Posts
All the articles I've posted.
-
Which Predictor? How GEPA Optimizes a Multi-Agent DSPy Program
A multi-agent DSPy program is really several prompts in a trench coat. Here is how GEPA figures out which agent it is improving, and how it hands the better prompt back.
-
LLM Optimization Is a Search Problem, and DSPy Makes It Easy
I tried seven ways to make a DSPy program faster and cheaper: three adapters, TOON, a custom adapter I almost wrote, JSON Patch, and finally diffs. Most lost. The real lesson was that DSPy and GEPA made the search cheap enough to run.
-
You won't be talking to AI in natural language for too long
Natural language will make AI accessible. Expert language will make it powerful.
-
Teaching Codex to Test a Voice-First Calendar
How I got Codex, FlowDeck, XCUITest, Loopback, and a local backend to test KIN's voice calendar path end to end.
-
Setting up Google sign in for Chrome extensions with Supabase
The least painful setup I found: Chrome owns the auth window, Supabase owns OAuth and PKCE, and a tiny relay page sends the result back.
-
Helix: Closing the Loop on DSPy Programs
Why I think DSPy programs need a managed optimization loop, not scattered experiments.
-
The Introvert Misdiagnosis: When Avoidance Gets Mistaken for Personality
Introversion and diminished social skills can look identical from the outside, but they are not the same thing.
-
Is Data Curation the New Feature Engineering?
Drawing parallels between Feature Engineering in traditional ML and Data Curation in AI Engineering.
-
Waiting for the Let's Encrypt Moment for Content Authenticity
Content Authenticity is missing the catalyst that made HTTPS Universal.
-
Strategy and Program: Two Concepts for working with DSPy
Introducing two Nouns that make working with DSPy clearer.