Mostly Technical Sweet Hang #3: Matching Tattoos w/ John O'Nolan
16 snips
Nov 20, 2025 
In this engaging conversation, John O'Nolan, founder of Ghost, dives into his passion for side projects and modernizing RSS. He shares insights on his double Laravel New strategy and how he leverages Claude AI for rapid development. John discusses his upcoming RSS reader and the challenges of existing solutions. He also touches on the intricacies of building features, optimizing code, and the balance between leading a sizable team and pursuing personal projects. Plus, a peek into his side-side project—a simpler applicant tracking system!
AI Snips
Chapters
Transcript
Episode notes
Embrace Occasional AI Messiness
- Prompting too tightly limits AI creativity and potential; occasional messy outputs indicate you're under-constraining it.
- Let the model make mistakes sometimes to discover better solutions or ideas.
Limit Early Signups To Iterate Faster
- Roll out new tools to a small group of users first to avoid support overload and large migration pain.
- Keep early access limited so you can iterate without public pressure.
Smarter Polling Cuts Load And Cost
- Adaptive polling based on a publisher's cadence reduces unnecessary checks and resource use.
- Dynamic backoff lets you poll active feeds frequently and dormant feeds rarely.