5,189 results for not

github.com
Show HN: I built an open source video editor that you can control with an LLMhttps://github.com/DonkeyCut/DonkeyHey HN, my name is David. I'm building an open source video editor.I'm a novice at video editing and previously only used iMovie. I recently opened iMovie to edit a video but noticed it didn't have some features I wanted, like text overlays. Apple probably hasn't updated it in ages. How hard could it be to build one?It's actually pretty hard. There are so many basic things that need to get right, like behavior in the timeline, drag and drop, coloring, etc. Good thing there are LLMs. I was able to put out a simple version in 3 days and have continued to refine it ever since.The idea is that it's focused on novice to intermediate video editors. I find modern video editors to be very overwhelming, with lots of features and controls. It's needed because video editing is a creative tool, and not everything can be built into one. So I turned every button, toggle, and slider into a tool that's accessible to an LLM. A user just needs to tell an LLM what to do, and it has access to tools that c
Aug 21, 2026 5:19 AM
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 P
Aug 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
dumpsort.vercel.app
Show HN: DumpSort – drop screenshots/PDFs, get a named zip (browser-only)https://dumpsort.vercel.appDrop up to 10 screenshots or PDFs. It reads the text in the browser, groups them (receipts / screenshots / documents), and downloads a zip with names like receipts/2026-08-20_receipts_uber-trip.png.Nothing is uploaded. No account. Happy to hear where the naming is wrong.
Aug 20, 2026 9:24 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 resoluti
Aug 20, 2026 8:51 PM
news.ycombinator.com
Qwen3.8 Fetches Weird URLshttps://news.ycombinator.com/item?id=49379079I am working on opencode with the last qwen3.8-27B from unsloth (with dynamic 3.0 quants).while checking documentation for a rust project, instead of fetching the url it had listed in its own reasoning, it tried fetching urls like:https://routify-file-proxy-sg.oss-ap-southeast-1.aliyuncs.com/proxy_temp_file/production/2026-08-20/trace_0baf8c2b17874702866132490e0b56/requestId_97422c0041074091a68367881782d7b7/7c0791038d2f58b3a52c0f07714d3627.html?Expires=1818574288&OSSAccessKeyId=LTAI5t…QVZr&Signature=96y%2B…w%3Dthis happened in the same session, different batches, 16 times in total.It convinced itself there was some rewriting proxy in the webfetch tool.`Expires`, `trace` and `requestId` were consistent for a few requests, but they do change.`AccessKeyId` was always the same, "LTAI5t…QVZr"I did not add the `…` in the signature and access key.Probably training links, but that `Expires` number seems very high...in unix timestamp:1818574288 -- Aug 20271787251180 -- nowJust leaving this here
Aug 20, 2026 7:32 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
kandelo.dev
Show HN: Kandelo – a POSIX-compatible multi-process WASM kernel for the browserhttps://kandelo.dev/20260819-demo/Kandelo is an open-source, Wasm-based multi-process kernel that runs POSIX programs in browsers and Node.js.Kandelo is still experimental, but it already runs a substantial range of existing software.Do you have use cases for this?We are trying Kandelo as a new foundation for WordPress Playground which runs server-side WordPress entirely in the browser. Kandelo also looks promising as a sandbox for running agents in the the browser and on the command line. On the side, we've been playing with porting games and desktop environments and even compiling runnable programs within Kandelo.Yet it feels like there are many possibilities we haven't considered.How would you like to use something like this?Demos:Some notes: The demos have been tested in desktop browsers. Unfortunately, YMMV on mobile today. Some of the disk images are large (~50MB) and may take a while to boot initially.Main set, with Shell (bash, vim, nethack, and more), Nginx, PHP, WordPress, and Doom: https://kandelo.dev/202608
Aug 20, 2026 6:25 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 observable
Aug 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
tablecanon.app
Show HN: Building Table Canon, an AI Campaign Memory Engine for TTRPGshttps://tablecanon.app/Hey HN! I built Table Canon to solve a problem my playgroup kept running into: 3-4 hour tabletop gaming sessions leave behind massive audio recordings, but standard meeting note-takers treat every session as an isolated island, butcher fantasy terms, and don't know who is speaking.I wanted an engine that tracks long-term state across months of games, so I built a pipeline to extract entity updates, open quest hooks, and character promises across sessions.The Tech Stack:* Transcription: whisper-large-v3-turbo * Diarization: pyannote for speaker embeddings & voice profile matching Extraction & Memory: OpenAI API with Structured Outputs (JSON Schema enforcement for state updates) * TTS & Audio Recaps: Kokoro / Chatterbox Turbo Music Generation: ACE-Step-v1.5-XL-Turbo for rendering session summaries into lyrics/balladsA Few Engineering Lessons & Challenges:* State Delta Extraction vs. Context Explosions: Feeding 20 prior session transcripts into context windows quickly becomes cost-prohibi
Aug 20, 2026 4:40 PM
spacenews.com
Rocket Lab launches 9th satellite for iQPShttps://spacenews.com/rocket-lab-launches-9th-satellite-for-iqps/Rocket Lab launched another satellite for Japanese radar-imaging company iQPS on Aug. 20. The post Rocket Lab launches 9th satellite for iQPS appeared first on SpaceNews.
Aug 20, 2026 4:38 PM
epho.io
Show HN: Epho – run Claude Code with a curlhttps://epho.ioHey folks, Burak here.Epho is an API that allows running Claude Code, Codex or Opencode in a sandbox in the cloud. It abstracts away sandboxes, and allows running coding agents with a single HTTP request.Epho came out of our own struggles with building our own AI analyst: - Sandboxes give you bare machines; you need to configure them for agentic workloads. - Each agent behaves differently, and you need to build integrations with each of them. - Sandbox providers are not very reliable, which means you need to figure out a multi-provider strategy to avoid failures. - Logging, artifacts, input/output, event streaming, and all of the other operational aspects need to be figured out.We had to go through the pain ourselves. We got to a point where things got quite reliable, and it became more obvious to us that this should be a primitive on its own: send a POST request, get the events streaming back to you.Epho is an agents-as-an-API product: you send a request, it spins up a sandbox, config
Aug 20, 2026 3:45 PM
news.ycombinator.com
Ask HN: No Path from Techie to Management?https://news.ycombinator.com/item?id=49376072When I was a much more junior techie I would apply for management roles in my company only to be told that I needed more experience and to upgrade my credentials. Years later I have certifications, a graduate degree and have advanced through the technical ranks. Now when I apply to management roles I am told that they are looking for a fresh perspective after hiring junior to intermediate applicants into the roles.I am not an isolated example at my work and as a result we have lost some excellent talent. Is this happening at other companies or is mine an outlier?Outside of this problem I really like where I work and the people that I work with but I feel that I may need to move on if I want to advance my career. I can't think of a way to address this problem with the higher ups without torching my future further.
Aug 20, 2026 3:32 PM
github.com
Launch HN: Vendo (YC S26) – Let users build features on top of your producthttps://github.com/runvendo/vendoHi HN, we’re Yousef & Nour, founders of Vendo (https://vendo.run). Vendo lets users create new features inside the software they already use. A user describes the dashboard, workflow, or small app they need, and Vendo builds it on top of the product’s existing data, API, and interface.Demo: https://www.youtube.com/watch?v=VdpHehY64lsWe built Vendo because every SaaS eventually faces the same problem: every customer needs something slightly different. One wants a new report and another needs a workflow that only makes sense for their team. These requests either sit on the roadmap, become one-off engineering work, or force the customer into spreadsheets and external tools. We wanted the user to be able to create the missing feature themselves, without leaving the product.Here is how it works:- npx vendo init reads the product's API surface, theme, routes, and more. These are used so that the apps Vendo creates (1) look on-brand and native and (2) have the ability to read data and perform
Aug 20, 2026 3:29 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
pub.doub.ly
Show HN: Check if any of the $656M in unclaimed royalties at The MLC is yourshttps://pub.doub.ly/Hi HN, I built this. Quick background on why it exists:When music is streamed on digital streaming platforms (think Spotify, Apple Music, Pandora), there are two separate royalty streams: one for the recording, paid through your distributor (DistroKid, TuneCore, CDBaby), and one for the underlying work (generally known as publishing). The work side's mechanical royalties are collected by The MLC, a nonprofit that was created by the 2018 Music Modernization Act (MMA). If you haven't registered your songs with The MLC, there are issues with your metadata, or about half a dozen other reasons, that money will never reach you, it just collects in a big pile we call the "black box".That pile is big. The MLC's own dashboard currently shows over $656M is held (themlc.com/blanket-royalties), and the biggest problem is the MMA dictates that The MLC cannot hold that money indefinitely. At some point, by law, The MLC must distribute this big pile of cash, and since they don't know who it's suppose
Aug 20, 2026 2:38 PM
news.ycombinator.com
Algorithm Interview: a conversation between two parrotshttps://news.ycombinator.com/item?id=49373709Algorithm Interview: a conversation between two parrotsAll children know that parrots can talk. All adults understand that parrots simply repeat sounds.You'll laugh, but these same adults actually believe that an Algorithm Interview is a conversation between a very smart algorithm expert who is trying to find out whether the candidate understands algorithms at an acceptable level…So, how many ycombinator.com readers have successfully passed the algorithms interview? Probably tens of thousands.Well, how many of them were able to understand that breaking down sorting into independent stages is a Fundamental Discovery? Zero!Zero questions and comments: https://news.ycombinator.com/item?id=49314420P.S. Have you ever thought that NOT everyone has a mental model? But most people just memorize ready-made answers instead of understanding the problem?I recommend reading The Programmers' Stone https://www.datapacrat.com/Opinion/Reciprocality/r0/index.html ---------------8
Aug 20, 2026 12:29 PM