3rd layer

The Curse of Talent, the Blessing of Temperament

Wed, 15 Jul 2026 00:00:00 +0000

Is talent a blessing or a trap? An analysis of how talent conditioned by short reward cycles sabotages long-term effort — and a look beneath what we call grit, at the two engines underneath: taste and lack.

Artificial Life and General System Theory

Sun, 12 Jul 2026 00:00:00 +0000

As an undergrad I opened ‘General System Theory’ expecting the ultimate design principle, and found biology instead. Half a century ago Bertalanffy said life is not matter but organization — and Lenia proves it on a computer.

Personal Information You Can Extract From a Genome

Sun, 05 Jul 2026 00:00:00 +0000

The Y chromosome and the surname are both inherited down the paternal line. That single fact was enough to recover real identities from ‘anonymous’ genomes, as shown in this 2013 Science paper.

A ReLU Network Is One Giant Piecewise-Affine Function

Fri, 03 Jul 2026 00:00:00 +0000

A network with ReLU activations secretly carves input space into polytope pieces and, on each piece, collapses into exactly one affine map. This post builds that view up from a single neuron to interactive demos.

Shrinking Models by Sharing Weights — K-Means-based Quantization

Sat, 06 Jun 2026 00:00:00 +0000

Group a neural network’s weights into a few representative values with K-Means, and you can shrink the model several-fold with almost no accuracy loss. We explore it with an interactive widget where you watch the clusters converge and the storage shrink in real time. (Deep Compression, Han et al. 2016)

Integer-Arithmetic-Only Neural Network Inference — Linear Quantization

Sat, 09 May 2026 00:00:00 +0000

Beyond storing weights as integers — running the multiplications and additions entirely in integer arithmetic at inference. We connect reals and integers with the affine map r = S(q − Z), and explore it with a widget where you change the scale and zero point and watch the quantization error. (Jacob et al. 2018, the basis of TFLite integer quantization)

Data Types in the Deep Learning Era

Sun, 12 Apr 2026 00:00:00 +0000

INT8, FP16, BF16, FP8, FP4 — what do the data types you keep seeing in deep learning actually mean, and how do bits turn into numbers? We take them apart one by one, with widgets where clicking a bit updates the formula and value in real time.

Setting Up Korean IME (kime) on AWS DCV

Sat, 21 Feb 2026 00:00:00 +0000

How I fixed the issue where kime Korean IME only types one character before reverting to English on AWS DCV remote desktop.

Shooting Dead Enemies: Why Academia Keeps Fighting Zombie Debates

Sun, 01 Feb 2026 00:00:00 +0000

Why we keep resurrecting settled debates, and the irony of this very essay doing the same

runpod-log — A CLI Log Viewer for RunPod

Wed, 28 Jan 2026 00:00:00 +0000

A CLI tool to fetch and monitor logs from RunPod GPU Pods in real-time.

My Father's Technology Timeline

Sun, 25 Jan 2026 00:00:00 +0000

In 1990, my father bought a computer for his five-year-old son.

Do LLMs Have Thinking Styles? REI-40 Experiment on 5 Frontier Models

Sat, 24 Jan 2026 00:00:00 +0000

We administered the REI-40 dual-processing personality inventory to 5 frontier LLMs. The results reveal distinct ’thinking style’ profiles — from neutral responders to rational enthusiasts.

psyctl — An LLM Personality Steering Tool

Sat, 24 Jan 2026 00:00:00 +0000

Building an open-source tool that controls LLM personality using Steering Vectors.

Self-Actualization Is No Different from a Pufferfish's Sand Circle

Sat, 24 Jan 2026 00:00:00 +0000

Kenrick’s evolutionary reconstruction of Maslow’s hierarchy, and how digital services exploit our evolved motivational systems.

Two Minds in One Brain: Why We Act Irrationally Even When We Know Better

Sat, 24 Jan 2026 00:00:00 +0000

Why can’t you resist that midnight snack during a diet? Two independent processing systems live inside your head—one that calculates and one that feels. A look at Pacini & Epstein’s 1999 study on the Rational-Experiential Inventory.

The Idea That Lost and Came Back: Skinner, Chomsky, and the Talking Machines

Thu, 20 Nov 2025 00:00:00 +0000

One man argued that language was a matter of reward and habit, and lost famously. Half a century later, the machines that talk to us are trained with exactly that: reward.

Sentence Reranking Using LLM Attention Maps

Fri, 12 Sep 2025 00:00:00 +0000

Leveraging what the LLM already knows. An experiment extracting document relevance signals from Attention Maps to rerank sentences, along with a survey of related papers.

Steering GPT-2's Emotions with Sparse Autoencoders

Sun, 16 Feb 2025 00:00:00 +0000

Finding emotion-related features in GPT-2 using OpenAI’s pretrained SAE, then training one from scratch. Feature patching turns ‘good person’ into ‘shit’.

K-means, GMM, EM: Three Nested Russian Dolls of Clustering

Sun, 10 Dec 2023 00:00:00 +0000

K-means is actually an extreme case of GMM, and GMM is the canonical application of the EM algorithm. How these three connect within a single framework, and how information geometry explains the relationship.

Information Geometry: How AI Learns Most Efficiently

Wed, 13 Jan 2021 00:00:00 +0000

Just as Newton’s F=ma describes the physical world, information geometry describes how AI learns. An intuitive guide for beginners.

About

Mon, 01 Jan 0001 00:00:00 +0000

Software developer based in Seoul.