Archives

2026 ³⁰

September ¹

Give Frontier Models Frontier Problems

September 6, 2026 · 20 min · Sae-Hwan Park

August ⁷

What I Kept From Stata

August 29, 2026 · 16 min · Sae-Hwan Park

What Does Claude’s Text Watermark Actually Tell Us?

August 21, 2026 · 2 min · Sae-Hwan Park

How I Take Games Apart

August 15, 2026 · 26 min · Sae-Hwan Park

JSM 2026 Part 3: What Statistics Contributes Beyond Prediction

August 9, 2026 · 11 min · Sae-Hwan Park

JSM 2026 Part 2: The Statistics I Found at JSM 2026

August 8, 2026 · 15 min · Sae-Hwan Park

JSM 2026 Part 1: Choosing What to Learn at My First Statistics Conference

August 7, 2026 · 9 min · Sae-Hwan Park

What Should Synthetic Medicare Data Be Faithful To?

August 1, 2026 · 23 min · Sae-Hwan Park

July ⁴

Research Python (Also) Needs Explicit Contracts

July 24, 2026 · 16 min · Sae-Hwan Park

Making Institutional Microeconomics Playable

July 17, 2026 · 16 min · Sae-Hwan Park

Fidelity of Consequence: What Capitalism 2 Taught Me About Modeling Systems

July 11, 2026 · 24 min · Sae-Hwan Park

A Management Game Where the Market Talks Back

July 3, 2026 · 19 min · Sae-Hwan Park

June ³

Why I Design CLI-First Software

June 19, 2026 · 20 min · Sae-Hwan Park

Repository Context Should Be a Fact Layer

June 13, 2026 · 21 min · Sae-Hwan Park

The Score Is Not Enough: Building Reviewable Risk-Adjustment Software

June 6, 2026 · 18 min · Sae-Hwan Park

May ⁴

Software Engineering as the Interface Between Humans and AI

May 30, 2026 · 14 min · Sae-Hwan Park

Why Mojo Finally Became Interesting to Me

May 22, 2026 · 21 min · Sae-Hwan Park

The Error Path Should Be a Type

May 9, 2026 · 18 min · Sae-Hwan Park

Python vs. Rust: Aren’t We Asking the Wrong Question?

May 2, 2026 · 18 min · Sae-Hwan Park

April ⁴

Why FP-Style Design Feels Highly Effective With Agentic Coding

April 24, 2026 · 12 min · Sae-Hwan Park

Where to Start: An FP-Style Engineering Workflow in Python

April 17, 2026 · 12 min · Sae-Hwan Park

From Tool-Calling Loops to Repository Contracts: Why Meta Harness Is Born

April 11, 2026 · 12 min · Sae-Hwan Park

The Claude Code Leak: What the Source Code Actually Reveals

April 3, 2026 · 20 min · Sae-Hwan Park

March ⁴

How to Build a Good NLP Baseline When Small Cues Matter

March 28, 2026 · 20 min · Sae-Hwan Park

Spec vs. Code in the Age of AI Agents: Lessons from Symphony and CodeSpeak

March 20, 2026 · 13 min · Sae-Hwan Park

The Narrowing Entrance: What Anthropic’s Report Actually Means

March 14, 2026 · 7 min · Sae-Hwan Park

Introduction to aTPR: Correcting for Risk Heterogeneity in Fairness Evaluation

March 7, 2026 · 14 min · Sae-Hwan Park

February ¹

Equal Opportunity Under the Microscope: Why Fairness Evaluation Needs Risk Awareness

February 28, 2026 · 7 min · Sae-Hwan Park

January ²

Why NLP Still Matters in the Age of AI Agents

January 17, 2026 · 9 min · Sae-Hwan Park

From Vague to Vivid

January 11, 2026 · 7 min · Sae-Hwan Park

2025 ⁴⁴

December ⁴

My Winter NLP Journey

December 27, 2025 · 20 min · Sae-Hwan Park

Post-mortem on Cloudflare Outage on Nov 2025: When a Single Assumption Went Global

December 19, 2025 · 20 min · Sae-Hwan Park

AoC 2025 Final Reflection: Serious FP Journey

December 14, 2025 · 9 min · Sae-Hwan Park

AoC 2025 Midpoint Review: How F# Clicks For Me

December 6, 2025 · 5 min · Sae-Hwan Park

November ⁴

Working Toward Robustness (F# c-MLE Project Part 2)

November 23, 2025 · 13 min · Sae-Hwan Park

My First F# Project: Implementing Constrained Optimization from Scratch

November 21, 2025 · 18 min · Sae-Hwan Park

Why I’m Learning F# (And Why It May Matter For You Data Scientists)

November 14, 2025 · 9 min · Sae-Hwan Park

Functional Programming in Python

November 8, 2025 · 17 min · Sae-Hwan Park

October ²

Why BRR Works: Deep Dive Into Hadamard Matrix

October 31, 2025 · 30 min · Sae-Hwan Park

How I Learned Monads: Not Through Haskell But Through Rust

October 25, 2025 · 17 min · Sae-Hwan Park

September ³

Building a Modern MICE Imputer: Episode 1

September 19, 2025 · 13 min · Sae-Hwan Park

Beyond Bootstrap: Why Survey Data Demands Specialized Variance Estimation

September 14, 2025 · 21 min · Sae-Hwan Park

Beyond Performance: Why Polars Represents a Paradigm Shift from pandas

September 6, 2025 · 24 min · Sae-Hwan Park

August ⁵

Why Memory-Safe Languages Matter: Lessons from C, Python, and Rust

August 29, 2025 · 17 min · Sae-Hwan Park

Announcement: Rust Security Bootcamp!

August 23, 2025 · 9 min · Sae-Hwan Park

AOC 2024 Postmortem: What I Actually Learned Throughout 50 Stars

August 15, 2025 · 11 min · Sae-Hwan Park

Rust Handshake Challenge #4: The Postmortem

August 8, 2025 · 19 min · Sae-Hwan Park

Rust Handshake Challenge #3: Event-Driven Handshaking

August 1, 2025 · 19 min · Sae-Hwan Park

July ⁵

Rust Handshake Challenge #2: Threading the Needle of Concurrency

July 25, 2025 · 15 min · Sae-Hwan Park

Rust Handshake Challenge #1 Simple Single Threading

July 19, 2025 · 20 min · Sae-Hwan Park

Quest for Better Blogging: #3 Building the Actual Blog

July 11, 2025 · 12 min · Sae-Hwan Park

Quest for Better Blogging: #2 The Architecture of Better Publishing

July 6, 2025 · 11 min · Sae-Hwan Park

Quest for Better Blogging: #1 Why I’m Evolving Beyond Medium

July 4, 2025 · 10 min · Sae-Hwan Park

June ³

The Other Path: Population-Average Models and GEE

June 27, 2025 · 18 min · Sae-Hwan Park

Inside Mixed Effect Model

June 20, 2025 · 12 min · Sae-Hwan Park

How Factor Analysis and PCA Actually Differ

June 13, 2025 · 10 min · Sae-Hwan Park

May ⁵

A Second Look at Linux: Reflections from 2025

May 30, 2025 · 13 min · Sae-Hwan Park

Writing Maintainable Array Code: When NumPy Isn’t Enough

May 23, 2025 · 15 min · Sae-Hwan Park

How I Leveraged C Learning to Understand Rust Better

May 17, 2025 · 14 min · Sae-Hwan Park

The Linux-Windows Bridge I Wish I’d Discovered Years Ago

May 9, 2025 · 16 min · Sae-Hwan Park

The Quest for Heterogeneity: Understanding Conditional Average Treatment Effects (CATE)

May 3, 2025 · 23 min · Sae-Hwan Park

April ³

The Dimensional Odyssey: Navigating the Manifolds of t-SNE and UMAP

April 18, 2025 · 25 min · Sae-Hwan Park

From Bayes to ChatGPT: Journey For Statisticians To Understand Gen-AI

April 11, 2025 · 16 min · Sae-Hwan Park

Beyond the Hype: Blockchain in 2025 - The Silent Revolution

April 5, 2025 · 16 min · Sae-Hwan Park

March ⁴

The Uncanny Valley of AI-Generated Art: Technical Challenges Behind the Artificial Aesthetic

March 29, 2025 · 7 min · Sae-Hwan Park

When AI Hallucinates: Building a Verification Framework for AI-Generated Content

March 21, 2025 · 9 min · Sae-Hwan Park

How Much VRAM Do You Need for LLMs? A Detailed Guide for Training/Fine-Tuning/Inference

March 14, 2025 · 8 min · Sae-Hwan Park

From Skeptic to Believer: How Diffusion Models Are Reshaping Language Generation

March 7, 2025 · 7 min · Sae-Hwan Park

February ⁴

DeepSeek R1, A New Chapter in Inference-Time Scaling for Reasoning Models : Reviewing DeepSeek (Part 2)

February 14, 2025 · 11 min · Sae-Hwan Park

Incremental Evolution Rather Than Radical Revolution: Reviewing DeepSeek (Part 1)

February 8, 2025 · 9 min · Sae-Hwan Park

Beyond Copying: Understanding the OpenAI-DeepSeek AI Controversy

February 2, 2025 · 5 min · Sae-Hwan Park

Unraveling Knowldge Distillation in AI/ML Models

February 1, 2025 · 7 min · Sae-Hwan Park

January ²

Rethinking the Monty Hall Problem: How to Get Along With Cognitive Bias

January 20, 2025 · 5 min · Sae-Hwan Park

Implementing Interfaces for an LC-3 Assembler in C

January 10, 2025 · 8 min · Sae-Hwan Park

2024 ⁴

December ⁴

Data Structures Deep Dive: Building an LC-3 Assembler

December 30, 2024 · 9 min · Sae-Hwan Park

Architectural Choices in Building LC-3 Assembler

December 28, 2024 · 9 min · Sae-Hwan Park

Diving Deeper into LC-3: From Opcodes to Machine Code

December 27, 2024 · 8 min · Sae-Hwan Park

Why I’m Learning C and LC-3 (Despite Being an AI/ML Person)

December 25, 2024 · 5 min · Sae-Hwan Park

2026 30

September 1

Give Frontier Models Frontier Problems

August 7

What I Kept From Stata

What Does Claude’s Text Watermark Actually Tell Us?

How I Take Games Apart

JSM 2026 Part 3: What Statistics Contributes Beyond Prediction

JSM 2026 Part 2: The Statistics I Found at JSM 2026

JSM 2026 Part 1: Choosing What to Learn at My First Statistics Conference

What Should Synthetic Medicare Data Be Faithful To?

July 4

Research Python (Also) Needs Explicit Contracts

Making Institutional Microeconomics Playable

Fidelity of Consequence: What Capitalism 2 Taught Me About Modeling Systems

A Management Game Where the Market Talks Back

June 3

Why I Design CLI-First Software

Repository Context Should Be a Fact Layer

The Score Is Not Enough: Building Reviewable Risk-Adjustment Software

May 4

Software Engineering as the Interface Between Humans and AI

Why Mojo Finally Became Interesting to Me

The Error Path Should Be a Type

Python vs. Rust: Aren’t We Asking the Wrong Question?

April 4

Why FP-Style Design Feels Highly Effective With Agentic Coding

Where to Start: An FP-Style Engineering Workflow in Python

From Tool-Calling Loops to Repository Contracts: Why Meta Harness Is Born

The Claude Code Leak: What the Source Code Actually Reveals

March 4

How to Build a Good NLP Baseline When Small Cues Matter

Spec vs. Code in the Age of AI Agents: Lessons from Symphony and CodeSpeak

The Narrowing Entrance: What Anthropic’s Report Actually Means

Introduction to aTPR: Correcting for Risk Heterogeneity in Fairness Evaluation

February 1

Equal Opportunity Under the Microscope: Why Fairness Evaluation Needs Risk Awareness

January 2

Why NLP Still Matters in the Age of AI Agents

From Vague to Vivid

2025 44

December 4

My Winter NLP Journey

Post-mortem on Cloudflare Outage on Nov 2025: When a Single Assumption Went Global

AoC 2025 Final Reflection: Serious FP Journey

AoC 2025 Midpoint Review: How F# Clicks For Me

November 4

Working Toward Robustness (F# c-MLE Project Part 2)

My First F# Project: Implementing Constrained Optimization from Scratch

Why I’m Learning F# (And Why It May Matter For You Data Scientists)

Functional Programming in Python

October 2

Why BRR Works: Deep Dive Into Hadamard Matrix

How I Learned Monads: Not Through Haskell But Through Rust

September 3

Building a Modern MICE Imputer: Episode 1

Beyond Bootstrap: Why Survey Data Demands Specialized Variance Estimation

Beyond Performance: Why Polars Represents a Paradigm Shift from pandas

August 5

Why Memory-Safe Languages Matter: Lessons from C, Python, and Rust

Announcement: Rust Security Bootcamp!

AOC 2024 Postmortem: What I Actually Learned Throughout 50 Stars

Rust Handshake Challenge #4: The Postmortem

Rust Handshake Challenge #3: Event-Driven Handshaking

July 5

Rust Handshake Challenge #2: Threading the Needle of Concurrency

Rust Handshake Challenge #1 Simple Single Threading

Quest for Better Blogging: #3 Building the Actual Blog

Quest for Better Blogging: #2 The Architecture of Better Publishing

Quest for Better Blogging: #1 Why I’m Evolving Beyond Medium

June 3

The Other Path: Population-Average Models and GEE

Inside Mixed Effect Model

How Factor Analysis and PCA Actually Differ

May 5

A Second Look at Linux: Reflections from 2025

Writing Maintainable Array Code: When NumPy Isn’t Enough

How I Leveraged C Learning to Understand Rust Better

The Linux-Windows Bridge I Wish I’d Discovered Years Ago

The Quest for Heterogeneity: Understanding Conditional Average Treatment Effects (CATE)

2026 ³⁰

September ¹

August ⁷

July ⁴

June ³

May ⁴

April ⁴

March ⁴

February ¹

January ²

2025 ⁴⁴

December ⁴

November ⁴

October ²

September ³

August ⁵

July ⁵

June ³

May ⁵

April ³

March ⁴

February ⁴

January ²

2024 ⁴

December ⁴