The teacher takes stand in school shotting criminal trial - WUSA9The teacher takes stand in school shotting criminal trial WUSA9
Marathon’s WSTR Shotgun Nerf Means No More Two-Shotting Blue Shield (and Above) Users - GamingBoltMarathon’s WSTR Shotgun Nerf Means No More Two-Shotting Blue Shield (and Above) Users GamingBolt
3.28 - Brother of minion pact and 1 shotting Uber's on a 2-link - YouTube3.28 - Brother of minion pact and 1 shotting Uber's on a 2-link YouTube
Show HN: Stagehand – the open source SDK for browser agentsHey HN, I’m Sam, a maintainer of Stagehand, and I’m excited to show off Stagehand v4: the SDK for browser agents.For agents to do most knowledge work, they needs access to the internet. Today most people allow their agents to use Playwright to control a browser for them.But Playwright was built for testing, not agents.If you’ve ever tried to give it to your agent, you’ll quickly run into bloated context windows, inability to use iframes, and painful state sync issues (on remote browsers).We built Stagehand specifically for agents. v4 fixes all of Playwright’s issues, with better page snapshotting, nested iframe support, webmcp, self-healing primitives, and we even rebuilt it to run as an extension in the browser which minimizes round trip time for all requests.We’re roughly ~80% more token efficient and 2x faster than Playwright.Use AI primitives for self-healing automations in natural language: // Act: execute natural language actions await stagehand.act("click the login button"); //
Show HN: Flashtype – Markdown editor for Claude and Codex with in-line diffsI wanted to better markdown editor for collaborating with Claude/Codex and built Flashtype (https://github.com/opral/flashtype):- opens local markdown files- Claude/Codex natively integrated (with my existing subscription!)- in-line diffing to quickly accept/reject changes- WYSIWYG (!)The in-line diffs are a big step up to other apps static previews, and, in theory, just the first collaborative primitive.But, I am getting feedback that "editing" might become a thing of the past. Why do I need to see diffs from Codex/Claude if the models are getting so good to the point that they need no correction?Which makes me wonder, how did your writing setup with AI change over the past months? Are you still iterating on posts or are agents one shotting them?
Show HN: I built music composition agent and browser-based DAW for Opus 4.5I was interested in exploring how good Opus 4.5 has become at music composition, so I built a local-first browser-based DAW where you describe music and Claude composes it using an agentic loop with lots of tools (create tracks, write notes, read back what it wrote, apply swing, humanize timing, set panning/volume, etc.). It also supports recording via MIDI keyboard, looping, multi-track, panning, a bunch of synth instruments, all inspired by the Logic Pro UI, so you can collaborate with the AI.Opus 4.5 is pretty good at one-shotting MIDI compositions already, even without a custom harness and tool, but it really shines when you ask it to self-review (a Ralph Wiggum loop would help here!) and correct multi-track mistakes, which it will capably do after being asked to. This results in nuanced multi-voice compositions with fewer clashes.There's a good onboarding flow in there as well so it's easy to get set up and prompt your first few compositions.You have to provide an Anthropic API ke
Show HN: We built an open source, zero webhooks payment processorHi HN! For the past bit we’ve been building Flowglad (https://flowglad.com) and can now feel it’s just gotten good enough to share with you all:Repo: https://github.com/flowglad/flowgladDemo video: https://www.youtube.com/watch?v=G6H0c1Cd2kUFlowglad is a payment processor that you integrate without writing any glue code. Along with processing your payments, it tells you in real time the features and usage credit balances that your customers have available to you based on their billing state. The DX feels like React, because we wanted to bring the reactive programming paradigm to payments.We make it easy to spin up full-fledged pricing models (including usage meters, feature gates and usage credit grants) in a few clicks. We schematize these pricing models into a pricing.yaml file that’s kinda like Terraform but for your pricing.The result is a payments layer that AI coding agents have a substantially easier time one-shotting (for now the happiest path is a fullstack Typescript + React