The Ruby AI Podcast Sublayer and Artificial Ruby with Scott Werner
9 snips
Jun 10, 2025 Scott Werner, an author and creator of the Sublayer AI-agent framework, dives into the evolving landscape of AI in the Ruby community. He discusses the innovative 'generators + actions' structure of Sublayer and the quirky Monkey’s Paw framework that turns Markdown wishes into web pages. The conversation also explores the tension between AI and human input in development, particularly the challenges of AI code generation. Plus, Scott emphasizes how community engagement fuels creativity while adapting to the rapid changes AI brings to the coding process.
AI Snips
Chapters
Transcript
Episode notes
Ruby Suits AI Experimentation
- Ruby's expressiveness and dynamism make it ideal for rapid AI-era experimentation and prototyping.
- Scott argues dynamic languages let you test ideas fast without heavy engineering overhead.
Monkey's Paw Generates First Drafts
- Scott describes Monkey's Paw: Markdown 'wishes' become real web pages via an LLM.
- Joe used it to generate a presentation's first version and found the results surprisingly useful.
See LLMs As Creative Collaborators
- Treat LLM output as raw creative material to iterate on, not finished work to paste unchanged.
- Scott compares the process to Paul McCartney noodling and iterating with collaborators to refine ideas.