If You’re Wearing More Than One Hat, Something’s Probably Wrong
Navigating competing roles in open source - why clarity about which hat you’re wearing matters.
Recent posts
Managing a manual Alexa Home Assistant Skill via the Web UI
Skip hand-editing YAML entity lists by tagging Home Assistant devices with labels and auto-generating the Alexa exposure list via an automation.
The Practitioner’s Keynote: A Look Behind the Curtain
A look at the messy reality of delivering a keynote as a practitioner, without the support teams that polish executive presentations.
Project Membership
posted on duckalignment.academy
Rituals
A personal reflection on the small, meaningful rituals of daily life, centered on the morning walk to school with my first-grade daughter.
Day 5: Microsoft Hackathon — Model Grading, Parameter Friction, and Next Questions
Pipeline runs, thread summaries graded, and model friction surfaced. Next test: can insights drive action?
Day 4: Microsoft Hackathon — Threading Failure, Recursion Repair, and Model Limits
Debugged a broken email threading approach, replaced it with a simple recursive pass, and resumed grading LLM-generated summaries.
Day 3: Microsoft Hackathon — Thread Heuristics, Importance Signals, and Agent Editing
Filtered 424 threads to ~250 candidates, added package/entity tagging, and built an agent writing editing workflow.
The Couple Across the Way
A whimsical moment observing a retired couple’s daily ritual and a surprise silly hat.
Day 2: Microsoft Hackathon — Distractions, Brainstorming, and Infrastructure
Distractions derailed metadata work; brainstormed importance heuristics and moved the MVP to SQLite for scale.