Technical Archives

Journal.

Documented engineering logs, systemic problem-solving, and theoretical experiments.

search
rocket_launch
article Log Entry 26.04.01

How Does AI Think? Part 5 — AI in the Wild: Applications, Building Blocks & the Developer's Toolkit

From theory to practice: how AI is transforming healthcare, science, code generation, and creative arts. Build your own AI-powered apps with RAG, vector databases, LangChain, and local models. Explore the open-source ecosystem, deployment strategies, and what it means to be a developer in the age of AI. Interactive demos: a RAG pipeline simulator, vector similarity search, model size calculator, AI application gallery, and a build-your-own-agent flowchart.

AI applications +6
arrow_forward
slideshow
slideshow Presentation 26.03.01

Presentation Demo - 5 Browser Slides

A presentation-type blog post that behaves like a mini PowerPoint in the browser. Includes 5 demo slides: hello, hi, hh, ii, jj.

presentation slides +1
arrow_forward
school
slideshow Presentation 26.03.01

Wang et al. (2024) — GenAI + TPB: Faktor Niat Mahasiswa

Presentasi 7 slide: Theory of Planned Behavior + AI Literacy untuk menjelaskan niat mahasiswa menggunakan GenAI. Attitude adalah faktor paling dominan.

research AI +3
arrow_forward
model_training
article Log Entry 26.03.01

How Does AI Think? Part 2 — From Neural Nets to Transformers

The deep learning revolution: backpropagation, CNNs, RNNs, word embeddings, attention, transformers, GPT, and the age of foundation models. Interactive demos include a CNN feature-map visualiser, an attention heatmap, and a live token predictor.

AI deep learning +4
arrow_forward
smart_toy
article Log Entry 26.03.01

How Does AI Think? Part 3 — Agents, Reasoning & the Road to AGI

Reinforcement learning from Atari to AlphaGo, AI agents that use tools, reasoning models that think step-by-step, the open-source revolution, safety & alignment, and the question of AGI. Interactive demos: train a Q-learning grid agent, build a ReAct tool-use chain, explore chain-of-thought reasoning, and simulate an alignment debate.

AI reinforcement learning +5
arrow_forward
build
article Log Entry 26.03.01

How Does AI Think? Part 4 — Under the Hood: Tokenizers, Training & the Art of Making AI Work

Peek behind the curtain: how text becomes tokens, how embeddings capture meaning, how models are trained at scale, fine-tuned with LoRA & RLHF, optimised for inference, prompted effectively, and extended to see images and hear audio. Interactive demos: a live BPE tokenizer, embedding space explorer, quantization impact visualiser, KV-cache animation, and prompt engineering playground.

AI tokenization +5
arrow_forward
edit_note
article Log Entry 26.02.28

Hello World — Welcome to My Blog

A first blog post to kick things off. Why I decided to start writing and what you can expect from this space.

personal blogging
arrow_forward
psychology
article Log Entry 26.02.28

How Does AI Think? — From Logic Machines to Linear Regression

An interactive 750-year journey through the history of AI — from Ramon Llull's rotating discs to gradient descent. Includes hands-on demos: Boolean gates, a perceptron trainer, BFS/DFS visualization, a mini-ELIZA chatbot, live linear regression with Chart.js, and a 3D loss surface in Three.js.

AI algorithms +4
arrow_forward