A developer hid 40 bugs in a test online store and had Claude Code explore it with Playwright using three prompt styles. With a full checklist it found about 30 bugs on average for under a dollar per run; five bugs were missed by every run. The takeaway: a useful first pass before release, not a replacement for human testers.
Meta has released the weights of Muse Spark Open, a multimodal model with about 816B parameters (42B active) and a one-million-token context, aimed at coding and long agentic tasks. It is on Hugging Face and available through providers such as Together AI, Fireworks and OpenRouter, although its license restricts commercial use.
The author of a directory of AI tools for developers explains how rankings are modeled as Zod-validated data in Astro content collections. The post also covers making the site readable by chatbots and letting an AI agent ship changes without bypassing the rules.
Gemini 4 Argon is Google’s new top model, aimed at multi-step work such as coding and agentic tasks. It is available now through the Google AI Studio API at an introductory $2/$10 per million input/output tokens, doubling after November 30. Google says that inside Antigravity it increased agent code submissions and cut rollbacks.
Anthropic says its daily merges went from about 2,500 to over 30,000 in a few months because Claude writes much of the code, turning git into the bottleneck. In five months it built Scion, a version control system designed for always-online agents. It is an early look at which workflows stop scaling once agents write the code.
