Auditing 13GB of Business Files with Fable 5 Multi-Agents
tomcrawshaw01 · x · 2026-07-03
The author ran 8 simultaneous agents using Anthropic's Fable 5 to conduct a comprehensive audit of 13GB of business files (including automation scripts, quotes, and personal knowledge bases). The AI gave a C- rating and uncovered several previously unnoticed issues, such as exposed API keys left over from the early Claude Code era and background scripts running idle for a long time.
More from coding & agent
- Agent verified 'success' after double-voting: a lesson in harness vs model bugs — TejasKumar_ · 2026-10-26
- diginomica: agentic automation hype is overdone, and 'The Hackening' of enterprise security has begun — jonerp · 2026-10-26
- 'Vibe verification': ~60% of AI-written formal specs prove the wrong property — basedjensen · 2026-10-26
- Devin launches Security suite powered by Claude Mythos with $100M+ credits — DevinAI · 2026-10-26
- HackBench injects reward hacks into agent trajectories to stress-test monitors — DanielKhashabi · 2026-10-26
- Hugging Face ships hf CLI updates: deduped cache saves 19GB, faster buckets, retryable GPU jobs — yb2698 · 2026-10-26