believe might be one-of-a-kind in the space today and could be valuable to others.1.) Visualize the entire commitment savings/discount curve for any commitment type (any RI, any SP, of any flavor), showing the exact savings achieved and the marginal discount rate at every level of commitment. This unlocks what we feel is the best purchasing strategy: "buy SP dollars or RI uniAug 20, 2026 1:36 PM
scibly.com
Show HN: Open-source tool turning company knowledge into Duolingo-like courseshttps://www.scibly.com/de/My buddy and I have been working on a side project for the past few months called Scibly.The idea is pretty simple:Companies already have an incredible amount of knowledge sitting in PDFs, documentation, internal wikis, etc. The problem is turning all of that information into something employees can actually learn from and retain.For this reason we decided to build Scibly, a tool that automatically turns boring company knowledge into interactive, Duolingo-like (but better) learning experiences.Today, we decided to open-source the whole thing.We're still pretty inexperienced when it comes to open source, so we'd genuinely love to hear your feedback, whether that's about the product, the idea, the codebase, or how we're approaching the project.Short product demo: https://www.youtube.com/watch?v=TcpLUNBRhQwGithub: https://github.com/scibly-dev/sciblyWould love to hear what you guys think!Aug 20, 2026 1:11 PM
simedw.com
Show HN: I trained a 125M model to autocomplete piano on-devicehttps://simedw.com/2026/08/20/midi-autocomplete/I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15).The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device.The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.Aug 20, 2026 12:04 PM
bing.com
McDonald’s Happy Meal to bring Hello Kitty and Godzilla togetherhttp://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6a88f514686741838a66b9a5d150d08b&url=https%3A%2F%2Fwww.msn.com%2Fen-us%2Flifestyle%2Flifestyle-buzz%2Fmcdonald-s-happy-meal-to-bring-hello-kitty-and-godzilla-together%2Far-AA2azxxj&c=452902551626708833&mkt=en-usHere's what you need to know about these new Sanrio and Godzilla toys at McDonald's.Aug 20, 2026 10:41 AM
news.ycombinator.com
Offline RAG on iOS with Spatial Integrationhttps://news.ycombinator.com/item?id=49371913I'm the developer behind CartoType. I’ve been working on bridging local language models with offline mapping, and I have just put together a demo of a completely offline Spatial RAG pipeline running natively on an iPhone. The new system is named the CartoType Field Assistant. You can find the website at https://cartotype.comDemo (1m 19s): https://www.youtube.com/shorts/a8yQPn7_jyIUse cases: Any organisation with field technicians or emergency first responders needs complex procedural knowledge tied to physical locations ('assets') where they don't have guaranteed network connectivity. Examples include offshore wind farms, power distribution networks, railway infrastructure, mountain rescue, and military uses.For this demo I query the iPhone app in Airplane mode: "A hiker near Tuolumne Meadows has a dislocated shoulder. What is the reduction protocol, and where is the Tuolumne Meadows Ranger Station?"HOW IT WORKSThe core is a portable C++ engine running vector search across an encryptedAug 20, 2026 8:28 AM
bing.com
Film festival celebrates 15 years with 40 films and a new Colorado Springs homehttp://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6a8af05d344a46b2929fd066116ef947&url=https%3A%2F%2Fgazette.com%2F2026%2F08%2F20%2Ffilm-festival-celebrates-15-years-with-40-films-and-a-new-colorado-springs-home%2F&c=4868808529754187867&mkt=en-usThere’s something about sitting in a dark theater with a room full of strangers. For a little while, the outside world fades, the lights dim and the only thing that matters is what’s unfolding on ...Aug 20, 2026 7:08 AM
github.com
Show HN: Do-over, undo for AI agent shell commandshttps://github.com/CaydenChik/dooverHello HN,I built this after a coding agent deleted my files while tidying a project. Do-over plugs into Claude Code's hooks and snapshots what a command is about to touch right before it runs.I know what you're thinking. Why don't you just commit more often?This tool doesn't seek to replace git. What it does is: [1] Protect the stuff git doesn't protect: your untracked/ignored files and files that exist outside your repo (which is how a guy lost 50GB of data - Claude code issue tracker) [2] Protects you when git itself is weaponized by your agent: git checkout ., git clean -fd, and git reset --hard (a three year old Unity project was deleted this way - Claude Code issue tracker) [3] Protects you in the case when you're just forgetful and don't commitIt really is a simple safeguard to potential headaches. And it's a last mile effort that secures what current measures can't. That includes sandboxes, checkpoints, git.Aug 20, 2026 6:42 AM
bing.com
Here's the Average Credit Card Debt for Your Age Group in 2026http://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6a89566665da4fddb7312d18d236b139&url=https%3A%2F%2Fwww.msn.com%2Fen-us%2Fmoney%2Fpersonalfinance%2Fheres-the-average-credit-card-debt-for-your-age-group-in-2026%2Far-AA2ay1SV&c=14633633087984383984&mkt=en-usGen X carries the highest card balances of any generation. See where you land, what carrying a balance costs, and how to start cutting it down.Aug 20, 2026 4:30 AM
