Masters3d

Blog

Back to Home

Blog

This is one body of work organized into four editorial tracks. Each track keeps a stable voice and reading rhythm, while tags connect related ideas across the whole collection.

Subscribe to the RSS feed to stay updated with new posts.

Editorial Tracks

Every post belongs to one track with its own subject, reading rhythm, and voice. The tracks follow the Quest Engine's own outline: the model, the record, then Search, Drive, and Renew. Tags connect ideas across tracks.

The Why · 10 posts

Quest Engine

The model itself: Search, Drive, and Renew, the Why, the four Ws, and how they fit together.

The four Ws · 9 posts

Field Notes

Personal history, retrospectives, portfolios, and observations from work in progress.

Search: mastery · 25 posts

Software Engineering

The craft and career: languages, code, verification, agent workflows, judgment, and growth.

Drive: autonomy · 29 posts

Engineering Systems

How teams and organizations work as systems: incidents, ownership, risk, context, and the words engineers use.

Renew: purpose · 17 posts

Human Systems

The person as a system: cognitive (attention, habit, motivation, meaning), physical (the body, energy, rest), and health (sleep, stress, burnout, recovery).

The Meta Structure: How to Read the Three Steps

A high-level map of Why, the four Ws, and How, plus the two properties that make them work: the structure is self-referencing (every step contains the whole shape) and it is a loop (the end of one cycle issues the start of the next). Which also means half the vocabulary is relative to wherever you are currently standing.

Read more →

The Primary Directive: The Objective Function as Why

Why is not a question, it is the Primary Directive, and it stands alone above the other two steps. What it is, why the general human directive is Explore/Play/Joy, how the specific human directive nests inside the general authentic one, and why Why is answered first and audited last.

Read more →

Models Are Tools: Portability, Watermarks, and the Work I Want to Keep

A few weeks of running Astra next to Opus 5 left me with three conclusions: the behavior I depend on is mostly harness and habit rather than intelligence, watermarking every output treats a shared piece of work as if the model made it alone, and I want a personal profile that travels with me so the model stops being the thing I have to learn.

Read more →

There Is No Speedup for Shared Understanding

Six months of building AI infrastructure and coaching coworkers on their agent workflows taught me the bottleneck is no longer code creation. Someone can write ten thousand lines in a day, but nobody found a way to make a colleague understand those ten thousand lines any faster than in 2019. Validation is still the vehicle through which humans actually learn a system, and that work has not been automated.

Read more →

I Am Often Wrong: The Six-Step System Hiding a Quest Engine

Boris Cherny says he loves being wrong, and lays out a six-step system for how he solves every problem. Underneath the labels, it's three moves repeated twice, and the move he treats as a footnote (Renew) is doing exactly as much work as the one he calls urgent (Drive).

Read more →

The MOOC Era Was All Exploration and No Action

Nanodegrees and massive open online courses gave me an endless exploration phase and almost no action phase. Watching someone else code feels like learning right up until you open an empty file. Exercism and Math Academy fixed that by making the first move yours.

Read more →

The Why Doc and the How Doc: Steering Agents from the Middle

Start with the code works for the software engineering circle of the Venn diagram, but a technical program manager naturally starts from the why, not the code. Once agents act like subordinates, the person steering them sits in the overlap and needs two documents: a Why doc facing outward toward the problem and stakeholders, and a How doc facing inward toward the agent's technical direction.

Read more →

Verification-Driven Development: Let Proofs of Concept Write the Spec

Spec-driven development is a vague enough term that it can mean anything from a paragraph of intent to a fully waterfalled design. I tried the fully-specified version and it backfired: it left no room for an autonomous agent to explore alternatives. What worked instead was naming the actual sequence. Build multiple proofs of concept, verify each one against something real, and only then write the design document, informed by what the proofs of concept actually showed.

Read more →

From Apple Silicon to NVIDIA AI Factories

Revisiting a 2020 Apple Silicon and AR prediction in a world where NVIDIA, AI accelerators, software ecosystems, and electricity define the next computing platform.

Read more →