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

NerfGuard: A Classifier That Routes Coding Requests to Cheaper Models, Cutting Spend 3x
NerfGuard uses a fast classifier to route coding agent requests to the least expensive model and reasoning depth needed, yielding 3x usage for the same spend. Includes token optimizations.

CodeTalk: Open-source tool adds spoken reflections to Claude Code CLI
CodeTalk is a Python tool that adds spoken observations to Claude Code CLI responses using Microsoft's edge-tts. It extracts text embedded by Claude and plays it through speakers with natural-sounding neural TTS.

TranscriptionSuite v1.1.2 adds WhisperX, NeMo, and VibeVoice models
TranscriptionSuite v1.1.2 now offers three transcription pipelines: WhisperX with PyAnnote diarization, NeMo models (Parakeet & Canary) with PyAnnote diarization, and VibeVoice models with built-in diarization. The update includes a model manager, parallel processing, shortcut controls, and a 24kHz recording pipeline for VibeVoice.

TUI Studio: Visual Terminal UI Design Tool in Alpha
TUI Studio is a Figma-like visual editor for designing terminal user interfaces with drag-and-drop components, real-time ANSI preview, and planned export to six frameworks including Ink, BubbleTea, and Textual. Currently in alpha with non-functional exports, it's available for macOS, Windows, and Docker.