wocal.app
Show HN: A botless meeting recorder and summarizer that runs in the browserhttps://wocal.appI built a browser app for recording calls and turning them into transcripts/summaries without inviting a meeting bot.The current version is BYOK: you provide an OpenAI API key, stored locally in your browser. Recordings/projects stay in browser storage; selected audio/transcript text is sent to OpenAI only when you run transcription/summary.I am testing whether the wedge is real: no bot in the meeting, no SaaS workspace for recordings, summaries/exports afterward.I would appreciate feedback on the trust boundary and whether BYOK is acceptable for a first version.I used it once to record a meeting I didn't want to spend 1 hour on, and just needed the summary - the tool captured the meeting audio even after I turned off the laptop audio.May 22, 2026 2:36 PM
bing.com
The 9 Best Table Saws to Rip Boards with Accuracy and Precisionhttp://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6a8d951719fa4f43abc7d16b2dff66a6&url=https%3A%2F%2Fwww.popularmechanics.com%2Fhome%2Ftools%2Fa37343759%2Fbest-table-saws%2F&c=17370892499753937466&mkt=en-usA table saw isn’t just another tool—it’s the one that decides whether your work looks intentional or as if you were guessing. I’ve spent enough time on job sites and in workshops to know the ...May 22, 2026 9:26 AM
news.ycombinator.com
Ask HN: Anyone else struggling with AI and work?https://news.ycombinator.com/item?id=48225837Been a developer for a little over 10 years now. I work on web stuff. Your typical React/Svelte codebases with Node backends.The past year or so I've been working with coding agents and at first they just felt like a really really great tool. They'd allow me to do my work faster, and while obviously not perfect, they'd do a pretty good job.When Opus 4.5 came out it seemed like something changed. I found myself reviewing less and less code. I wasn't writing any on my own either. And for the past several months it's really just been like that. I dictate to my machine a long prompt as to what feature I want, how I want it architected, and what success looks like and Codex just does it. And does it pretty damn well.This has left me feeling a bit lost in my career because much of the challenge and flow that I would get from coding is gone. Thinking through intricate data flows, mapping them out in my brain, etc... is just gone. I don't do it anymore because there's just no need.Many will saMay 21, 2026 4:59 PM
news.ycombinator.com
Show HN: I Dedicated 4 Years to Mastering Offline Password Crackinghttps://news.ycombinator.com/item?id=48221896Hi everyone,I am Bojta Lepenye, and first of all, I want to thank the core developers of Hashcat. In my experience, it is quite literally the most capable tool available for offline password cracking across a wide range of use cases.I have spent the last 4 years (from age 14 to 18) extensively working with Hashcat and the tools surrounding it, and I have documented what I have learned throughout that time (since January 18, 2022) in my first book. During that period, I also had to continuously update and rewrite major sections as the field evolved. One example was the introduction of GPU support for Argon2 and other memory-hard password hashing algorithms, which significantly changed some cracking workflows.My passion for this book, or its “quick starter,” if you will, came from an ethically conducted penetration test I performed with full authorization at my school. This is something I am both hesitant and quite proud to acknowledge.At the beginning, I simply wrote down everything I hMay 21, 2026 12:56 PM
news.ycombinator.com
Ask HN: Does anyone believe role-play AI is effective for training?https://news.ycombinator.com/item?id=48221788We built Socratize, an AI-based training tool where employees practice real workplace scenarios instead of watching videos or taking quizzes.Most corporate training is passive. People watch content, click through slides, pass a quiz, and forget most of it within days.We wanted to try a different approach: learning through dialogue and repetition.With Socratize, users enter realistic scenarios and have to respond to an AI “counterparty”.For example:A sales rep practices handling: “Your product is too expensive” A support agent practices de-escalating an angry customer An employee practices explaining a compliance rule in their own wordsThe AI responds like a realistic counterpart, challenges weak arguments, and continues the conversation until the user improves or fails the scenario.The goal is simple: replace passive training with active practice.We’re using Claude to generate responses and evaluate the quality of the user’s arguments based on context and reasoning. Each session is stoMay 21, 2026 12:46 PM
bing.com
WordPress.com Review: Easy Blogging and Hosting, With a Few Site-Building Tradeoffshttp://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6a8cd4dbae2a4eb0a5666ecc2d28169e&url=https%3A%2F%2Fau.pcmag.com%2Fweb-hosting%2F57767%2Fwordpresscom&c=10516439032424540685&mkt=en-usWordPress.com is a high-quality, low-cost blogging option, but competitors with more up-to-date tools make it easier to build custom websites. From the outset, it's important to make clear that ...May 21, 2026 11:23 AM
nasa.gov
NASA-developed AI Could Help Track Harmful Algaehttps://www.nasa.gov/science-research/earth-science/nasa-developed-ai-could-help-track-harmful-algae/NASA scientists have developed an artificial intelligence tool to take on a longstanding challenge in ocean waters. In a study recently published in AGU Earth and Space Science, researchers reported the tool was able to fuse data from multiple satellites and detect harmful algal blooms that occurred in western Florida and Southern California. Severe blooms […]May 20, 2026 5:39 PM
getatrium.dev
Show HN: atrium – a resumable, tiling workspace manager for Claude Code, Codexhttps://getatrium.devatrium is a macOS desktop app that provides a fully resumable workspace manager with a variety of heterogenous panes including terminals, browsers, tasks, notes, and more.Over the last couple of months, I've been building an AI development tool that treats CLI AI dev harnesses as first class citizens. With Claude's SDK pricing changes on the horizon, I wanted to avoid getting locked in to paying API rates for something I already had a subscription for.It started after my computer crashed and iTerm didn't restore my sessions, so I set out to solve that problem initially. I liked it and added functionality till it became my daily driver. I ended up with atrium and I'm enjoying it so much I thought maybe others would, too.A little about the principles I started following as I built:Organization - everything fits into a hierarchy of workspaces, rooms, panes (agents, terminals, browser, notes, source control, etc), and stacks within a highly customizable mosaic.Persistence - everything, incMay 20, 2026 2:44 PM
bing.com
New insights into how the human hand evolved from our ape-like ancestorshttp://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6a8974bdcea444f7a5ffc6ae3c31db23&url=https%3A%2F%2Fphys.org%2Fnews%2F2026-05-insights-human-evolved-ape-ancestors.html&c=14148544098581840510&mkt=en-usThe human hand is an evolutionary marvel. While other primates rely on their hands for locomotion and basic grasping, ours can shape tools, manipulate objects, and perform detailed tasks requiring ...May 20, 2026 10:10 AM
bing.com
New insights into how the human hand evolved from our ape-like ancestorshttp://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6a8b580d083a4ddb9ab78d26db3537c9&url=https%3A%2F%2Fphys.org%2Fnews%2F2026-05-insights-human-evolved-ape-ancestors.html&c=14148544098581840510&mkt=en-usThe human hand is an evolutionary marvel. While other primates rely on their hands for locomotion and basic grasping, ours can shape tools, manipulate objects, and perform detailed tasks requiring ...May 20, 2026 10:10 AM
github.com
Show HN: Alint, a fast linter for repository structure and hygienehttps://github.com/asamarts/alintHi HN, I have been working on alint for the last little while. It is a linter for the shape of a repository rather than the code inside it. clippy, ruff, eslint, and others already handle the AST and code space. alint checks the other layer: required files, filename conventions, content patterns, structured values inside package.json / Cargo.toml / GitHub workflow YAML, and cross-file invariants. You write one .alint.yml describing what the repo should look like, and it runs in CI. Today it covers 70 rule kinds across 13 families, 19 bundled rulesets, 12 auto-fix ops, and 8 output formats including SARIF.To check the design against reality, I built (vibed) working configs for 30 real OSS repos. The corpus is deliberately varied: single-language workspaces and polyglot monorepos, from small clean trees up to roughly 150k-file mega-repos, with and without mature in-house tooling. Each one has a writeup of what alint catches that the repo's existing tooling does not, including the false-pMay 19, 2026 11:39 PM
limitless-osint.com
Show HN: Limitless – AI OSINT search and interactive intelligence sandboxeshttps://limitless-osint.com/Hi HN,I built Limitless because I wanted to create a unified, high-fidelity platform for Open Source Intelligence (OSINT), dark web collection, and interactive threat training.Most cybersecurity training systems are either standard slide decks or text-heavy questionnaires. At the same time, actual analyst tools are scattered across hundreds of disconnected command-line scripts and API wrappers.Limitless merges real analyst tools with a reactive, browser-based training simulator.The Ecosystem Components: 1. *Feynman (OSINT search): An intelligence search engine that maps digital footprints, uncovers hidden connections, and aggregates intelligence across 200+ online sources instantly. 2. *Sentinel (Darknet Agent):* An autonomous AI agent designed for deep-web collection, learning, and reasoning across darknet forums. 3. *Interactive Training Sandboxes:* Scenario-driven tutorials that teach cybersecurity operations through visual tools: * GEOINT Simulator: Uses Leaflet and coordinates to May 19, 2026 9:00 PM
news.ycombinator.com
CloudNSite – AI agents that replace manual business processes for SMBshttps://news.ycombinator.com/item?id=48199120Hey HN,I built CloudNSite, a consulting firm that deploys AI agents to automate repetitive business workflows across healthcare, legal, real estate, and a few other verticals.The problem I kept running into with clients was that most AI tooling assumes you have an engineering team. Small businesses don't. They have manual processes held together with spreadsheets and email.We built a library of 30+ pre-built agents and multi-agent bundles tuned to specific industry workflows. Clients pick what fits, we customize and deploy. For healthcare and legal clients with strict data requirements, we handle private LLM deployments on their own infrastructure with HIPAA-ready architecture.We also built a free AI Readiness Assessment that generates personalized use cases and rough ROI estimates without a sales call.Would love feedback from anyone who has worked in this space or has thoughts on the agent library approach.May 19, 2026 8:30 PM
usagiengine.com
Show HN: I made a 2D Lua game engine using Rust with code and asset live reloadhttps://usagiengine.com/I love making small 2D pixel art games, especially using tools that have some constraints. Things like Pico-8 and the Playdate SDK are simple, fun, and allow for focusing on the game idea rather than the technical minutia. Years ago I prototyped an idea for this little game engine, Usagi, but used Rhai instead of Lua. The idea for this little game engine never went away, so I decided to finally dig in and build it.Today I released v1.0.0 of Usagi Engine after making a bunch of small games, getting feedback from developers, and stabilizing the API. It's simple, has a great developer experience (CLI-based, init template, Lua plugin integration, and cross-platform export for web, Linux, macOS, and Windows with a single command).The engine is public domain, and its source is on GitHub (linked from the website).Rust was a great fit for this project due to its stability and tooling. The crate ecosystem is a real highlight for me. Plus clippy. I made a couple of games in Rust in the past (usiMay 19, 2026 7:46 PM
scan.gethyperpress.com
Show HN: Website Performance Scanner Specifically for WordPresshttps://scan.gethyperpress.com/Hi HN, Kevin Gilleard here from GillyTech. I run a digital agency that deals with a lot of WordPress sites and have always been interested in optimizing my WP instances (going back 16 years).I love to find ways to optimize for speed, security and stability and found myself using a ton of different tools to do performance audits. GTmetrix and Google Page Speed Insights are my go-to's as a starting point. But there were other things I needed to check like security headers, which builder (if any) is used on the site, WooCommerce, caching plugins, CDNs, WAF, etc. So I decided to make my own performance scanner with persistent reports that can be shared with clients and bring those tools together in one custom app. It shows a number of metrics that are specifically important for optimizing WordPress against the three S's: Speed, Stability and Security.Necessarily this scanner will reject your website if it isn't WordPress, so there is some unique exclusivity here. Full transparency: we do oMay 19, 2026 5:28 PM
weloveit.io
Show HN: How Expensive Is Your (Steam) Wishlist?https://weloveit.io/how-expensive-is-your-wishlist/A tool/toy that lets you connect to your Steam wishlist to calculate the total list/current price of all the games on it.There's a shallow, jokey purpose to it ("I could buy a BMW with this amount!"), but the real purpose is to demonstrate how we can do a better job of portraying a game catalog. I often wishlist stuff, then it pops up in a "Hey, it's on sale!" email months later. In that email, there's a banner capsule, but that doesn't help my brain remember why I added it.To that end, after you get the bill, you get a nice, flat feed of stuff about all the titles you've wishlisted over the years. It's all stuff that developers painstakingly put together, but which Steam tucks away under the fold of a game's Store page.Anyway, my wishlist came to about $250. My QA guy is up to $19k. Give it a go; hope you enjoy it!May 19, 2026 5:15 PM
news.ycombinator.com
Show HN: Heard Google copied part of our product for IO. Want to show off firsthttps://news.ycombinator.com/item?id=48195533I just heard from a very reputable source that Google built part of our product and that they're about to show it off at Google IO.We built a 3D film tool called ArtCraft:https://getartcraft.comhttps://github.com/storytold/artcraft (our monorepo with the desktop app, server, and website code)Our 3D virtual film set enables set decoration, location reuse, precision blocking (control over where things are), character posing, etc.Sets and objects can be generated as meshes or gaussian splats.Autoregressive multimodal models can treat input "previz" style scenes as ControlNets of sorts. Combined with reference images and a possibly a few follow-up rounds of editing, you can create extremely precise starting frames that reflect your vision as a director or creative almost exactly as you see it.It gets rid of the "roulette wheel" of prompting in the places and times where you know you what you want. It's like a WYSIWYG editor.Here's an example:https://app.getartcraft.com/edit-3d/m_qa72baw3crMay 19, 2026 4:28 PM
superlog.sh
Show HN: Superlog (YC P26) – Observability that installs itself and fixes bugshttps://superlog.sh/Hey HN, we’re Nico and Arseniy, co-founders of Superlog (https://superlog.sh). We're building a self-installing, self healing observability tool meant not to be opened. It has a wizard that daily sets up proper logging and an agent that investigates errors and opens PRs.Super short demo: https://www.youtube.com/watch?v=xFhU9Mk247M.In our earlier startups, we tried Sentry, Datadog, Grafana, Dash0, and nothing was good enough. Proper telemetry and alerting still requires a ton of manual setup. We struggled with adding good logs, so debugging was tough, especially as codebases grow at a faster pace. Meanwhile, the Datadog/Dash0 bill kept climbing, and we still spent engineering hours to learn, configure, and maintain our observability tooling.With Sentry, we found ourselves flooded by a stream of alerts into our Slack channel, most were duplicates or lacked context, so alert fatigue/constant interrupts were a real pain. The #ops notification is consistently the worst feeling on a SaturdayMay 19, 2026 3:54 PM
news.ycombinator.com
Show HN: Updatecli – A Declarative Update Policy Enginehttps://news.ycombinator.com/item?id=48192415A few years ago, I came here to share this side project that I was building.At the time, my problem was simple, I kept forgetting to update files across Git repositories, and none of the tools available to me could cover all my use cases without extensive scripting.So I decided to build a declarative update policy engine for crafting tailored update workflows.I needed a way to define, what information to monitor, which files to update, the conditions required before applying changes, and finally a way to push the changes on a Git repositoryWhether it was documentation, dependency management, or release orchestration, the goal was always the same.To stop forgetting updates across repositories.Back then, I received a lot of great feedback, but I also noticed that people were sometimes confused about how Updatecli differs from Renovatebot or Dependabot. So before going further, let me clarify that point.Renovatebot and Dependabot are excellent tools, easy to use and requiring very little May 19, 2026 12:27 PM
github.com
Show HN: Forge – Guardrails take an 8B model from 53% to 99% on agentic taskshttps://github.com/antoinezambelli/forgeHi HN, I'm Antoine Zambelli, AI Director at Texas Instruments.I built Forge, an open-source reliability layer for self-hosted LLM tool-calling.What it does:- Adds domain-and-tool-agnostic guardrails (retry nudges, step enforcement, error recovery, VRAM-aware context management) to local models running on consumer hardware- Takes an 8B model from ~53% to ~99% on multi-step agentic workflows without changing the model - just the system around it- Ships with an eval harness and interactive dashboard so you can reproduce every numberI wanted to run a handful of always-on agentic systems for my portfolio, didn't want to pay cloud frontier costs, and immediately hit the compounding math problem on local models. 90% per-step accuracy sounds great, but with a 5-step workflow that's a 40% failure rate. No existing framework seemed to address this mechanical reliability issue - they all seemed tailor-made for cloud frontier.Demo video: https://youtu.be/MzRgJoJAXGc (side-by-side: same model, sameMay 19, 2026 12:23 PM
