Playwright

Evidence (11)

• 2Simon Willison·9/26/2026product_launch
  Claude Creates a Kākāpō Pixel Art Party Video

  Simon Willison described using Claude Opus 5.5 to generate an animated pixel-art HTML5 canvas scene of kākāpō parrots, based on reference photos. He then used Claude Code with Playwright to load the page, trigger clicks, and record a short video for a keynote slide.

• 6Hacker News·9/24/2026product_launch
  Opus 5.5 used to generate explainer videos

  The post shows a system that uses Anthropic Claude Opus 5.5 to generate explainer-style videos from a URL or prompt, with no manual editing. It describes a serverless workflow on OpenComputer that renders deterministic videos in a fresh microVM using Playwright, Chromium, and ffmpeg, then uploads the result to Blob storage.

• 6Hacker News·9/18/2026framework_update
  Stagehand speeds up Playwright and cuts token use

  Browserbase says it has made its Stagehand/Playwright workflow run about 2x faster while reducing token usage by 80%. The change is presented as an efficiency improvement for browser automation and AI-assisted testing or agent workflows built on Playwright.

• 2Simon Willison·9/13/2026framework_update
  shot-scraper 1.12 adds WebP screenshot support

  Simon Willison released shot-scraper 1.12 with support for saving webpage screenshots as WebP files. The new --quality option controls WebP compression, and images are lossless by default when quality is not specified.

• 7The New Stack·9/10/2026open_source
  AWS open-sources Pizza Bot for managing background AI agents

  AWS has released Pizza Bot, an open-source desktop app that gives developers an email-style inbox for monitoring and triaging background AI agents. The project is self-hosted and uses LangGraph-based persistence so agent work can pause, resume, and surface updates even when the user is away.

• 5The New Stack·9/3/2026research
  PhiloLabs built a virtual Union Square with AI agents for $33

  PhiloLabs used Claude Fable 5.1 agents to build a browser-based 3D reconstruction of San Francisco’s Union Square from geographic data and reference images. The experiment paired Playwright screenshot comparisons with agent review loops to catch visual issues that conventional tests would miss, and the full run reportedly cost about $33 in API usage.

• 5GitHub Blog·8/24/2026product_launch
  GitHub adds an alt text plugin to improve accessibility checks

  GitHub describes how it built an alt text plugin for the GitHub Accessibility Scanner to catch not only missing alt text but also low-quality cases such as filenames, placeholders, and repeated labels. The post explains the tradeoff between deterministic rules and model-based judgments, and how the team tuned the checker to avoid false positives that would cause developers to disable it.

• 7The New Stack·8/21/2026product_launch
  Anthropic adds structured Browser Use for Claude

  Anthropic introduced Browser Use, a browser tool that lets Claude interact with web pages through the accessibility tree instead of screen coordinates. The release also adds support for batching multiple browser actions in one turn and brings Computer Use, Skills API, and Files API to general availability.

• 8Hacker News·8/20/2026framework_update
  Bun 1.4 expands Node.js compatibility and adds new tooling

  Bun 1.4 adds 1,517 more passing Node.js test cases, improving compatibility with the Node.js ecosystem and fixing over 2,900 issues. It also brings new features such as parallel run/test commands, audit and package management utilities, and support for tools including Playwright, Vitest, and OpenTelemetry.

• 6Hacker News·7/4/2026research
  Agentic coding, testing, and the risks of synthetic repros

  The post describes hands-on experience using AI coding agents for debugging and testing, including a case where an agent produced a convincing but fabricated reproduction of a bug in a fake browser environment. It argues that agentic workflows can be powerful for testing and triaging issues, but also prone to errors, hallucinations, and misleading outputs that require human verification.

• 5Simon Willison·6/30/2026framework_update
  shot-scraper adds storyboard-based video recording for web demos

  shot-scraper 1.10 introduces a new `video` command that uses a YAML storyboard and Playwright to record scripted interactions with a web application. The post shows it being used to capture a demo of Datasette features, including bulk inserting rows and creating a table from pasted data.