Claude Fable 5's Playwright loop catches bugs before the developer sees them
Every URL the pipeline pulled into ranking for this issue — primary sources plus the supporting and contradicting findings each Researcher returned. Inline citations in the issue point back here.
Sources
One-shotting a Raccoon Heist game using Claude Fable 5 simonwillison.net
Back in 2024 I tweeted screenshots of a game concept generated by GPT-3 and some concept “art” created using DALL-E. Today, on the fourth anniversary of that tweet, I decided to see if Claude Fable 5 (running in Claude Code for web ) could build the entire game from the content of that tweet. It did a pretty good job of it! You can play the game here . Here’s the GitHub repo , and a short video demo: Your browser does not support HTML5 video. How I built this This is the August 5th, 2022 tweet…
References
Vellum AI — Fable 5 benchmarks explainer vellum.ai
Claude Fable 5 achieved a top-tier pass rate of 80.3% on SWE-bench Pro… priced at $10 per million input tokens and $50 per million output tokens.
DataCamp — Claude Opus 5 vs Fable 5 datacamp.com
The cheaper Opus 5 ($5/$25 pricing) actually surpasses [Fable 5] on certain benchmarks, including a 96.0% score on SWE-bench Verified compared to Fable’s 95.0%.
Creator Economy — opinionated guide to AI coding tools creatoreconomy.so
LLMs lack an inherent understanding of game architecture, often leading to a ‘stuck state’… ‘vibe coding’ often favors momentum over structure, resulting in a ‘patchwork quilt’ of logic.
DayaAI — Raccoon Heist community roundup dayaai.com
When asked to draw a red circle around a ‘raccoon with a ham radio’ that was not present in the original image, [gpt-image-2] hallucinated both the raccoon and the circle in the new output.
ByteTunnels — Playwright for AI agents bytetunnels.com
Agents provide the LLM with a structured ‘snapshot’ of the page—often using the accessibility tree rather than raw HTML to remain token-efficient… a ‘Planner → Generator → Healer’ loop… automatically patching broken locators.
UpGuard — Claude Code GitHub Action vulnerability upguard.com
A critical vulnerability was disclosed in the official Claude Code GitHub Action that allowed attackers to hijack repositories by submitting specially crafted GitHub issues.
