הרווח שבין מחיאות הכפיים
ה-ma של מיאזאקי, ‘שדה הריקות’ של נישיטאני וה״מה״ של משה מצביעים כולם על דבר אחד: המרחב הפנוי שבו אפשר לקבל.
The Space Between the Claps
Miyazaki’s ma, Nishitani’s field of emptiness, and Moshe’s mah all point to one thing: the open space where something can be received.
Pairing Elixir with Cheese, Part II: In Search of Something Salty
Embeddings taught my Elixir cheese catalog that cabernet means red wine, but a search for salty proved similarity isn’t the same as a good pairing.
Pairing Elixir with Cheese
I built a cheese catalog in Elixir, letting an LLM fill in flavor profiles and pairings — then used pattern matching to keep the data honest.
Personal Ops: Learning From Its Own Mistakes
A voice note got misread as a literal agenda item called ‘whatever I missed.’ The fix turned into a general system for catching ambiguous commands, logging corrections, and a plan to move routine parsing off the API and onto a local model.
My Arabic Music Liner Notes
Twenty Arabic songs across Tunisian, Algerian, Levantine, and Sudanese dialects — liner notes for training your ear, song by song.
Count First, Interpret Second
My personal-ops bot’s weekly digest kept turning noisy logs into confident diagnoses. The fix was one rule: count first, interpret second, diagnose cautiously.
Reed, Not Cedar: Building a Productivity System That Bends With You
I built a Telegram bot to offload my executive function and accidentally gave myself a taskmaster. So I rebuilt it around one rule from the Talmud and the Daode Jing: be a reed, not a cedar — firm but yielding, advisory not prescriptive.
Don’t Clip Your Wings: On Building Systems That Push You Toward Greatness
Completion rate is a trap. The moment your productivity system scores you on what percentage of commitments you finish, the rational move is to stop writing down anything you might actually fail at. I ran into this building my own personal ops system, and it turns out fixing it means thinking about Item Response Theory, Glicko ratings, and the Sharpe ratio.
Personal Ops: Capture, Digest, Adapt, Propose
Two years ago my Elul accountability experiment half-worked. The problem was friction, not motivation — and I had no mechanism to adjust expectations based on actual performance. So I built one: voice capture via Telegram, weekly LLM digest, and a daily agenda calibrated to what I’ve actually been completing versus missing.