Claude Fable Demo: Relentlessly Proactive Bug Fixing with Browser Automation

Simon Willison's Claude Fable is relentlessly proactive post demonstrates how Claude Fable 5 autonomously diagnosed a horizontal scrollbar bug in Datasette Agent. After telling it to check dependencies, Fable took unexpected actions — opening browser windows, injecting JavaScript, and even writing a custom CORS web server — all without explicit instructions.
Key Behaviors Observed
- Browser window detection: Fable used
uv run --with pyobjc-framework-Quartzto enumerate macOS windows, filtering for Safari windows containing expected strings (e.g.,textarea). It then usedscreencapture -x -o -l [window_id]for screenshots. - Template injection: To trigger a modal dialog (which normally requires a keyboard shortcut), Fable edited Datasette's templates to inject
<script>window.addEventListener('load', function() { setTimeout(function() { document.dispatchEvent(new KeyboardEvent('keydown', {key: '/', bubbles:true})); },1200); });</script>. This simulated the/key 1.2 seconds after page load. - Custom CORS web server: Fable wrote a Python HTTP server using
http.server(standard library) running on127.0.0.1:9999. It accepted POST requests with JSON, wrote to/tmp/diag.json, and setAccess-Control-Allow-Origin: *headers — allowing JavaScript on the test page to send diagnostic data back.
How It Worked
Fable identified the scrollbar bug was likely in a dependency (Datasette itself). It edited a local template to auto-trigger the dialog, opened Safari with a freshly generated test HTML page, took a screenshot via screencapture, and ran JavaScript in the browser that posted measurements to its own local web server. All of this was done autonomously — Willison only gave it the initial prompt and a screenshot.
This showcases Fable's relentless proactivity: it invents workarounds, instruments browsers, and orchestrates multi-step debugging pipelines without being told to.
📖 Read the full source: HN AI Agents
👀 See Also

Integrating Local LLM Agents with ComfyUI for Natural Language Batch Image Generation
A developer shares how they wired their local OpenClaw agent to ComfyUI, enabling natural language commands for batch image generation workflows. The integration uses a custom agent skill that maps English requests to ComfyUI workflow JSON and handles API communication.

SuperHQ: Run AI coding agents in isolated microVM sandboxes
SuperHQ is an open source Rust/GPUI app that runs AI coding agents (Claude Code, OpenAI Codex, Pi) in isolated microVM sandboxes. Each agent gets a full Debian VM, mounts project dirs read-only, and never sees host API keys — they're injected via an auth gateway proxy.

Claude Code HUD: Terminal Dashboard for Monitoring AI Coding Sessions
claude-code-hud is a terminal dashboard that provides real-time monitoring for Claude Code sessions, showing context window usage, API rate limits, and file changes without requiring an IDE. Run it with npx claude-code-hud.

OpenClaw skill reduces accessibility tree tokens from 600K to 1.3K for ad-heavy sites
A developer built an OpenClaw skill that uses ML-based element ranking to prune accessibility trees, cutting slickdeals.com from ~598K tokens to ~1.3K tokens by keeping only the top ~50 actionable elements.