-
Two Hours vs. One Question
-
Building a JSON File Index for Safer Chunking Experiments
-
Sketching a Chatbot UI That Builds a Canvas
-
Wait, CLAUDE.md Is Actually a Thing?
-
Weekend Processing Marathon
-
Building AI That Learns from Every Pipeline Run: Part 2
-
A Curious Fix for Summaries That Might Be a Product
-
Building Pipeline Insight Capture for Better ETL Debugging: Part 1
-
Why I'm Still Not Using Deepgram for Speaker ID (Yet)
-
Why I Went Local with pyannote for Speaker Diarization (vs API)
-
Trying to Bring Audio Snippets into Chatbots
-
Why I Spent My Weekend Renaming Database Tables Instead of Building Features
-
How I Labelled 5,220 Podcast Segments in One Day
-
How I Built Self-Updating Documentation with GitIngest
-
From Minutes to Meaning: How I'm Restructuring The Game Podcast
-
Failing to Prototype Extracting Alex Hormozi’s Pricing Quotes
-
I Built a Chunk Merger Validator
-
Prototype: Pricing for Episode 903
-
Migrated from SQLLite to Supabase with pgvector
-
I Built A Cross-Episode Speaker Memory
-
From Vercel to Fly.io
-
Better Code Through a Governance System
-
The JSON Body Architecture: Why I Ditched Direct Database Inserts
-
I Built a Confidence-Aware Filter and It Removed 8% of Garbage
-
I Just Wanted Better Logs. Now I Have a Whole New Architecture.
-
I had to Build a Memory-Efficient Speaker Diarization for large podcast episodes.
-
How I Combined pyannote.audio and ECAPA to Build Voice Intelligence
-
Topic Segmentation: The Next Step
-
Speaker ID, Database Timeouts & Content Hashing
-
I Built the Voice of Hormozi
-
From 'Speaker 0' to 'Alex Hormozi', a guess.
-
Pushing Things Forward (Even If I Still Can’t Match Speakers Yet)
-
Welcome