Bots and Boundaries: Who do you blame when the bot defames? (Part 2)
This is Part 2 of Bots and Boundaries, a three-part series on AI agents in open source.
Claude
15 posts
I gave 3 AIs a Murder Mystery PDF: One was Sherlock, one was high and one just ghosted me 7 times
Several AI models were given the same 36-page evidence file and the same strict instructions, no hints, no hand-holding. What followed was a revealing test of how each model actually reasons under pressure, not just pattern-matches its way to a tidy answer.
Out with multitasking, in with orchestrating
The return of multitasking, but not as we knew it. Running multiple Claude Code instances simultaneously isn't the context-switching productivity killer we've been warned about for years; it's orchestration
Why AI will not kill open source
In the wake of Tailwind's dramatic layoffs and growing fears about the future of open-source software, this post examines whether AI coding agents are truly threatening the OSS ecosystem or if the panic is overblown. And it's a reaction to Andreas' idea that open source will no longer exist.
Why I switched from BugBot to Claude for code reviews
I switched from Cursor's BugBot ($40/month) to Claude Code for code reviews. Setup is straightforward in VS Code, and Claude's bug detection has been notably better. While it still flags null reference checks like most AI reviewers, the difference in catching actual bugs is significant.
Claude as tester using Playwright and GitHub MCP
Claude can now test your frontend. With a bit of config, the Playwright MCP server lets Claude run browser tests, find bugs, and even generate reusable test code. This could be a game-changer for startups without QA.