Subject
9 entries
Methodology
Bookmarks
Claude Interactive Documentation Workflow: markdown before code
A structured interview-to-implementation workflow using Claude Code: document first, then code. The methodology produces specs that keep LLMs guardrailed and documentation that doesn't require clarifying questions.
From Prompt Alchemy to Prompt Engineering: Analytic Augmentation
An essay arguing for 'analytic augmentation' — using structured logical reasoning and philosophical method to improve LLM prompts, moving from intuitive prompt tweaking (alchemy) to principled prompt design (engineering). Connects formal reasoning frameworks to practical prompt construction.
Molecular Notes: A PKM System
Molecular Notes is a PKM system built around three primitives: Sources, Atoms (established concepts), and Molecules (personal insights). Mining Atoms from Sources and combining them into Molecules creates quadratic knowledge growth through cross-linking.
Shape Up: Stop Running in Circles and Ship Work that Matters
Shape Up is Basecamp's product development methodology written by Ryan Singer — six-week cycles, fixed time with variable scope, and 'shaping' work before scheduling it. A serious alternative to Scrum for product teams that want to ship meaningful work without constant sprint theater.
Cargo Cult Analytics
A four-step framework for avoiding cargo cult analytics — the pattern of running analyses that look like data science without asking whether the questions and methods actually match. A useful corrective for teams that confuse process with rigor.
Why Machine Learning Fails
Louis Dorard's analysis of why machine learning projects fail in practice — usually not because the algorithms are wrong but because the problem setup, data quality, or evaluation approach is broken. The engineering side of ML is where most projects die.
Everything Wrong With P-Values Under One Roof
A comprehensive critique of p-values and null hypothesis significance testing — cataloguing the ways researchers misinterpret and misuse them. Part of a growing 2013 literature on the replication crisis and statistical reform.
Six Steps in Data Science
A 2013 blog post laying out six practical steps in a data science workflow — from problem framing through data collection, exploration, modeling, evaluation, and deployment. A snapshot of how practitioners were thinking about the discipline before MLOps and production ML tooling matured.
The Dangers of Cargo Cult Data Science
Forbes piece on cargo cult data science — organizations adopting the trappings of data-driven decision-making (dashboards, models, data scientists) without the epistemological rigor that makes it actually work. A 2013 critique that remains current.